Best Open-Source Workflow Automation Tools

Self-hostable alternatives to Zapier and friends, ranked by how honest the setup story really is. Ranked by our usability scores across setup ease, docs, community health, and maturity — 167 tools reviewed in full.

01

homebrew-cask

Homebrew/homebrew-cask · ★ 22k ▲20/7d · Ruby

Homebrew Cask is the catalogue that lets Homebrew install and manage prebuilt applications, fonts, plugins, and other vendor packages. It replaces manual download-and-drag installation with repeatable `brew` commands, while each cask records where an artifact comes from and how Homebrew should install or remove it.

SetupDocsCommunityMaturity

Verdict GitHub listed 29 open issues and pull requests and a push on August 25, 2026, so Homebrew Cask is an actively maintained catalogue despite its 2016 release tag. It is the default choice for scriptable Mac application setup when Homebrew is already present, but it is not a fleet-management system and it cannot make inconsistent vendor installers uniform.

Full review →

02

checkout

actions/checkout · ★ 8.9k ▲19/7d · TypeScript

Actions Checkout is the official GitHub Action that places repository files in a workflow's workspace so later steps can build, test, or publish them. It handles authentication, shallow history, sparse checkout, submodules, Git LFS, and repositories other than the one that triggered the run.

SetupDocsCommunityMaturity

Verdict Our actions/checkout run passed all 128 tests in 10 seconds, but npm audit still found 4 vulnerabilities, including 2 high-severity findings. Use v7 for normal GitHub Actions jobs, especially privileged pull-request workflows, and pin the exact commit when supply-chain policy demands it.

Full review →

03

puppeteer

puppeteer/puppeteer · ★ 96k ▲18/7d · TypeScript

Puppeteer is a TypeScript and JavaScript library for controlling Chrome or Firefox from Node.js. It turns browser tasks such as navigation, form input, screenshots, PDF creation, debugging, and page inspection into code, using the DevTools Protocol or WebDriver BiDi.

SetupDocsCommunityMaturity

Verdict Puppeteer is an excellent fit for Node.js code that needs direct, scriptable control of Chrome, with Firefox available where its support fits the task. The API is mature and the documentation is unusually practical about browser downloads and Linux problems.

Full review →

04

winutil

ChrisTitusTech/winutil · ★ 63k ▲418/7d · PowerShell

WinUtil is a PowerShell utility that puts common Windows setup jobs, software installs, debloating, troubleshooting, and update controls in one place. It is meant to replace the repetitive clicking and script hunting that follows a fresh Windows installation, while offering presets for people who want a repeatable starting point.

SetupDocsCommunityMaturity

Verdict Our build succeeded in 13 seconds, while the measured project offered no test target. WinUtil is an unusually convenient choice for experienced Windows users who understand that its one-command launch grants administrator-level power to remotely fetched code.

Full review →

05

Win11Debloat

Raphire/Win11Debloat · ★ 57k ▲340/7d · PowerShell

Win11Debloat is a PowerShell script that removes preinstalled Windows 11 apps, disables telemetry and ads, and applies dozens of UI and privacy tweaks in one run. It solves the problem of manually clicking through Windows settings or hunting down app removal commands.

SetupDocsCommunityMaturity

Verdict We could not run it: no PowerShell in our Debian sandbox and no Dockerfile, so there are no install/build/test numbers from us. For a Windows user, Win11Debloat is a proven, active, and very popular way to strip Windows 11 down to a cleaner state in minutes, but you are trusting a script with administrator rights to do a lot at once..

Full review →

06

freqtrade

freqtrade/freqtrade · ★ 54k ▲251/7d · Python

Freqtrade is a Python bot for researching, simulating, and automating cryptocurrency trading strategies. It connects strategy code to historical data, dry-run trading, supported exchanges, a web interface, and optional Telegram control. FreqAI adds adaptive prediction models, but users still supply and validate the trading logic.

SetupDocsCommunityMaturity

Verdict Our Freqtrade run passed 4,516 tests with 0 failures, recorded 20 skipped, and found 0 known dependency vulnerabilities, which is enough for us to recommend it to technical crypto traders who will dry-run before using funds. The project supplies far more operational guidance than most trading bots, including bias checks and exchange notes.

Full review →

07

terraform

hashicorp/terraform · ★ 50k ▲35/7d · Go

Terraform is an infrastructure-as-code command-line tool that compares declarative configuration with provider-managed infrastructure, shows a plan, and applies the resulting changes. It gives teams a versioned way to create and modify cloud, service, and in-house resources through provider plugins.

SetupDocsCommunityMaturity

Verdict Our Terraform run built successfully but ended with 101 of 102 test results passing, so the code is substantial and the supplied log still leaves one failure unexplained. New adopters should compare OpenTofu before committing, because the license difference can settle the decision even when the operating model is familiar.

Full review →

08

zx

google/zx · ★ 46k ▲10/7d · JavaScript

zx lets JavaScript and TypeScript developers write shell scripts with normal loops, promises, exception handling, and npm packages. Its tagged template runs commands through Bash or PowerShell, escapes interpolated arguments, and returns output as a process object.

SetupDocsCommunityMaturity

Verdict Our Node 22 sandbox installed zx's 531-package tree in 29 seconds and built it in 19 seconds, but 6 tests failed, so commit `65fc542` was easy to start and did not produce a clean test run. zx is still a good choice for JavaScript teams whose shell scripts have become programs, provided they pin the version and test their actual shell and platform.

Full review →

09

maigret

soxoj/maigret · ★ 38k ▲166/7d · Python

Maigret is a Python OSINT tool that checks a username across more than 3,000 sites, then collects profile details and links into readable or machine-friendly reports. It turns a slow, repetitive account hunt into one command, with no site API keys required for the standard search.

SetupDocsCommunityMaturity

Verdict Our Maigret run passed 369 of 447 pytest cases, with 64 failures and 14 setup or collection errors, so its useful reports cannot be treated as proof that every site checker works. It remains a strong first pick when a username search must become a reviewable investigation artifact.

Full review →

10

helm

helm/helm · ★ 30k · Go

Helm is a package manager for Kubernetes applications. It bundles configurable Kubernetes manifests into charts, installs them through the cluster API, and keeps release history so operators can upgrade, inspect, roll back, or remove an application as one named unit.

SetupDocsCommunityMaturity

Verdict Our Helm run installed 341 packages in 46 seconds, built successfully in 178 seconds, and passed all 118 tests in 151 seconds. Use Helm 4 when reusable application packaging and release history justify a template layer in front of Kubernetes.

Full review →

11

celery

celery/celery · ★ 29k · Python

Celery is a Python task queue that sends work from an application through a message broker to worker processes. It moves slow, scheduled, or retryable jobs out of a web request and can route them across many workers while optionally recording their status and results.

SetupDocsCommunityMaturity

Verdict Our Celery run passed 3,912 tests and failed 8 privilege-check cases in 599 seconds, which shows a deep test suite and a real environment-sensitive edge. Use Celery when background work has grown into shared infrastructure and your team can own a broker, worker supervision, delivery semantics, and monitoring.

Full review →

12

jenkins

jenkinsci/jenkins · ★ 27k ▲15/7d · Java

Jenkins is a self-hosted automation server used to build, test, analyze, and deploy software. Its controller schedules work across local or remote executors, while more than 2,000 plugins connect jobs to source control, build tools, credentials, notifications, and deployment systems.

SetupDocsCommunityMaturity

Verdict Our Jenkins frontend run installed 715 packages in 57 seconds, then built successfully and passed all 5 Vitest tests. Jenkins remains a sensible choice for mixed infrastructure and established plugin-heavy pipelines when a team can own the controller, agents, credentials, and upgrade testing.

Full review →

13

pulumi

pulumi/pulumi · ★ 26k ▲29/7d · Go

Pulumi is an infrastructure-as-code system that lets teams define cloud resources with TypeScript, JavaScript, Python, Go, .NET, Java, or YAML. Its CLI evaluates that program, compares the desired resources with stored stack state, and asks cloud providers to create, update, or delete infrastructure.

SetupDocsCommunityMaturity

Verdict Our `npm/` run passed 15 of 15 tests in 14 seconds and found 0 known vulnerabilities, but it covered only a tiny corner of Pulumi's 1.7-million-line repository. Pulumi is a strong choice when developers will genuinely benefit from normal language features and the organization can govern state, credentials, plugins, and previews.

Full review →

14

argo-cd

argoproj/argo-cd · ★ 24k ▲50/7d · Go

Argo CD is a continuous-delivery controller for Kubernetes that treats Git as the desired state of applications. It compares repository manifests with live clusters, shows drift, and can synchronize changes manually or automatically.

SetupDocsCommunityMaturity

Verdict Our Argo CD build passed in 253 seconds, but 3 of 40 Go tests failed, so this commit does not get a clean source-suite recommendation from us. Argo CD remains the sensible default for Kubernetes teams that want a visible GitOps control plane and can govern its cluster permissions.

Full review →

15

node-red

node-red/node-red · ★ 24k ▲17/7d · JavaScript

Node-RED is a browser-based tool for building event-driven applications by wiring reusable nodes into flows. It is most useful for connecting devices, message brokers, APIs, files, and small pieces of JavaScript without building the whole runtime from scratch.

SetupDocsCommunityMaturity

Verdict Our Node-RED run built in 9 seconds and 2,843 tests passed, but 3 failed and npm audit found 7 known vulnerabilities. Use it when visual message routing will shorten the path between real devices and services, and the team can own authentication, storage, and node review.

Full review →

16

renovate

renovatebot/renovate · ★ 23k ▲59/7d · TypeScript

Renovate finds dependency references in a repository, checks for newer releases, and opens pull requests with the version and lockfile changes. It covers more than 90 package managers and several source-control platforms, giving teams one policy engine for updates that would otherwise be checked by hand.

SetupDocsCommunityMaturity

Verdict Our Renovate run installed 1,094 packages and built in 15 seconds, but its test suite ended in failure after 607 seconds, so platform teams get deep dependency automation with a substantial codebase behind it. Choose Renovate when more than 90 package managers, private registries, grouping, and scheduled update policy need to work the same way across many repositories.

Full review →

17

argo-workflows

argoproj/argo-workflows · ★ 17k ▲10/7d · Go

Argo Workflows is a workflow engine that runs each step as a container on Kubernetes. Teams describe a sequence or dependency graph in Kubernetes resources, then use the controller, API, CLI, or web interface to submit, watch, retry, schedule, and archive jobs.

SetupDocsCommunityMaturity

Verdict Our Argo Workflows checkout built in 10 seconds and passed 5 of 6 test packages; the sole failed package needed rootless Docker for a MySQL container. That is a strong source baseline for a Kubernetes platform team, and a reminder that realistic validation crosses into containers and cluster services.

Full review →

18

pipeline

tektoncd/pipeline · ★ 9.1k ▲1/7d · Go

Tekton Pipelines is a Kubernetes controller and set of custom resources for defining CI and delivery work as Tasks and Pipelines. It solves the problem of running container-based build and deployment steps inside a cluster without tying the workflow to one hosted CI service.

SetupDocsCommunityMaturity

Verdict Our Tekton checkout built successfully and all 150 tests passed, but a production install still requires a Kubernetes 1.28 cluster and operator attention. Use it when your platform team wants CI as cluster resources and is willing to own the controller, policies, and upgrades.

Full review →

19

claude-code-action

anthropics/claude-code-action · ★ 8.9k ▲59/7d · TypeScript

Claude Code Action puts Claude inside GitHub issues and pull requests, where it can answer questions, review changes, edit code, and run prompted maintenance jobs. It solves the handoff between a repository conversation and an agent working on the checked-out code.

SetupDocsCommunityMaturity

Verdict Our run installed 150 packages in 31 seconds and all 966 tests passed, which makes the action easy to trust at the repository-mechanics level. Use it when Claude is already an approved provider and maintainers will keep triggers, tools, and GitHub permissions narrow.

Full review →

20

App-Store-Connect-CLI

rorkai/App-Store-Connect-CLI · ★ 7.3k ▲104/7d · Go

App Store Connect CLI, called `asc`, puts Apple's app-management APIs and common Xcode release work behind scriptable commands. It covers builds, TestFlight, submissions, metadata, screenshots, signing, subscriptions, analytics, Xcode Cloud, and Apple Ads without making developers click through each task in the web console.

SetupDocsCommunityMaturity

Verdict Our `asc` run passed 101 of 104 tests after a 56-second install, but 3 failures kept the source checkout from a clean bill of health. It is still a strong choice for Apple teams that want JSON-first automation, explicit dry runs, and much wider App Store Connect coverage than a homegrown script.

Full review →

21

rclone

rclone/rclone · ★ 60k ▲121/7d · Go

Rclone is a command-line tool for copying and synchronizing files and directories between local storage and a wide range of cloud storage services. It solves the awkward problem of moving data across providers without adopting a separate vendor-specific utility for every destination.

SetupDocsCommunityMaturity

Verdict Our build completed in 139 seconds, but 15 of 236 test results failed in the same sandbox. Rclone is still a strong default for experienced operators who need one command-line vocabulary across many storage providers, especially when transfers must be scripted.

Full review →

22

PowerShell

PowerShell/PowerShell · ★ 55k ▲114/7d · C#

PowerShell is a cross-platform command shell, scripting language, and automation framework for Windows, Linux, and macOS. It helps administrators and developers automate systems while working directly with structured data, REST APIs, and object models instead of treating every result as plain text.

SetupDocsCommunityMaturity

Verdict Our run produced no install, build, or test result because the harness lacked C# support and the repository supplied no Dockerfile. Even without a lab pass, PowerShell 7.6.5 is an easy recommendation for serious Windows automation and a credible option for mixed operating-system fleets.

Full review →

23

acme.sh

acmesh-official/acme.sh · ★ 48k ▲51/7d · Shell

acme.sh is a Shell client that requests, renews, and deploys TLS certificates through the ACME protocol. It replaces manual certificate expiry work with scheduled renewal and supports webroot, standalone server, web server, and DNS validation paths.

SetupDocsCommunityMaturity

Verdict Our standard sandbox could not run acme.sh at commit 9656842 because Shell is outside its supported ecosystems, so we cannot give you a passing test or build result. Use acme.sh when a small Unix client and its specific DNS or deployment hooks match your infrastructure.

Full review →

24

airflow

apache/airflow · ★ 47k ▲70/7d · Python

Apache Airflow schedules and monitors workflows whose steps and dependencies are written in Python. It is meant for recurring, mostly stable jobs such as data pipelines and model training, where teams need retries, history, a UI, and a shared scheduler instead of a pile of cron entries.

SetupDocsCommunityMaturity

Verdict Our Airflow run installed 151 packages and built in 26 seconds, but its test command stopped after 7 seconds on an unrecognized pytest option, so established data teams should expect a capable scheduler with a serious development environment. Use it when scheduled Python DAGs, backfills, provider integrations, and operational history justify running shared infrastructure.

Full review →

25

agent-browser

vercel-labs/agent-browser · ★ 43k ▲328/7d · Rust

agent-browser is a command-line browser controller designed for coding agents and automation scripts. It turns pages into accessibility-tree references, then lets an agent click, type, inspect, record, and compare browser state through a native Rust daemon or an MCP server.

SetupDocsCommunityMaturity

Verdict Our source install consumed 1,091 packages and 894 MB, while the workspace offered no build or test target, so agent-browser's excellent command design was not independently exercised in our sandbox. It is a strong fit for coding agents that need concise, inspectable Chrome actions and typed MCP tools.

Full review →

26

fastlane

fastlane/fastlane · ★ 42k ▲22/7d · Ruby

fastlane is a Ruby command-line tool that automates tedious iOS and Android release tasks like generating screenshots, managing provisioning profiles, and uploading apps. It solves the real problem of Apple code signing and manual App Store or Play Store submission eating days of developer time.

SetupDocsCommunityMaturity

Verdict fastlane has 42,092 GitHub stars, a last push one day ago, and a 2.239.0 release six days before this review, but our run measured zero install, build, or test steps because the repo has no supported ecosystem. That makes it hard to verify setup ease from our sandbox, though the project's longevity and active maintenance suggest it remains the default mobile release automation tool for teams that already run Ruby..

Full review →

27

selenium

SeleniumHQ/selenium · ★ 34k ▲12/7d · Java

Selenium is an open-source toolkit for controlling major web browsers through the W3C WebDriver standard. It solves the problem of automating real browser actions for testing, repetitive workflows, and cross-browser checks without tying teams to one programming language or browser vendor.

SetupDocsCommunityMaturity

Verdict Our install succeeded in 21 seconds, but build and tests were skipped because no corresponding pnpm targets were detected. Selenium remains a strong default when standards-based, multi-browser, multi-language automation matters more than having the neatest all-in-one test runner.

Full review →

28

conductor

conductor-oss/conductor · ★ 32k ▲8/7d · Java

Conductor is a self-hosted workflow engine that records each step of a distributed job or AI agent so work can resume after failures. Teams describe the orchestration as versioned JSON while their workers keep business logic in Java, Python, Go, JavaScript, C#, Ruby, or Rust.

SetupDocsCommunityMaturity

Verdict Our Conductor checkout installed 60 packages in 28 seconds and built in 7 seconds, but the harness found no test target, so the result supports only a trial. Use it when durable state, inspectable JSON graphs, and workers in several languages are worth operating a workflow service.

Full review →

29

kestra

kestra-io/kestra · ★ 28k ▲94/7d · Java

Kestra is an event-driven workflow orchestrator for data jobs, AI tasks, infrastructure operations, and business processes. Teams define flows in YAML, edit them visually, trigger them on schedules or events, and run scripts or plugins across local machines, containers, Kubernetes, and cloud services.

SetupDocsCommunityMaturity

Verdict Our Kestra UI build took 45 seconds after a 1,420-package install, but that workspace had no test target and npm audit found 1 moderate vulnerability. Kestra is a strong choice when visual editing, YAML in Git, event triggers, and a broad plugin catalog need to coexist.

Full review →

30

prefect

PrefectHQ/prefect · ★ 24k ▲42/7d · Python

Prefect is a Python workflow system that adds scheduling, retries, caching, state tracking, and a web dashboard to ordinary functions. It helps data teams run scripts repeatedly, see what failed, and move the same workflow from a laptop to workers without rewriting it as a separate configuration language.

SetupDocsCommunityMaturity

Verdict Our Prefect run installed 128 packages in 53 seconds and built in 12 seconds, but tests stopped before collection because `numpy` was missing. Prefect is a strong choice when Python workflows have outgrown cron and a team will use the run history, retries, parameters, and worker model.

Full review →

31

temporal

temporalio/temporal · ★ 23k ▲157/7d · Go

Temporal is a durable execution server for application workflows that must survive process crashes, network failures, retries, and long waits. Developers write workflow and activity code with a language SDK, run their own workers, and let the server persist event history and coordinate the next task.

SetupDocsCommunityMaturity

Verdict Our Temporal build took 278 seconds, and 13 of 15 test targets passed before two PostgreSQL CLI tests failed, so source contributors should expect a large server with persistence-sensitive tests. Temporal is worth the conceptual and operating cost when a failed business process cannot simply be restarted from step one.

Full review →

32

Karabiner-Elements

pqrs-org/Karabiner-Elements · ★ 23k ▲43/7d · C++

Karabiner-Elements is a macOS keyboard remapper that can make one key act like another or apply different rules by device, application, and input state. It solves awkward keyboard layouts and repetitive shortcuts at a lower level than most app-specific hotkey settings.

SetupDocsCommunityMaturity

Verdict Our sandbox found 25 known npm vulnerabilities in the vendored Duktape debugger and could not build or test the macOS app, so the 42-second install is not evidence that Karabiner-Elements itself passed a health check. The official binary remains a strong choice for Mac users who need device-aware remapping and can accept its deep system permissions.

Full review →

33

windmill

windmill-labs/windmill · ★ 18k ▲111/7d · Rust

Windmill is a self-hosted platform that turns scripts into APIs, scheduled jobs, workflows, and internal applications. It gives developers one place to write automation in several languages, connect credentials, compose steps, and put a generated or custom interface in front of the result.

SetupDocsCommunityMaturity

Verdict Our Windmill CLI build finished in 22 seconds, but all 111 test files errored when the suite could not find `cargo`, so contributors should budget for the full multi-language toolchain. Windmill is a strong choice for developer-owned automation that also needs generated forms and internal apps.

Full review →

34

browser-harness

browser-use/browser-harness · ★ 18k ▲119/7d · Python

Browser Harness lets a coding agent control a real Chrome session through the Chrome DevTools Protocol. It can use existing logins, click and type on interactive pages, and write reusable Python helpers when a site needs behavior the base tool does not provide.

SetupDocsCommunityMaturity

Verdict Our Browser Harness install, build, and all 140 tests passed in 61 seconds combined, with 0 known package vulnerabilities. It is a strong fit for a careful developer who wants an agent to use a real logged-in Chrome session and can watch high-impact actions.

Full review →

35

goreleaser

goreleaser/goreleaser · ★ 16k · Go

GoReleaser turns a version tag and a YAML file into compiled binaries, archives, packages, checksums, container images, and published releases. It replaces project-specific release scripts for Go, Rust, Zig, JavaScript, TypeScript, and Python projects.

SetupDocsCommunityMaturity

Verdict Our GoReleaser build passed in 134 seconds, but its test run ended with 23 failures among 177 results at commit 2ab3100. Use it when one team owns a cross-platform artifact pipeline and will test the exact YAML, tools, and credentials used in CI.

Full review →

36

keda

kedacore/keda · ★ 11k ▲19/7d · Go

KEDA adds event-driven autoscaling to Kubernetes, including scaling workloads down to zero and back up when an external signal changes. It exposes those signals through Kubernetes metrics and works with the Horizontal Pod Autoscaler, so operators define scaling behavior with custom resources instead of writing a controller for each queue or service.

SetupDocsCommunityMaturity

Verdict Our KEDA build took 273 seconds, and the test command finished with 20 of 23 packages passing, so the code built but the pinned checkout did not clear its plain sandbox suite. Use KEDA when event backlogs should control Kubernetes capacity and your platform team can own the credentials, failure modes, and upgrade notes.

Full review →

37

motrix-next

AnInsomniacy/motrix-next · ★ 10k ▲102/7d · JavaScript

Motrix Next is a desktop download manager for HTTP, HTTPS, SFTP, ED2K, BitTorrent, magnet links, and torrent files. It rebuilds the Motrix experience with Tauri 2, Vue 3, Rust, and a maintained aria2 fork, while adding browser-extension control and native desktop integration.

SetupDocsCommunityMaturity

Verdict Our Motrix Next checkout installed in 27 seconds, built in 43 seconds, and passed its tests in 34 seconds, making it a credible modern replacement for the older Motrix codebase. Use it if its multi-protocol desktop workflow fits and you can accept unsigned binaries from GitHub Actions.

Full review →

38

lego

go-acme/lego · ★ 9.9k ▲4/7d · Go

Lego is a Go command-line client and library for obtaining, renewing, and revoking TLS certificates from Let's Encrypt and other ACME certificate authorities. Its main draw is DNS challenge automation for more than 200 providers, alongside HTTP and TLS challenge support.

SetupDocsCommunityMaturity

Verdict Our lego install never completed: after 682 seconds, Go module downloads ended on `proxy.golang.org` stream errors before build or tests began. Use a v5.4.1 release binary or pinned container when your DNS provider is supported, then test that provider against a staging CA before touching production records.

Full review →

39

atlantis

runatlantis/atlantis · ★ 9.3k ▲8/7d · Go

Atlantis is a self-hosted service that runs Terraform plans and applies from pull-request comments. It puts infrastructure changes, plan output, approvals, and execution history in the same review thread instead of relying on engineers to run Terraform from their laptops.

SetupDocsCommunityMaturity

Verdict Our Atlantis npm run installed 300 packages and found 0 known vulnerabilities, but it exposed no build or test target, so the 157,048-line checkout did not receive an executable server-level check from this harness. Use Atlantis when pull requests are already the control point for Terraform and you can treat the service as privileged infrastructure.

Full review →

40

gogcli

openclaw/gogcli · ★ 8.4k ▲21/7d · Go

gogcli is one command-line client for Gmail, Calendar, Drive, Docs, Sheets, and much of Google Workspace. It gives people, scripts, and agents stable machine output, explicit account selection, and controls that can prevent an automated caller from sending mail or changing cloud data.

SetupDocsCommunityMaturity

Verdict Our gogcli run installed 139 packages, built successfully, and passed all 84 tests, so the code is a credible base for Google Workspace automation. Choose it when one explicit, scriptable interface across several Google services is worth the OAuth setup, especially for read-only jobs or tightly allowed agent tools.

Full review →

41

flux2

fluxcd/flux2 · ★ 8.4k ▲17/7d · Go

Flux keeps Kubernetes clusters aligned with configuration stored in Git repositories, OCI artifacts, Helm repositories, or buckets. Its controllers repeatedly fetch declared sources, apply Kustomize or Helm changes, report status, and can write new image versions back to Git.

SetupDocsCommunityMaturity

Verdict Our Flux build finished in 9 seconds, but the test command ended with 8 passes and 1 unexplained failure, so this checkout did not earn a clean lab result. Flux remains a strong choice for Kubernetes teams that want pull-based reconciliation and can operate its controllers, CRDs, and source credentials.

Full review →

42

hatchet

hatchet-dev/hatchet · ★ 7.9k ▲42/7d · Go

Hatchet is an orchestration system for background jobs, AI agents, and workflows that must recover after a process stops. Python, TypeScript, Go, and Ruby applications get queues, retries, schedules, rate limits, monitoring, and durable execution through a hosted service or a self-managed deployment.

SetupDocsCommunityMaturity

Verdict Our Hatchet build succeeded in 224 seconds, but 3 of 43 Go package results failed, so teams should trial their exact SDK and failure cases before committing. Hatchet is a good fit when durable jobs, agent waits, throttling, and run visibility justify operating PostgreSQL and a control plane.

Full review →

43

karpenter-provider-aws

aws/karpenter-provider-aws · ★ 7.7k ▲4/7d · Go

Karpenter Provider AWS is a Kubernetes controller that launches suitable EC2 instances when pods cannot be scheduled, then removes or replaces nodes as demand changes. It chooses capacity from pod requirements and AWS instance options instead of making teams predefine a node group for every workload shape.

SetupDocsCommunityMaturity

Verdict Our Karpenter build passed in 180 seconds, but tests ended with 19 of 21 packages failing, so source contributors need the project's intended test environment before treating a generic Go run as healthy. For EKS teams, Karpenter is a strong choice when mixed workloads make fixed node groups wasteful and operators can govern IAM plus disruption.

Full review →

44

mobile-mcp

mobile-next/mobile-mcp · ★ 6.7k ▲157/7d · TypeScript

Mobile MCP is a Model Context Protocol server that lets an AI agent inspect and control iOS and Android apps through one set of tools. It uses device accessibility data where possible, with screenshots and coordinate taps as a fallback, so agents can explore apps without separate XCUITest and Espresso scripts.

SetupDocsCommunityMaturity

Verdict Our Mobile MCP run installed 437 packages in 17 seconds, passed its build and tests in 19 seconds combined, and reported 0 known npm vulnerabilities, making it an easy MCP server to trial. Use it for agent-led inspection and exploratory mobile flows when you already have the platform SDK and device setup.

Full review →

45

gh-aw

github/gh-aw · ★ 5.1k ▲18/7d · Go

GitHub Agentic Workflows lets maintainers describe repository jobs in Markdown and run an AI coding agent inside GitHub Actions. Its CLI compiles those instructions into normal workflow YAML, with read-only agent jobs by default and validated safe-output jobs for approved writes such as comments, issues, or pull requests.

SetupDocsCommunityMaturity

Verdict Our gh-aw run installed 241 packages and built successfully, but 1 of 3 tested packages failed because the Go container had no `node` executable for fuzz sanitization. Adopt it for interpretive repository chores only when permissions, egress, safe outputs, and human review are owned like production CI.

Full review →

46

actionlint

rhysd/actionlint · ★ 4.2k ▲19/7d · Go

actionlint is a static checker for GitHub Actions workflow YAML. It catches workflow syntax errors, invalid expressions, incorrect action inputs, dependency mistakes, unsafe script interpolation, and some embedded shell or Python problems before GitHub runs the workflow.

SetupDocsCommunityMaturity

Verdict Our actionlint build took 17 seconds, but its 5-group test run ended 4 passed and 1 failed in the popular-actions generator. The core linter remains an easy recommendation for fast workflow feedback, provided you pin a release and treat new GitHub syntax as a possible false-positive source.

Full review →

47

upload-artifact

actions/upload-artifact · ★ 4.2k ▲5/7d · TypeScript

GitHub's upload-artifact action moves files from a workflow run into GitHub's artifact storage, where later jobs or signed-in users can retrieve them. It handles files, directories, wildcard paths, retention, compression, overwrite behavior, and a direct single-file mode without asking you to run a storage service.

SetupDocsCommunityMaturity

Verdict Our upload-artifact run installed 699 packages, built in 14 seconds, and passed all 31 tests, but npm audit still reported 14 known vulnerabilities. Use v7 for routine file handoff inside GitHub-hosted Actions when short-lived, immutable artifacts match the workflow.

Full review →

48

kueue

kubernetes-sigs/kueue · ★ 3.0k ▲12/7d · Go

Kueue is a Kubernetes controller that decides when batch, AI, and other resource-heavy jobs may start. It adds job-level queues, quotas, borrowing, fair sharing, and preemption while leaving pod placement to the normal Kubernetes scheduler.

SetupDocsCommunityMaturity

Verdict Our Kueue build passed in 263 seconds, but its 614-second test run ended with 4 of 8 packages failing after a performance checker received an empty summary path. The project remains the strongest first trial for Kubernetes-native job admission when you want to keep existing job APIs and the default scheduler.

Full review →

49

n8n

n8n-io/n8n · ★ 204k ▲560/7d · TypeScript

n8n is a visual workflow and AI-agent builder that connects apps, APIs, code, and human approval steps. You can run it on n8n Cloud or host it yourself when workflows and their credentials need to stay under your control.

SetupDocsCommunityMaturity

Verdict Our n8n install took 633 seconds, consumed 3,667 MB, and built successfully, but the full test command still exited 1 after its task runner flagged `@n8n/computer-use#test`. Use n8n when the 1,500-plus integrations and visual canvas can replace enough private glue code to justify operating a full platform.

Full review →

50

kubernetes

kubernetes/kubernetes · ★ 128k ▲877/7d · Go

Kubernetes is an open-source control system for deploying, maintaining, and scaling containers across multiple machines. It keeps applications close to a declared state by scheduling workloads and coordinating the control plane, nodes, networking, storage, and service discovery around them.

SetupDocsCommunityMaturity

Verdict Our Kubernetes build took 561 seconds, and 433 of 434 reported test results passed before the command hit our 900-second cap. Use Kubernetes when a platform team can turn its APIs and ecosystem into shared infrastructure for many workloads.

Full review →

51

obs-studio

obsproject/obs-studio · ★ 76k ▲277/7d · C

OBS Studio is a desktop application for capturing, compositing, encoding, recording, and streaming video. It solves the practical problem of turning cameras, screens, audio, and other sources into a finished recording or live output from one production workspace.

SetupDocsCommunityMaturity

Verdict Our measured npm install finished in 6 seconds, but it did not build OBS Studio. Use OBS when you want a mature, actively maintained open-source center for recording or live production and are willing to learn a serious desktop tool.

Full review →

52

openpilot

commaai/openpilot · ★ 64k ▲54/7d · Python

openpilot is an open-source driver-assistance system that adds adaptive cruise control and lane centering to supported cars through comma hardware. It solves the gap between basic factory assistance and a frequently updated Level 2 system, while keeping the driver responsible for the vehicle.

SetupDocsCommunityMaturity

Verdict Our openpilot install took 42 seconds and its build passed in 14 seconds, but the sandbox could not test the 335-car hardware matrix. Use it when your exact vehicle is supported, you accept Level 2 responsibility, and comma hardware is a reasonable purchase.

Full review →

53

remotion

remotion-dev/remotion · ★ 59k ▲659/7d · TypeScript

Remotion turns React components into videos and images, with frames driven by code, props, and data. It gives developers a browser-based studio for authoring and several rendering paths for local jobs, servers, cloud functions, applications, and batch production.

SetupDocsCommunityMaturity

Verdict Our Remotion checkout installed 3,978 packages and used 4,533 MB, then build and tests both failed because `bun` was missing. That makes the repository contributor path heavier than the one-command project starter suggests, while the end-user framework remains a strong fit for React teams producing repeatable, data-fed video.

Full review →

54

multica

multica-ai/multica · ★ 50k ▲555/7d · Go

Multica is a work board for assigning software tasks to AI coding agents and keeping their runs, comments, blockers, costs, and human review in one issue. It drives 23 supported agent command-line tools on machines you control, while the board can run in Multica's cloud or on your own server.

SetupDocsCommunityMaturity

Verdict Our Multica run installed 2,014 packages, used 2,385 MB, and spent 539 seconds building and testing successfully, so this is serious team infrastructure rather than a lightweight agent launcher. Adopt it when multiple coding CLIs already create a coordination problem and a human review gate is non-negotiable.

Full review →

55

novu

novuhq/novu · ★ 40k ▲49/7d · TypeScript

Novu is a notification and conversation platform for products and software agents. It gives developers one workflow layer for in-app inboxes, email, SMS, push, and chat, while outside providers still perform most delivery.

SetupDocsCommunityMaturity

Verdict Our Novu install pulled 5,192 packages and used 3,845 MB before a successful 334-second build, so self-hosting is a platform commitment rather than a small dependency. Choose Novu when notification preferences, an in-app inbox, workflow logic, and several providers belong under one operating model.

Full review →

56

browser

lightpanda-io/browser · ★ 35k ▲210/7d · Zig

Lightpanda is a headless browser built for web automation and AI agents rather than human browsing. It implements web APIs, JavaScript, CDP, agent commands, and MCP access without shipping Chromium or WebKit.

SetupDocsCommunityMaturity

Verdict Our run built Lightpanda's 122-package Rust subtree in 108 seconds, but Cargo found 0 tests and did not exercise the full Zig browser. Lightpanda is worth a controlled trial for high-volume extraction or agent browsing where Chromium's resource cost hurts.

Full review →

57

AIHawk

feder-cr/Jobs_Applier_AI_Agent_AIHawk · ★ 32k ▲1.3k/7d · Python

AIHawk is an open-source browser agent that turns plain-language instructions into real browser actions such as clicking, typing, and reading pages. It can work as an MCP browser for an existing assistant or as a standalone web interface powered by an OpenRouter model, solving tasks that require navigating websites rather than calling an API.

SetupDocsCommunityMaturity

Verdict AIHawk is worth trying if ordinary browser automation gets blocked or if you want to hand browsing work directly to an MCP-capable assistant. Its clean sandbox result, specific operational documentation, and active release are reassuring, but the separate browser layer and lack of macOS support keep it from being a universal default.

Full review →

58

OpenCLI

jackwener/OpenCLI · ★ 29k ▲219/7d · JavaScript

OpenCLI turns websites, logged-in browser sessions, Electron apps, and existing command-line programs into commands that people or AI agents can call. It ships a large adapter catalog and browser primitives for navigating pages, filling forms, extracting data, and building new adapters.

SetupDocsCommunityMaturity

Verdict Our OpenCLI build passed in 14 seconds and 7,312 of 7,317 tests passed, but 2 download tests failed and 3 were skipped. It is worth trying for supervised browser work or a site you repeatedly automate, because the adapter catalog and logged-in bridge save real setup.

Full review →

59

crawlee

apify/crawlee · ★ 26k ▲101/7d · TypeScript

Crawlee is a TypeScript and JavaScript framework for web crawling, scraping, and browser automation. It gives HTTP and browser crawlers a shared system for queues, retries, sessions, proxies, storage, routing, and scaling, so developers do not have to assemble those pieces around Playwright or an HTML parser.

SetupDocsCommunityMaturity

Verdict Our Crawlee build passed in 38 seconds, but its 374-second test run finished with 1,559 passed, 192 failed, and 38 skipped out of 1,801. Use it when a Node.js crawler needs queues, sessions, retries, storage, and both HTTP and browser execution under one API.

Full review →

60

MaaAssistantArknights

MaaAssistantArknights/MaaAssistantArknights · ★ 23k ▲134/7d · C++

MAA is a desktop and command-line assistant that automates repetitive tasks in Arknights by recognizing what is on screen and controlling the game. It handles chores such as farming, base shifts, recruitment, rewards, and selected battle plans, reducing the daily attention the game demands.

SetupDocsCommunityMaturity

Verdict Our build completed in 20 seconds, but all 9 test packages in the measured Go test step failed to build. MAA is still the strongest-looking choice here for committed Arknights players because its automation breadth, platform support, integrations, and active maintenance are unusually substantial.

Full review →

61

semaphore

semaphoreui/semaphore · ★ 14k ▲27/7d · Go

Semaphore UI puts a web interface, schedules, credentials, inventories, and access control around Ansible, Terraform, OpenTofu, Terragrunt, PowerShell, and shell tasks. It is for teams that have outgrown running deployment commands from one person's terminal but do not want a larger automation platform.

SetupDocsCommunityMaturity

Verdict Our Semaphore UI run built in 13 seconds, but 3 of 20 test packages failed, so pin the release and rehearse repository, database, and credential paths before moving real deployments into it. It is a good fit for a small team that wants shared Ansible and Terraform jobs without adopting AWX.

Full review →

62

crossplane

crossplane/crossplane · ★ 12k ▲29/7d · Go

Crossplane turns a Kubernetes cluster into an API for provisioning cloud services, applications, and other infrastructure. Platform teams define their own resource types, then Crossplane keeps the resources behind those APIs in the requested state through providers and composition functions.

SetupDocsCommunityMaturity

Verdict Our Crossplane build succeeded in 138 seconds, while the test run reported 86 passed and 3 failed of 89 before ending on the `test/e2e` package. Crossplane 2.4 is a strong choice for a staffed platform team that wants Kubernetes-native product APIs and continuous reconciliation across providers.

Full review →

63

douyin-downloader

jiji262/douyin-downloader · ★ 12k ▲1.9k/7d · Python

Douyin Downloader is a Python tool for saving Douyin videos, image posts, collections, music, comments, live streams, and whole profiles. It adds retries, local history, browser-assisted pagination, optional transcription, and a small job API for people who need more than one pasted-link download.

SetupDocsCommunityMaturity

Verdict Our Douyin Downloader run passed 649 tests in 134 seconds and pip-audit found 0 known vulnerabilities, making the Python CLI a credible choice for a permitted personal archive. Use it when cookies, local files, and occasional manual browser checks fit the job.

Full review →

64

skypilot

skypilot-org/skypilot · ★ 11k ▲25/7d · Python

SkyPilot is a Python control plane for launching and managing AI workloads across Kubernetes, Slurm, public clouds, and specialist GPU providers. One task file can request hardware, sync code, run setup commands, recover jobs, and stop idle resources without rewriting the workload for every backend.

SetupDocsCommunityMaturity

Verdict Our SkyPilot run installed 372 packages and consumed 1,672 MB, then its tests stopped in 10 seconds on a missing UID 1000 passwd entry and pip-audit found 13 known vulnerabilities. That is a heavy client and a container compatibility snag, but the project still deserves a trial when fragmented GPU infrastructure is costing a team real engineering time.

Full review →

65

claude-squad

smtg-ai/claude-squad · ★ 8.5k ▲33/7d · Go

Claude Squad is a terminal interface for running several coding-agent sessions at once. It puts each Claude Code, Codex, Gemini CLI, Aider, or custom command in its own tmux session and Git worktree, then lets you inspect diffs and move finished work back into your branch.

SetupDocsCommunityMaturity

Verdict Our Claude Squad run installed 48 Go packages, built successfully, and passed all 6 tests in 91 seconds combined. It is worth using on macOS or Linux when you already know how to manage worktrees and want one screen for several agent CLIs.

Full review →

66

pi-autoresearch

davebcn87/pi-autoresearch · ★ 8.1k ▲50/7d · TypeScript

pi-autoresearch is an extension for the pi coding agent that changes code, runs a numeric measurement, keeps improvements, and reverts regressions. It stores the goal, measurement script, and experiment history in the project so the work can resume after a restart or context reset.

SetupDocsCommunityMaturity

Verdict Our pi-autoresearch run installed 127 packages in 35 seconds and passed all 46 tests, making it a low-friction trial for existing pi users with a numeric target. Its durable `.auto` record makes long sessions inspectable and resumable.

Full review →

67

apify-mcp-server

apify/apify-mcp-server · ★ 7.3k ▲739/7d · TypeScript

Apify MCP Server lets an AI assistant find and run Apify's web scrapers, crawlers, and automation jobs as tools. It gives chat and coding clients a common way to collect data from websites, search engines, maps, social networks, and stores without writing a scraper for every request.

SetupDocsCommunityMaturity

Verdict Our Apify MCP Server run installed 788 packages, then passed its 23-second build and 43-second test step. Use it when an assistant needs controlled access to approved Apify Actors and your team can govern cost, data transfer, and long jobs.

Full review →

68

go-whatsapp-web-multidevice

aldinokemal/go-whatsapp-web-multidevice · ★ 4.8k ▲76/7d · Go

GOWA turns one or more linked WhatsApp accounts into a self-hosted REST API, webhook source, dashboard, Chatwoot bridge, and MCP server. It lets software send and receive messages through unofficial WhatsApp Web sessions instead of Meta's supported business platform.

SetupDocsCommunityMaturity

Verdict Our GOWA build passed in 111 seconds, while its 439-second test run ended with 12 of 13 packages passing and no failing package named in the supplied log tail. It is a capable bridge for experiments and internal automation that can tolerate re-pairing or protocol breakage.

Full review →

69

user-scanner

kaifcodec/user-scanner · ★ 4.8k ▲71/7d · Python

User Scanner is a Python OSINT tool that checks an email address or username across hundreds of sites, then exports the findings or passes them to an MCP client. Its useful trick is cross-scanning: it can extract another handle, profile link, or exposed address from one result and follow that lead into a second scan.

SetupDocsCommunityMaturity

Verdict Our User Scanner run installed 53 packages and passed 375 tests, but the suite stopped at collection because the optional `mcp` module was absent. Use it for investigator-led sweeps where errors, collisions, and profile pivots will be reviewed by a person.

Full review →

70

dagu

dagucloud/dagu · ★ 4.0k · Go

Dagu is a self-hosted workflow engine that adds schedules, dependencies, retries, logs, and human approval steps around scripts and containers you already have. It aims to replace tangled cron jobs without making teams adopt a large orchestration platform or rewrite working automation in a framework.

SetupDocsCommunityMaturity

Verdict Our build succeeded in 370 seconds, but the full test run still had 2 failures and hit the 900-second cap. Dagu is an appealing upgrade from cron when existing scripts should remain ordinary scripts and infrastructure overhead must stay low.

Full review →

71

BrowserSkill

Tencent/BrowserSkill · ★ 2.0k ▲137/7d · TypeScript

BrowserSkill lets a shell-capable AI agent control Chrome or Edge through a local command-line tool and browser extension. It opens a separate Agent Window, can temporarily borrow a tab you approve, and reuses the login state already present in your browser.

SetupDocsCommunityMaturity

Verdict Our BrowserSkill install added 726 packages in 45 seconds, but no root build or test target was available, so the published binaries and extension deserve a separate trust review before they touch logged-in accounts. It is worth trying for supervised, low-risk browser chores where reusing your real session saves substantial setup.

Full review →

72

huginn

huginn/huginn · ★ 50k ▲26/7d · Ruby

Huginn is a self-hosted web application for building agents that watch websites and feeds, pass events through a graph, and trigger actions. It solves the recurring job of monitoring online changes without handing every workflow and its data to a hosted automation service.

SetupDocsCommunityMaturity

Verdict Our Huginn run installed 80 npm packages in 17 seconds and built in 10 seconds, but it exposed no test target, so the clean result does not prove the Rails application passes its own specs. Use Huginn when self-hosted monitoring and an event graph fit the job, and when someone can own its database and aging connectors.

Full review →

73

cli

googleworkspace/cli · ★ 31k ▲220/7d · Rust

Google Workspace CLI, invoked as `gws`, turns Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and other Workspace APIs into JSON-producing terminal commands. It builds most of its command tree from Google's Discovery documents and includes agent skills, so scripts and coding agents can use Workspace without a separate wrapper for each service.

SetupDocsCommunityMaturity

Verdict Our googleworkspace/cli install took 10 seconds and 36 MB, but its test command failed in 6 seconds because Cargo was absent from the Node image. The prebuilt binary is a strong fit for engineers automating several Workspace APIs who can keep OAuth scopes narrow and verify every mutating helper.

Full review →

74

nanoclaw

nanocoai/nanoclaw · ★ 31k ▲54/7d · TypeScript

NanoClaw is a self-hosted personal AI assistant that receives messages, runs each agent in a container, remembers conversations, and handles scheduled work. It connects to chat services through installable skills and routes model credentials through a separate vault instead of placing raw keys inside agent containers.

SetupDocsCommunityMaturity

Verdict Our NanoClaw build finished in 13 seconds, but 95 of 2,044 tests failed after a 762-second run, so the current checkout belongs in a trial environment before it gets access to messages, files, or scheduled jobs. It is a sensible fit for one technical owner who values per-agent containers and is willing to maintain a fork with Claude Code.

Full review →

75

OfficeCLI

iOfficeAI/OfficeCLI · ★ 31k ▲309/7d · C#

OfficeCLI lets scripts and AI agents create, inspect, and edit Word, Excel, and PowerPoint files without Microsoft Office. It presents document parts as addressable elements, returns structured JSON, and can render HTML or PNG previews so an agent can check its work.

SetupDocsCommunityMaturity

Verdict Our npm-scope run installed in 22 seconds and found 0 known vulnerabilities, but the checkout exposed neither a build target nor a test target. OfficeCLI is worth trying when one automation layer must handle all 3 modern Office formats and an agent benefits from JSON plus visual previews.

Full review →

76

budibase

Budibase/budibase · ★ 28k ▲20/7d · TypeScript

Budibase is an open-source platform for building internal apps, workflow automations, and AI agents that can act on business systems. It aims to replace the usual patchwork of forms, approval tools, dashboards, and custom glue code with one system that engineers can host themselves or consume as a cloud service.

SetupDocsCommunityMaturity

Verdict Budibase deserves a serious trial if your organization regularly builds operational apps and workflows and values self-hosting. Its breadth, public API, active release activity, and successful build are reassuring, but the platform is heavy and our test command did not complete cleanly.

Full review →

77

activepieces

activepieces/activepieces · ★ 24k ▲124/7d · TypeScript

Activepieces is a visual workflow builder for connecting apps, running scheduled jobs, and adding approval or AI steps without writing the whole integration yourself. Its TypeScript integration packages can also be exposed as MCP servers for agent clients.

SetupDocsCommunityMaturity

Verdict Our Activepieces install took 367 seconds, added 3,143 packages, and used 2,670 MB, so self-hosting it is a platform commitment rather than a small automation experiment. Use it when a visual builder, TypeScript integrations, and MCP exposure belong in the same system.

Full review →

78

stagehand

browserbase/stagehand · ★ 24k ▲117/7d · TypeScript

Stagehand is a browser automation SDK for TypeScript, Python, and Go. It combines familiar page and locator methods with language-model commands that click, inspect, and extract data when fixed selectors are too brittle.

SetupDocsCommunityMaturity

Verdict Our Stagehand run installed 1,444 packages in 58 seconds and built in 41, but the 23-second test command still exited 1 after all 34 browser tests were skipped. Use it when a few change-prone browser steps justify model calls and you can keep hard assertions around the result.

Full review →

79

whatsapp-web.js

wwebjs/whatsapp-web.js · ★ 23k ▲39/7d · JavaScript

whatsapp-web.js is a Node.js library that controls a linked WhatsApp account through WhatsApp Web in a managed browser. It lets developers send and receive messages, media, reactions, polls, and group actions without using Meta's official business API.

SetupDocsCommunityMaturity

Verdict Our run installed 427 packages in 36 seconds, then the tests failed after 9 seconds and npm audit found 20 vulnerabilities, so whatsapp-web.js needs active ownership even before WhatsApp Web changes underneath it. Use it for a personal or internal workflow when its broad Web feature access is worth running Chromium and accepting account risk.

Full review →

80

generator-jhipster

jhipster/generator-jhipster · ★ 22k ▲3/7d · TypeScript

JHipster generates full web applications and microservice systems around Java and Spring Boot, with Angular, React, or Vue on the client. It solves the blank-project problem by producing an opinionated application, build setup, security choices, database integration, and deployment files from one configuration.

SetupDocsCommunityMaturity

Verdict Our JHipster run built in 44 seconds and passed 10,348 tests, but 888 failures still made the 141-second test command exit 255. That result makes the current checkout a poor candidate for blind adoption, even though the 0-vulnerability audit and active release work are encouraging.

Full review →

81

SpotX

SpotX-Official/SpotX · ★ 22k ▲65/7d · PowerShell

SpotX is a PowerShell patcher for the official Spotify desktop client on Windows. It removes banner, video, and audio ads, and can also hide unwanted content sections, disable analytics, and control client updates.

SetupDocsCommunityMaturity

Verdict We could not run SpotX because our Debian sandbox does not provide its supported Windows environment, and the repo has no Dockerfile. For a technically confident Windows user, it is a focused, unusually configurable Spotify patcher with clear presets and a current codebase.

Full review →

82

espanso

espanso/espanso · ★ 14k ▲28/7d · Rust

Espanso is a local text expander that watches for typed triggers and replaces them in desktop applications. Its YAML rules can insert plain text, dates, images, form results, or output from local scripts, giving one snippet system to Windows, macOS, and Linux users.

SetupDocsCommunityMaturity

Verdict Our Espanso checkout installed 350 packages in 41 seconds, then both build and tests failed because wxWidgets was absent. The released desktop app is still an easy recommendation for people who want local, system-wide snippets and can test their own applications.

Full review →

83

OpenWA

rmyndharis/OpenWA · ★ 14k ▲198/7d · TypeScript

OpenWA is a self-hosted REST, webhook, dashboard, and MCP gateway for WhatsApp automation. It runs unofficial reverse-engineered clients through either whatsapp-web.js or Baileys, giving developers multi-session messaging without Meta's official Cloud API.

SetupDocsCommunityMaturity

Verdict Our OpenWA run passed 5,897 of 5,903 Jest tests after a 59-second install, but npm audit still found 5 high-severity vulnerabilities. It is a capable gateway for disposable-number hobby and internal automation when you accept that a successful API response may not mean delivery.

Full review →

84

camofox-browser

jo-inc/camofox-browser · ★ 11k ▲212/7d · JavaScript

Camofox Browser wraps the Firefox-based Camoufox anti-detection engine in a REST API and MCP server for AI agents. It returns compact accessibility snapshots with stable element references, manages isolated browser sessions, and supports clicks, typing, screenshots, downloads, cookies, proxies, and structured extraction without asking an agent to parse a full page.

SetupDocsCommunityMaturity

Verdict Our Camofox Browser build passed in 7 seconds with 0 known npm vulnerabilities, but Jest stopped before executing tests because `jest-junit` was missing. Use it when an authorized agent needs compact browser controls and ordinary automation fingerprints are the blocker.

Full review →

85

claude-ads

AgriciDaniel/claude-ads · ★ 9.3k ▲250/7d · Python

Claude Ads is a Claude Code skill and Python toolkit for auditing, planning, monitoring, and reporting paid advertising across 12 platforms. It turns authorized exports or account reads into evidence-backed findings and drafts changes behind approval, rollback, and verification gates.

SetupDocsCommunityMaturity

Verdict Our Claude Ads run installed 60 packages, passed its build, and reported 506 passing tests, but pip-audit still found 3 known vulnerabilities. Use it when a Claude Code based media team wants conservative, evidence-labeled work across several platforms and accepts that humans remain responsible for every mutation.

Full review →

86

actions-runner-controller

actions/actions-runner-controller · ★ 6.5k ▲12/7d · Go

Actions Runner Controller, usually called ARC, is a Kubernetes operator for creating and scaling self-hosted GitHub Actions runners. It adds runner capacity when workflows need it and can remove ephemeral runner pods after jobs finish.

SetupDocsCommunityMaturity

Verdict Our ARC checkout built successfully in 196 seconds, but only 7 of 12 test packages passed because the end-to-end path expected a kubeconfig that the sandbox did not have. Use ARC when GitHub Actions capacity belongs inside an existing Kubernetes platform and your team can own cluster security and scaling.

Full review →

87

volcano

volcano-sh/volcano · ★ 6.0k ▲19/7d · Go

Volcano is a Kubernetes-native batch scheduling system. It extends the standard kube-scheduler to run AI/ML, big data, and HPC workloads efficiently, with gang scheduling, queueing, fair-share, and preemption.

SetupDocsCommunityMaturity

Verdict Our sandbox run finished a clean install in 71 seconds and a successful build in 280 seconds, but 33 of 227 tests failed, all in e2e suites that need a live cluster. If you run batch AI or big data jobs on Kubernetes, Volcano is a proven, actively maintained scheduler with an unusually wide integration surface..

Full review →

88

loopx

huangruiteng/loopx · ★ 5.9k ▲112/7d · Python

LoopX keeps goals, approvals, evidence, quotas, and handoffs outside an AI agent's chat history so work can survive restarts and move between agent hosts. It sits above Codex, Claude Code, Cursor, and custom runners as a local control plane; it does not execute the agent's work itself.

SetupDocsCommunityMaturity

Verdict Our LoopX checkout installed only 3 npm packages in 6 seconds, but its 3,053 files and roughly 859,791 source lines describe a control system that requires deliberate operating habits. Use it when losing goal state, approval history, or ownership across long agent runs has become a recurring cost.

Full review →

89

kudu

AdventDevInc/kudu · ★ 3.5k ▲155/7d · TypeScript

Kudu is a desktop and command-line system cleaner for Windows, macOS, and Linux. It scans for disposable caches and logs, manages startup and privacy settings, and includes malware checks, with deletion kept local unless optional cloud features are enabled.

SetupDocsCommunityMaturity

Verdict Our Kudu run installed 564 packages, built in 16 seconds, and passed 2,613 of 2,614 tests with 1 skip, which is strong evidence for the checked-out code. Use it first as a scan-and-review tool, especially while v2.7.0 has open reports about signed binaries being flagged and cloud permissions defaulting on.

Full review →

90

WiiUDownloader

Xpl0itU/WiiUDownloader · ★ 2.1k ▲26/7d · Go

WiiUDownloader is a desktop app that downloads Wii U games, updates, DLC, and demos directly from Nintendo's CDN without requiring title keys. It solves the problem of abandoned, Windows-only Wii U USB Helper by providing a cross-platform, open-source downloader that also decrypts files for use on a real console or the Cemu emulator.

SetupDocsCommunityMaturity

Verdict Our build succeeded in 28 seconds on a fresh Debian container and produced no test output (0 passed, 0 failed of 0), so this is a small, compiling, active tool with no automated test safety net. If you need a no-title-key Wii U downloader on macOS, Linux, or Steam Deck, yes, use it.

Full review →

91

delegate-skills

amElnagdy/delegate-skills · ★ 2.0k ▲208/7d · JavaScript

delegate-skills is a collection of agent skills that lets one coding agent hand an implementation brief to a separate CLI, then bring back a structured report and working-tree diff for review. It supports direct dispatch or named fleet lanes while leaving the final commit with the orchestrator.

SetupDocsCommunityMaturity

Verdict Our harness could not run commit b19180c because JavaScript was unsupported and the repository had no Dockerfile, so we cannot vouch for its install or relay tests. delegate-skills is worth adopting when you already pay the mental cost of several agent CLIs and want their diffs to arrive in one shape.

Full review →

92

skill-up

alibaba/skill-up · ★ 905 ▲30/7d · Go

skill-up is a command-line evaluator for Agent Skills, including skills used by Claude Code, Codex, Qoder CLI, and Qwen Code. It runs YAML-defined cases, grades the results, produces local or CI reports, and ships a companion skill that can revise a skill or its eval suite after failures.

SetupDocsCommunityMaturity

Verdict Our npm run installed 150 packages in 35 seconds, but the package exposed no build or test target, so it did not verify the Go evaluator. skill-up is worth adopting when Agent Skills already affect real work and failures need to become repeatable regression cases across several clients.

Full review →

93

agent-deck

asheshgoplani/agent-deck · ★ 901 ▲48/7d · Go

Agent Deck is a terminal control panel for running many coding-agent sessions across projects. It organizes Claude Code, Codex, Gemini CLI, OpenCode, and other tools through tmux, then adds status tracking, worktrees, MCP and skill management, cost records, and optional phone control.

SetupDocsCommunityMaturity

Verdict Our Agent Deck build succeeded in 64 seconds, but 5 of 26 Go test packages failed during a 568-second run, including a watcher queue assertion. It is a capable choice for an experienced operator managing enough agents to justify a control plane, especially with Claude Code or Codex.

Full review →

94

paperclip

paperclipai/paperclip · ★ 81k ▲421/7d · TypeScript

Paperclip is a self-hosted control plane for coordinating teams of AI agents around company goals, tasks, reporting lines, budgets, approvals, schedules, and audit records. It does not build the agents; it connects Claude Code, Codex, OpenClaw, shell, HTTP, and plugin workers to persistent work with operator controls.

SetupDocsCommunityMaturity

Verdict Our Paperclip build passed in 121 seconds, but its test command was still running when our 900-second limit expired. Use it when many agents already create ownership, budget, and audit problems that a task board cannot solve.

Full review →

95

CloakBrowser

CloakHQ/CloakBrowser · ★ 31k ▲191/7d · Python

CloakBrowser is a browser-automation wrapper that replaces ordinary Playwright or Puppeteer Chromium with a build patched to expose fewer automation and fingerprint clues. It is meant for authorized scraping, testing, and agent workflows that are blocked when a site recognizes a standard automated browser.

SetupDocsCommunityMaturity

Verdict Our CloakBrowser run installed 47 packages and built in 61 seconds combined, but pytest finished with 54 failures and 15 errors, so we would trial it against one authorized target before paying or scaling. Its familiar Playwright surface and source-patched Chromium are useful when ordinary automation is rejected.

Full review →

96

sim

simstudioai/sim · ★ 30k ▲59/7d · TypeScript

Sim is a shared workspace for building, deploying, and monitoring AI agents and automated workflows. Teams can assemble work visually, through chat, or in code, then connect models, business apps, files, tables, and searchable knowledge in one system.

SetupDocsCommunityMaturity

Verdict Our Sim checkout installed 2,519 packages and used 2,560 MB, then both the 8-second build and 203-second test command exited 1. Trial the published self-hosting images if one workspace for agents, data, schedules, and run monitoring would replace several internal tools.

Full review →

97

Archon

coleam00/Archon · ★ 23k ▲72/7d · TypeScript

Archon is an open-source workflow engine that turns an AI coding process into a repeatable YAML-defined sequence. It coordinates planning, implementation, testing, review, approval, and pull-request creation so an agent is less likely to skip a step or improvise the process each time.

SetupDocsCommunityMaturity

Verdict Our build finished in 59 seconds, but the full test command ended with 26 failures after 353 seconds. Archon has a sharp, useful idea: keep AI judgment inside a process that your team owns and can review.

Full review →

98

skyvern

Skyvern-AI/skyvern · ★ 23k ▲57/7d · Python

Skyvern is an open-source system for automating browser work with language models, computer vision, and Playwright-compatible controls. It aims to replace fragile scripts tied to fixed selectors with workflows that can interpret pages, take actions, extract structured data, and check results.

SetupDocsCommunityMaturity

Verdict Our build finished in 8 seconds, but the test run ended with 150 passed, 1 failed, 3 skipped, and 16 collection or setup errors. Skyvern is compelling when websites vary enough that maintaining fixed selectors has become the real cost, and its SDK plus workflow builder give it more range than a narrow agent library.

Full review →

99

spiderfoot

smicallef/spiderfoot · ★ 22k ▲182/7d · Python

SpiderFoot automates open-source intelligence collection for domains, IP addresses, networks, email addresses, usernames, people, and cryptocurrency addresses. Its web interface and CLI connect more than 200 modules, pass discoveries between them, correlate results, and export the resulting investigation data.

SetupDocsCommunityMaturity

Verdict Our SpiderFoot environment installed 85 packages in 28 seconds, but its 900-second test command timed out with 6 failures and pip-audit found 19 known vulnerabilities. Use it for authorized, analyst-led reconnaissance when breadth matters and every result will be verified.

Full review →

100

TikTokDownloader

JoeanAmier/TikTokDownloader · ★ 16k · JavaScript

DouK-Downloader is Chinese-first software, and a full English README is available. It downloads and records Douyin or TikTok posts, account feeds, images, and live streams, while also saving collected metadata to files or exposing it through a local API.

SetupDocsCommunityMaturity

Verdict Our DouK-Downloader run installed 57 packages in 31 seconds and built in 8 seconds, but it offered no test target and cannot promise maintained request signing. Use version 5.8 for supervised, authorized archives when you can refresh Cookies, inspect output, and repair workflows after platform changes.

Full review →

101

midscene

web-infra-dev/midscene · ★ 15k ▲99/7d · TypeScript

Midscene is a TypeScript GUI automation system that asks a multimodal model to find and operate controls from screenshots. It plugs into Playwright, Puppeteer, Vitest, YAML workflows, and agent skills, with adapters extending the same approach to mobile and desktop interfaces.

SetupDocsCommunityMaturity

Verdict Our Midscene checkout built in 13 seconds, but its 2,236-package install used 2,057 MB and the full test target exited 1 despite 88 reported passes and 0 failed cases. Trial it for visual surfaces that defeat selectors, especially canvas, cross-origin, and native interfaces.

Full review →

102

k-skill

NomaDamas/k-skill · ★ 7.6k ▲103/7d · JavaScript

k-skill is a Korean-first collection of 118 agent skills for Korean transport, government data, shopping, finance, documents, local services, and language tasks. The README and feature guides are written primarily in Korean, with no English README listed. It installs into Claude Code, Codex, OpenCode, OpenClaw, and other skill-aware agents.

SetupDocsCommunityMaturity

Verdict Our 91 MB k-skill install built in 6 seconds, but testing stopped after 5 seconds because Debian lacked `python3.11-venv`. For Korean-speaking users, the 118-skill catalogue is unusually practical and its read-only or manual-handoff boundaries are often explicit.

Full review →

103

flyte

flyteorg/flyte · ★ 7.5k ▲73/7d · Go

Flyte 2 is a Python-facing system for running data, machine-learning, model-serving, and agent workflows on managed compute. This repository contains its Go control-plane work and API definitions, while the full Python SDK lives in a separate repository and the public self-hosted Flyte 2 backend is still described as coming soon.

SetupDocsCommunityMaturity

Verdict Our Flyte checkout built in 231 seconds, but 10 of 159 tests failed when embedded Postgres could not initialize, so the backend is not a clean drop-in on a fresh Debian box. Flyte 2 deserves evaluation by Kubernetes-equipped ML platform teams, especially those already invested in Flyte, but the main README still sends today's production backend users to Union.ai.

Full review →

104

md2wechat-skill

geekjourneyx/md2wechat-skill · ★ 3.6k ▲11/7d · Go

md2wechat is a Chinese-first CLI and agent skill that turns Markdown into formatted WeChat Official Account articles, checks them, creates images, and can send finished work to the WeChat draft box. The README and linked operating guides are in Chinese; the license contains an English legal text, but the repository does not list a full English user guide.

SetupDocsCommunityMaturity

Verdict Our md2wechat run installed 0 packages in 13 seconds, but the repository exposed no build or test command to verify the shipped CLI path. It is a sensible fit for Chinese WeChat creators who want agent-readable checks and accept the paid renderer, credential work, and source-available license.

Full review →

105

OpenMausBot

milind-soni/OpenMausBot · ★ 2.9k ▲432/7d · TypeScript

OpenMausBot is a local-first desktop chat app in English where each contact is a separate Claude, Codex, or Grok agent running through a CLI on your computer. It gives those agents their own conversations, models, approvals, optional cloud or local computers, connected apps, routines, and voice features.

SetupDocsCommunityMaturity

Verdict Our OpenMausBot run built in 21 seconds and passed 1,692 of 1,701 tests, but one process-cleanup test failed after the 1,405 MB install, so the current source is substantial and still has a reliability edge to investigate. Try it if a local desktop roster is more useful than one agent terminal and you can keep approvals enabled.

Full review →

106

karpenter

kubernetes-sigs/karpenter · ★ 2.2k ▲20/7d · Go

Karpenter is the provider-neutral core of a Kubernetes node autoscaler. It watches pods the scheduler cannot place, chooses machines that satisfy their resource and placement rules, asks a cloud-provider implementation to create those nodes, and removes capacity when it is no longer useful.

SetupDocsCommunityMaturity

Verdict Our Karpenter run installed 204 packages and built successfully, but only 15 of 25 test suites passed before Go exited 1 after 88 seconds. Adopt it when node selection and consolidation are large enough problems to justify a provider-specific rollout, disruption drills, and close controller monitoring.

Full review →

107

agent-teams-ai

777genius/agent-teams-ai · ★ 2.1k ▲29/7d · TypeScript

Agent Teams AI is a desktop control room for several coding agents working on the same project. It turns their tasks, messages, terminal sessions, code changes, reviews, and usage into a visual workspace so a developer can supervise a team instead of juggling separate terminals.

SetupDocsCommunityMaturity

Verdict Our Agent Teams AI test process was still running at 900 seconds after a successful 101-second build, so the desktop download is easier to adopt than the source tree is to validate. Use it when you already run several supported coding agents and need one place to see their tasks, diffs, messages, and cost.

Full review →

108

gawkbot

najmuzzaman-mohammad/gawkbot · ★ 1.4k · Go

gawkbot turns a described or demonstrated work routine into a locally run bot and a small app for managing its results. It is meant to automate recurring work across more than 1,200 integrations while holding sends, commits, purchases, and deletions for human approval.

SetupDocsCommunityMaturity

Verdict Our sandbox install succeeded in 151 seconds, but this checkout exposed no build or test target for us to run. gawkbot is worth a careful local trial if its approval-first approach solves a real workflow and you already use one of its supported coding runtimes.

Full review →

109

ongrid

ongridio/ongrid · ★ 1.0k ▲35/7d · Go

Ongrid is a self-hosted operations workspace where an AI agent can inspect metrics, logs, traces, topology, runbooks, and hosts from a web console or team chat. It aims to shorten incident diagnosis, then puts production-changing commands behind a human approval flow.

SetupDocsCommunityMaturity

Verdict Our Ongrid run built in 104 seconds and passed all 117 discovered tests, which supports a serious read-only pilot for a Linux fleet. Do not enable production write actions until your exact release proves that redirection, pipes, substitutions, and compound commands all enter the approval flow.

Full review →

110

link-cli

stripe/link-cli · ★ 782 ▲11/7d · TypeScript

Link CLI gives software agents one-time payment credentials from a user's Link wallet, so an agent can complete a purchase without storing the user's real card details. It supports ordinary checkout forms, Stripe-hosted payment pages, and sellers using machine payment protocols, with the user approving a spend request before credentials are issued.

SetupDocsCommunityMaturity

Verdict Our build finished in 7 seconds, and all 166 tests passed, which makes Link CLI unusually credible for a project still at version 0.14.0. Use it if you are building a US-focused purchasing agent and want approval-gated credentials without exposing a real card.

Full review →

111

hey-cli

basecamp/hey-cli · ★ 371 ▲15/7d · Go

HEY CLI brings HEY Mail, Contacts, Calendar, and Journal into a terminal, with both an interactive TUI and scriptable commands. It solves the gap between a web inbox and shell or coding-agent workflows by exposing readable output, JSON pipelines, live event watching, and MCP tools.

SetupDocsCommunityMaturity

Verdict Our build succeeded in 48 seconds, but the test run ended with 36 of 39 checks passing. HEY CLI is the clearest choice for a HEY customer who wants one path across a TUI, shell automation, and coding agents, because its commands reflect HEY concepts instead of flattening them into generic IMAP.

Full review →

112

agentcore-cli

aws/agentcore-cli · ★ 283 ▲4/7d · TypeScript

AgentCore CLI creates, runs, packages, deploys, and operates AI agents on Amazon Bedrock AgentCore. It turns agent code and JSON resource specifications into AWS infrastructure, with commands for memory, gateways, credentials, evaluations, policies, knowledge bases, observability, and payments.

SetupDocsCommunityMaturity

Verdict Our AgentCore CLI run passed 6,030 of 6,148 tests and found 0 known npm vulnerabilities, but 23 tests still failed after an 848 MB install. It is a credible control surface for a team already committed to Bedrock AgentCore and AWS operations.

Full review →

113

career-ops

career-ops-hq/career-ops · ★ 72k ▲1.1k/7d · JavaScript

Career Ops is a local, AI-assisted workspace for finding jobs, comparing listings with your background, tailoring a CV, and tracking applications. It runs inside coding agents such as Claude Code and Codex, keeps its working files in a project directory, and leaves submission decisions to the user.

SetupDocsCommunityMaturity

Verdict Our Career Ops install stopped after 30 seconds because Playwright rejected Node.js 18.20.8, despite the project documenting Node.js 18+ support. Try it if you want a hands-on, agent-driven search system and will inspect every recommendation and document before use.

Full review →

114

EasySpider

NaiboWang/EasySpider · ★ 45k ▲41/7d · JavaScript

EasySpider is a Chinese-first visual web crawler with partial English documentation. It lets people build browser automation and data-collection flows by selecting page elements, arranging actions, and running the saved task through a desktop interface or command line.

SetupDocsCommunityMaturity

Verdict Our install pulled 468 packages and 392 MB in 40 seconds, while npm audit found 45 known vulnerabilities, so EasySpider deserves a disposable-machine trial before any sensitive login is used. Its visual selector and flowchart can save non-programmers real time on browser-bound collection.

Full review →

115

gkd

gkd-kit/gkd · ★ 42k ▲356/7d · Kotlin

GKD is a Chinese-language Android app for clicking interface elements when user-written selector rules match the current screen. Its README is in Chinese and includes no English guide; an open issue requests English language support. It is useful for skipping repetitive prompts and automating small actions across other apps.

SetupDocsCommunityMaturity

Verdict Our GKD run installed in 16 seconds, but its build and tests both ended with exit 126 and `./gradlew: Permission denied`, so source adopters should budget a manual build fix before evaluation. The app is worth trying for Chinese-speaking Android users who will audit their subscriptions and want precise selector rules.

Full review →

116

video-use

browser-use/video-use · ★ 25k ▲412/7d · Python

video-use is a skill and helper toolkit that lets Claude Code, Codex, Hermes, or another shell-capable agent edit raw video through transcripts and selected visual timelines. It turns an approved edit plan into cuts, subtitles, color treatment, overlays, and a rendered `final.mp4` while keeping the source footage outside the skill directory.

SetupDocsCommunityMaturity

Verdict Our video-use install took 28 seconds, used 508 MB, and built in 8 seconds, but the repository exposed no automated test target. It is a sensible experiment for transcript-led talking-head edits when a human approves the plan and checks the render.

Full review →

117

openwork

different-ai/openwork · ★ 24k ▲149/7d · TypeScript

OpenWork is a desktop workspace and shared capability layer for AI agents. One remote MCP lets Codex, Claude Code, Cursor, OpenCode, and other clients search and run assigned skills, plugins, MCP connections, Google Workspace actions, and Microsoft 365 actions without copying each integration into every client.

SetupDocsCommunityMaturity

Verdict Our OpenWork install consumed 1,439 packages and 2,055 MB, then tests stopped after 5 seconds because Bun was missing, so source contributors need more than the pnpm quick path implies. The two-tool MCP design is a sensible way to share capabilities across Codex and Claude Code, especially for a small team.

Full review →

118

suna

kortix-ai/suna · ★ 20k ▲22/7d · TypeScript

Kortix, in the repository still named Suna, is a system for running AI agents inside isolated cloud computers and reviewing their work through git-style change requests. It gives a company one place to version agent instructions, skills, memory, connectors, schedules, and the machine configuration behind automated work.

SetupDocsCommunityMaturity

Verdict Our Suna install pulled 2,651 packages and 3,393 MB, then build and tests both failed within 4 seconds because Bun was missing. Kortix is worth evaluating when isolated agent computers, reviewed change requests, and shared company configuration are the actual requirements.

Full review →

119

res-downloader

putyy/res-downloader · ★ 20k ▲96/7d · Go

res-downloader is a Chinese-first desktop application, with a separate English README, for finding and downloading video, audio, images, M3U8 playlists, and live streams passing through your computer. It runs a local proxy, watches network requests, and presents likely media resources in a simpler interface than a general packet-capture tool.

SetupDocsCommunityMaturity

Verdict Our res-downloader build took 3 seconds, but its only discovered Go test package failed because the embedded `frontend/dist` files were missing. Use the packaged desktop release when a Chinese media app exposes no convenient URL and interactive proxy capture is acceptable.

Full review →

120

phoneinfoga

sundowndev/phoneinfoga · ★ 18k ▲68/7d · Go

PhoneInfoga is a command-line and web tool for collecting public information connected to a phone number. It normalizes the number, identifies basics such as country and carrier, then helps an investigator search external services and the open web for leads.

SetupDocsCommunityMaturity

Verdict Our PhoneInfoga run built in 13 seconds, but 3 of 12 tested packages failed and upstream says future bugs will not be fixed. It remains useful for bounded, supervised OSINT because it combines number parsing, scanner orchestration, search links, an API, and a browser interface.

Full review →

121

ego-lite

citrolabs/ego-lite · ★ 16k ▲615/7d · JavaScript

ego lite is a macOS Chromium browser built so people and coding agents can work in separate Task Spaces while sharing login state. This repository contains the MIT-licensed `ego-browser` helper and agent skill; the browser application itself is a separate free download.

SetupDocsCommunityMaturity

Verdict Our ego-browser helper installed 49 packages, passed all 299 tests, and reported 0 known npm vulnerabilities, but that clean result does not cover the separate browser binary or its session boundary. Try it on a dedicated low-privilege Mac profile for supervised work where shared login state saves real time.

Full review →

122

automatisch

automatisch/automatisch · ★ 14k ▲5/7d · JavaScript

Automatisch is a self-hosted workflow builder for connecting online services and moving data between them without writing each integration from scratch. It targets the same trigger-and-action work as Zapier, while keeping workflow data and third-party credentials on infrastructure you control.

SetupDocsCommunityMaturity

Verdict Our Automatisch install pulled 727 packages in 71 seconds, but its tests stopped after 8 seconds because the required `.env.test` file was missing. It is worth a controlled trial for a team that wants visual automation on its own servers and can own four services, durable secrets, and integration credentials.

Full review →

123

escrcpy

viarotel-org/escrcpy · ★ 12k ▲349/7d · JavaScript

Escrcpy is a desktop app for viewing and controlling Android devices through a graphical interface built around scrcpy. It brings mirroring, keyboard mapping, multi-device operations, wireless connections, automation, and an MCP-based assistant into one place, reducing the need to juggle separate ADB commands and utilities.

SetupDocsCommunityMaturity

Verdict Our clean-container build failed after 24 seconds with exit code 127. Escrcpy is appealing for people who have outgrown plain scrcpy and genuinely need multi-device control, keyboard mapping, or visual automation in one desktop app.

Full review →

124

web-access

eze-is/web-access · ★ 9.0k ▲72/7d · JavaScript

Web Access is a Chinese-first Agent Skill that teaches Claude Code and other SKILL.md-capable agents how to choose web tools and drive a logged-in Chrome or Edge session through CDP. An English translation exists through the README language menu, but the repository documentation and issue discussion are primarily Chinese.

SetupDocsCommunityMaturity

Verdict Our sandbox produced no install, build, or test result for Web Access because its JavaScript skill layout was unsupported and it ships no Dockerfile. Version 2.5.4 is worth reading if you use Claude Code in Chinese and explicitly want an agent inside your current Chrome or Edge session.

Full review →

125

agenta

Agenta-AI/agenta · ★ 4.8k ▲24/7d · TypeScript

Agenta is a shared workspace for building agents through chat, connecting them to tools, and running them interactively or on schedules and app events. It adds files, team access, configuration history, traces, costs, permissions, and background execution around harnesses such as Claude Code, Pi, and Codex.

SetupDocsCommunityMaturity

Verdict Our Agenta API install and build finished in 35 seconds combined, but pytest stopped after 6 seconds because two configured arguments were unrecognized. Trial Agenta when you need Claude Code or Codex to live inside a shared, traceable workspace and you can operate its multi-service stack.

Full review →

126

background-agents

ColeMurray/background-agents · ★ 3.2k · TypeScript

Background Agents, branded Open-Inspect in its documentation, is a self-hosted system for sending coding work to remote sandboxes and checking the result later. It connects a web app, Slack, GitHub, Linear, schedules, and webhooks to coding agents that can edit repositories and open pull requests.

SetupDocsCommunityMaturity

Verdict Our Background Agents run installed 1,296 packages and 1,184 MB, built in 64 seconds, then exited 1 after a 408-second test run whose log included 18 failures and 1 error. It is worth studying or piloting for a trusted engineering organization that wants shared background coding sessions and can operate the cloud pieces.

Full review →

127

phone-harness

ShawnPana/phone-harness · ★ 2.8k ▲149/7d · Python

Phone Harness gives a coding agent basic sight and input on a real iPhone or Android phone. It uses iPhone Mirroring plus macOS capture and input APIs for iOS, or adb screenshots, the accessibility tree, and input commands for Android, without installing an app on the phone.

SetupDocsCommunityMaturity

Verdict Our phone-harness run installed 33 packages in 26 seconds and built in 7 seconds, but there was no test target to check its device helpers. Try it for supervised agent experiments on a phone you can watch and unlock yourself.

Full review →

128

krops

polarsquad/krops · ★ 143 ▲8/7d · Rust

Krops is an English-language reference implementation for managing cloud infrastructure through Kubernetes resources and GitOps. It combines Flux, Cluster API, and existing cloud controllers instead of adding its own controller or resource type. Platform teams can study or fork it to manage clusters and AWS resources from the same YAML, policy, and audit system used for workloads.

SetupDocsCommunityMaturity

Verdict Our krops build took 75 seconds and all 100 Rust tests passed in 44 seconds, making the bootstrap code the strongest measured result in this group. Fork it when your platform team already trusts Flux and Cluster API, and when AWS plus local Docker cover the environments you can verify yourself.

Full review →

129

n8n-workflows

Zie619/n8n-workflows · ★ 57k ▲74/7d · Python

n8n-workflows is a searchable collection of workflow JSON files gathered from n8n examples and other sources. Its FastAPI and SQLite site helps you find and download examples, but it does not run automations or replace an n8n instance.

SetupDocsCommunityMaturity

Verdict Our n8n-workflows audit found 32 known vulnerabilities and no test target, while the checked tree held 2,061 workflow JSON files rather than the README's advertised 4,343. Use it as a large idea shelf whose contents must be inspected, repaired, and tested in a disposable n8n instance.

Full review →

130

zapret-discord-youtube

Flowseal/zapret-discord-youtube · ★ 33k ▲351/7d · Batchfile

Zapret Discord YouTube is a Russian-language Windows bundle for working around provider-level blocking of Discord, YouTube, and other configured services. The main documentation is in Russian and no English guide is included; it packages Batch scripts, traffic-routing strategies, WinDivert, and binaries from the upstream zapret projects.

SetupDocsCommunityMaturity

Verdict Our 2026-08-26 Debian lab with 3 CPUs and 8 GB of RAM could not run this Windows Batch and WinDivert bundle, so no independent install or test result exists. It is a practical option for Russian-speaking Windows users who can inspect binaries, accept administrator-level network changes, and test provider-specific strategies.

Full review →

131

ios_rule_script

blackmatrix7/ios_rule_script · ★ 28k · JavaScript

ios_rule_script is a Chinese-first collection of traffic-routing rules, rewrite rules, and automation scripts for tools such as Quantumult X and MagicJS. No English documentation is evident in the supplied README excerpt, so English-only users should expect to translate the instructions. It solves the tedious work of gathering and organizing rules and small device-side automations from many sources.

SetupDocsCommunityMaturity

Verdict Our install completed in 14 seconds, and our build completed in 2 seconds. Use ios_rule_script if you already understand the destination clients and want a broad Chinese-language rule warehouse that was pushed today.

Full review →

132

awesome-n8n-templates

enescingoz/awesome-n8n-templates · ★ 25k

Awesome n8n Templates is an English-led collection of 280+ workflow JSON files for the n8n automation platform, with translated READMEs in 13 other languages. It saves users from drawing every workflow from scratch, but it does not turn community files into maintained integrations.

SetupDocsCommunityMaturity

Verdict Our lab found no runnable ecosystem or Dockerfile; issue 201 lists 7 files rejected by n8n. Use this collection as a large reference shelf if you already know how to audit n8n nodes and credentials.

Full review →

133

cli

larksuite/cli · ★ 17k ▲115/7d · Go

Lark CLI is the official command-line interface for operating Lark and Feishu services such as Messenger, Docs, Base, Calendar, Mail, and Tasks. It gives people and AI agents structured commands for work that would otherwise require the web app or custom Open Platform code.

SetupDocsCommunityMaturity

Verdict Our Lark CLI install failed after 28 seconds because its installer could not find `checksums.txt`, so commit 35bd5ec is a poor choice for unattended bootstrap despite the project's broad official coverage. It is still worth evaluating for developers and controlled agents already committed to Lark, especially when dry runs and structured output can sit behind human approval.

Full review →

134

holehe

megadose/holehe · ★ 15k ▲82/7d · Python

Holehe is a command-line OSINT tool that checks whether an email address appears to be registered on many websites. It infers the answer from signup, login, and password-recovery responses, sometimes returning masked recovery details without intentionally sending a message to the address.

SetupDocsCommunityMaturity

Verdict Our Holehe install took 36 seconds, used 42 MB, built in 9 seconds, and had no test target, so its clean setup says little about whether 120-plus live provider probes remain correct. Use it only for authorized, low-volume reconnaissance where every hit is corroborated manually.

Full review →

135

superplane

superplanehq/superplane · ★ 7.5k ▲894/7d · Go

SuperPlane is an automation system for engineering work that crosses source control, CI, cloud infrastructure, monitoring, incident tools, and AI agents. It stores those steps as durable, Git-backed workflow apps with approvals, shared memory, and operator dashboards so a long process can survive failures and remain inspectable.

SetupDocsCommunityMaturity

Verdict Our SuperPlane run built in 11 seconds, but 9 of 142 tests failed, so its polished demo should lead to a bounded pilot rather than control of a critical release path. The app model is well suited to work where agents, approvals, events, and operators must share durable state.

Full review →

136

claude-code-security-review

anthropics/claude-code-security-review · ★ 6.2k ▲34/7d · Python

Claude Code Security Reviewer is a GitHub Action that sends pull-request changes to Claude Code, filters the resulting findings, and can post security comments on affected lines. The repository also supplies the prompt behind Claude Code's built-in `/security-review` command.

SetupDocsCommunityMaturity

Verdict Our build of Claude Code Security Reviewer installed 52 packages in 17 seconds and built in 6 seconds, but the harness found no test target to run. Treat it as a second reviewer for maintainer-approved code, never as the only security gate or as a safe scanner for hostile pull requests.

Full review →

137

Telegram-Media-Downloader

Neet-Nestor/Telegram-Media-Downloader · ★ 5.5k ▲43/7d · JavaScript

Telegram Media Downloader is an English-documented browser userscript that restores download buttons in Telegram Web, including chats and channels where saving is restricted. It handles images, GIFs, videos, stories, and some voice messages without asking for a separate Telegram API account.

SetupDocsCommunityMaturity

Verdict Version 1.212 has no package-defined install, build, or test path, so reliability rests on live Telegram Web behavior and manual checking. Use it for occasional, authorized single-file saves when the browser button is the whole problem.

Full review →

138

youtube-automation-agent

darkzOGx/youtube-automation-agent · ★ 3.5k ▲213/7d · JavaScript

YouTube Automation Agent is a Node.js application that turns a topic into a script, images, narration, a rendered video, metadata, and a scheduled YouTube upload. It is designed to replace the repetitive handoffs between idea research, asset generation, editing, SEO, publishing, and basic analytics for a small automated channel.

SetupDocsCommunityMaturity

Verdict Our AgentTube test step passed but took 652 seconds, while npm audit reported 29 vulnerabilities, including 1 critical and 18 high. Its approval, provenance, resume, and scene-repair controls make it a credible private trial for a technical creator.

Full review →

139

goldie

kacperkapusciak/goldie · ★ 2.1k · TypeScript

Goldie is a command-line tool and coding-agent skill that turns scripted mobile-app flows into framed App Store and Google Play screenshots. It also records preview clips, opens a browser studio for visual edits, and checks the exported media against store rules.

SetupDocsCommunityMaturity

Verdict Our Goldie install took 94 seconds and 492 MB, and its 97-second build passed, but there was no test target to run. It is worth trying when store media is recurring work and your team already maintains simulator flows.

Full review →

140

macos-harness

browser-use/macos-harness · ★ 868 ▲32/7d · Python

macOS Harness gives a coding agent direct Python access to screenshots, keyboard and pointer events, Accessibility data, Apple Events, browser control, files, and shell commands on a Mac. Instead of shipping a tool for every application, it exposes a small set of low-level primitives and lets the agent write missing automation during the task.

SetupDocsCommunityMaturity

Verdict Our Debian run built macOS Harness in 7 seconds, then passed 10 of 26 tests because the remaining 16 required unavailable macOS ApplicationServices bindings. Try it on a dedicated Mac when an agent needs to bridge browser and native applications, and treat every permission as production access.

Full review →

141

backlink_skills

flaqai/backlink_skills · ★ 715 ▲27/7d · Python

Backlink Skills is primarily documented in Simplified Chinese, with a full English README and shorter documentation in many other languages. It is a collection of Codex workflows for qualifying product directories, recording authorized submissions, and writing SEO content for websites, LinkedIn, Medium, and WeChat.

SetupDocsCommunityMaturity

Verdict Our lab could not run backlink_skills because it found no supported executable ecosystem and no Dockerfile, so this review cannot offer an independent install or test result. The quality-first V2 workflow is worth borrowing for a small, authorized directory campaign because it treats relevance, approval, evidence, and ambiguous outcomes seriously.

Full review →

142

mcp-server

sv-number/mcp-server · ★ 556 ▲1/7d · JavaScript

SV Number MCP Server lets an AI agent rent a temporary phone number, wait for its SMS verification code, and close or cancel the order. It exposes nine tools to MCP clients such as Claude Code, Codex, Cursor, and Claude Desktop, while the actual number inventory comes from a paid hosted service.

SetupDocsCommunityMaturity

Verdict Our SV Number MCP Server run installed 101 packages, built in 13 seconds, and reported 0 known vulnerabilities, but there was no test target to exercise its nine tools. Use it for legitimate, supervised temporary SMS verification when broad country inventory matters.

Full review →

143

bettergi-scripts-list

babalae/bettergi-scripts-list · ★ 549 ▲8/7d · JavaScript

bettergi-scripts-list is a Chinese-language community catalog of automation scripts for BetterGI and Genshin Impact. The repository has no English documentation; it collects combat routines, map paths, JavaScript tasks, and card-game strategies that run through the separate BetterGI Windows application.

SetupDocsCommunityMaturity

Verdict Our ArtifactScore run installed 10 packages in 18 seconds, but the repository supplied no build or test target, so that clean audit does not establish that any game automation works. Use this catalog only if you already accept BetterGI's Windows, Chinese-interface, display, and account-risk constraints.

Full review →

144

GitHub520

521xueweihan/GitHub520 · ★ 30k ▲64/7d · Python

GitHub520 is documented primarily in Chinese, and the repository does not provide an English guide. It publishes a frequently refreshed hosts file that maps GitHub domains to selected IP addresses, aiming to reduce slow loads and missing images for users whose normal DNS route performs poorly.

SetupDocsCommunityMaturity

Verdict Our run installed 61 packages and built in 7 seconds, but the absence of a test target and 5 pip-audit findings make GitHub520's generator less reassuring than its tiny size suggests. Use the published list as a reversible diagnostic or personal workaround, especially through SwitchHosts, not as an unquestioned fleet-wide networking policy.

Full review →

145

obscura

h4ckf0r0day/obscura · ★ 27k · Rust

Obscura is an open-source headless browser engine written in Rust for web scraping and AI-agent automation. It runs JavaScript through V8 and aims to replace headless Chrome in existing Puppeteer or Playwright workflows while using a smaller native engine.

SetupDocsCommunityMaturity

Verdict Our build succeeded in 220 seconds, but 6 of 26 tests failed. Obscura is one of the more interesting attempts to reduce dependence on headless Chrome, and its V8, CDP, Puppeteer, and Playwright ambitions make it worth a controlled trial.

Full review →

146

XianyuAutoAgent

shaxiu/XianyuAutoAgent · ★ 9.2k ▲69/7d · Python

XianyuAutoAgent is a Python bot that reads seller messages on China's Xianyu marketplace and drafts or sends replies through a configured language model. The README and setup material are in Chinese, with no English guide in the repository; its main jobs are classifying questions, answering product queries, and handling price negotiation with conversation history.

SetupDocsCommunityMaturity

Verdict Our XianyuAutoAgent install took 15 seconds and the build passed, but there was no test target and pip-audit found 3 known vulnerabilities. Use it only as supervised starting code for a Chinese-speaking seller who accepts cookie maintenance, model-data exposure, and marketplace risk checks.

Full review →

147

Sequoia-X

sngyai/Sequoia-X · ★ 7.3k ▲353/7d · Python

Sequoia-X is a Python screener for mainland China's A-share market. Its documentation is mainly Chinese, with English headings and an English subtitle but no full English setup guide; it downloads daily market data, runs technical screens, stores results in SQLite, and sends picks to Feishu.

SetupDocsCommunityMaturity

Verdict Our Sequoia-X run installed 67 packages and built cleanly, but 3 of 9 tests failed after 501 seconds, all in the Feishu notification suite. Use it as inspectable starting code for a Chinese-market hobby screener if you already use Feishu and will verify every signal.

Full review →

148

firstmate

kunchenguid/firstmate · ★ 6.1k · Shell

firstmate is a directory of instructions and shell tools that turns one terminal coding agent into a supervisor for several coding agents. It gives each worker a separate Git worktree, watches their progress, and brings one human the resulting pull requests, local merges, or research reports.

SetupDocsCommunityMaturity

Verdict Our Firstmate run installed 35 packages in 16 seconds and built in 4 seconds, but pytest collected 0 tests and exited 5, so that clean setup result does not validate the crew workflow. Use it if you already trust terminal coding agents and want one of them to supervise isolated workers under explicit merge rules.

Full review →

149

centaur

paradigmxyz/centaur · ★ 1.3k ▲20/7d · Python

Centaur is a self-hosted platform that lets a team talk to coding agents from Slack or an API and gives each conversation a Kubernetes sandbox. It stores the conversation and execution state, brokers approved credentials, runs durable workflows, and can host Claude Code, Codex, Amp, or another command-line agent behind one shared control plane.

SetupDocsCommunityMaturity

Verdict Our Centaur checkout installed 364 pnpm packages in 20 seconds, but it offered no root build or test target to prove that the multi-service platform worked. Centaur is worth evaluating for a platform team that already runs Kubernetes and needs shared, credential-aware coding agents across chat and APIs.

Full review →

150

eve-software-factory-template

vercel-labs/eve-software-factory-template · ★ 1.1k ▲20/7d · TypeScript

The Eve Software Factory Template deploys Foreman, a four-stage coding-agent workflow that takes work from GitHub or Linear and ends with a reviewed draft pull request. It separates classification, planning, implementation, and review into different agents while reserving approval and merge decisions for people.

SetupDocsCommunityMaturity

Verdict Our Eve template install took 32 seconds, but its build failed in 8 seconds because the required `FACTORY_REPO` value was absent, and the repository supplied no test target. That is acceptable for a deployment template only if your team is already committed to Vercel Connect and can trial it against a scratch repository.

Full review →

151

lanshu-create-ai-presenter-video

cclank/lanshu-create-ai-presenter-video · ★ 1.0k ▲7/7d · Python

The primary README is in Chinese, and English operational documentation is available in `SKILL.md` and its reference files. Lanshu Create AI Presenter Video is a Codex skill that organizes a topic or script, an authorized adult presenter image, voice generation, presenter animation, lip sync, captions, editing, rendering, and quality checks into one resumable job.

SetupDocsCommunityMaturity

Verdict Our install added 35 packages in 11 seconds and the build passed in 4 seconds, but no test target exercised an actual video job. Lanshu is useful as a cautious production checklist for Codex users who already own the missing generation services and can review paid outputs.

Full review →

152

rewards-farmer

User0332/rewards-farmer · ★ 879 ▲37/7d · Python

Rewards Farmer is a Python browser bot that completes Microsoft Rewards searches and dashboard tasks through Edge. It replaces a daily manual routine with Selenium automation, using public trend feeds or an Ollama model to generate search terms.

SetupDocsCommunityMaturity

Verdict Our Rewards Farmer run installed 35 packages in 35 seconds, but pytest completed 0 tests because `selenium` could not be imported. Treat it as inspectable personal automation for an expendable account, not as a dependable service for an account you care about.

Full review →

153

Cybermes

Zyrexnn/Cybermes · ★ 826 ▲60/7d · Python

Cybermes is an English-language offensive-security framework for authorized reconnaissance, vulnerability checking, evidence collection, and report generation. It combines a Go MCP server, Python orchestration, outside security tools, and more than 200 playbooks so an AI client or terminal workflow can carry an assessment from scope checks to written findings.

SetupDocsCommunityMaturity

Verdict Our Cybermes install added 252 packages and the audit found six high-severity advisories, while the repository offered no npm test target, so this is a framework to isolate and inspect before it touches an authorized target. Its MCP tools, evidence layout, and scope engine can save an experienced tester repetitive work.

Full review →

154

scalable-cli

ScalableCapital/scalable-cli · ★ 470 ▲3/7d · Rust

Scalable CLI is the official command-line interface for Scalable Broker accounts. It replaces browser scripting with structured commands for viewing portfolios, market data, savings activity, and supported account changes, while requiring explicit confirmation for sensitive actions.

SetupDocsCommunityMaturity

Verdict Our build failed after 127 seconds, and the test command failed after 51 seconds. Use the official v1.0.0 binaries if you are a Scalable Broker customer who values JSON output, local automation, and deliberate confirmation before account changes.

Full review →

155

nft-public-mint

morsyxbt/nft-public-mint · ★ 286 ▲9/7d · TypeScript

NFT Public Mint Sniper is a command-line tool that prepares and sends SeaDrop public-mint transactions on Ethereum, Base, and Robinhood Chain. It reads the price, fee recipient, wallet limit, and opening time from the contract so a user does not need an OpenSea login or API token.

SetupDocsCommunityMaturity

Verdict Our NFT Public Mint Sniper run installed 67 packages in 9 seconds and built in 7 seconds with 0 audit findings, but there was no test target for the code that signs real transactions. Use it only with a dedicated, minimally funded wallet after reading the roughly 150-line signing path and rehearsing on a low-stakes mint.

Full review →

156

AI-Trader

HKUDS/AI-Trader · ★ 22k ▲121/7d · Python

AI-Trader is a hosted and self-hostable platform where software agents publish trading ideas, simulate trades, follow other agents, and compete in challenges. It gives each registered agent a token and paper balance, then exposes feeds, positions, notifications, and copy-trading actions through HTTP and WebSocket APIs.

SetupDocsCommunityMaturity

Verdict Our AI-Trader run installed 46 packages in 10 seconds with 0 audit findings, but the repository exposed neither a build target nor a test target for us to verify. Use it as a paper-trading and agent-coordination research project, with a human approving consequential actions.

Full review →

157

follow-builders

zarazhangrui/follow-builders · ★ 6.7k ▲45/7d · JavaScript

Follow Builders is a Claude Code and OpenClaw skill that turns a centrally maintained feed of AI podcasts, posts, and company blogs into a scheduled or on-demand digest. It solves the filtering problem for readers who want a fixed list of AI practitioners summarized inside an agent they already use.

SetupDocsCommunityMaturity

Verdict Our sandbox produced no install, build, or test result for commit 6df06d7 because the JavaScript repository matched no supported ecosystem and had no Dockerfile. Try Follow Builders if you already use Claude Code or OpenClaw and accept its fixed editorial feed.

Full review →

158

wecom-cli

WecomTeam/wecom-cli · ★ 3.1k ▲37/7d · Rust

wecom-cli is a command-line client for WeCom whose README and command guidance are primarily Chinese, with no English README linked. It lets people and AI agents work with messages, mail, documents, spreadsheets, tasks, calendars, meetings, cloud-drive files, and contacts from a terminal.

SetupDocsCommunityMaturity

Verdict Our wecom-cli installation stopped after 6 seconds with a Corepack wrapper error, so commit 59604ae never reached build or tests in our sandbox. The published CLI is still worth a guarded trial for a Chinese-speaking WeCom user who needs broad office automation, but its write paths require read-back checks and human approval.

Full review →

159

ars0n-framework-v2

R-s0n/ars0n-framework-v2 · ★ 816 ▲19/7d · Go

Ars0n Framework v2 is a self-hosted bug bounty workspace that puts more than 50 reconnaissance and scanning tools behind a web interface, shared database, and guided workflows. It is written in English and aims to teach beginners a specific hunting method while letting experienced users control the same system through a 142-tool MCP server.

SetupDocsCommunityMaturity

Verdict Our Ars0n server build took 39 seconds and both Go tests passed, but 2 tests cannot validate a 50-plus-container security platform with an unauthenticated 142-tool MCP endpoint. Use beta 0.1.0 on an isolated machine when you want its guided bug bounty method and accept hands-on Docker work.

Full review →

160

fire-your-seo-agency

leopard627/fire-your-seo-agency · ★ 438 ▲19/7d

fire-your-seo-agency is a Claude Code skill that guides an agent through technical SEO, answer-engine visibility, AI crawler access, brand consistency, and Naver search work. Its canonical operating instructions are Korean, while the README and all six reference guides have English versions for human readers.

SetupDocsCommunityMaturity

Verdict Our sandbox did not run commit eb9be9f because it has no supported ecosystem and no Dockerfile, so its audit workflow remains unverified by our lab. Use fire-your-seo-agency as a reviewable checklist for a Claude Code operator, especially on a Korean-market site, rather than as proof that an automated SEO system works.

Full review →

161

wechaty

wechaty/wechaty · ★ 23k · TypeScript

Wechaty is a TypeScript toolkit for writing chatbots against one shared set of contacts, rooms, messages, and login events. A separate connector, called a puppet, links that bot code to WeChat, WeCom, WhatsApp, or another supported messaging service.

SetupDocsCommunityMaturity

Verdict Our Wechaty checkout installed 1,302 packages, failed both build and test, and reported 75 known vulnerabilities, including 4 critical. Existing users with a proven puppet may still value its common bot API, but a new production project should start elsewhere unless WeChat compatibility is non-negotiable.

Full review →

162

gpt_nerver

Nervercc/gpt_nerver · ★ 1.2k ▲399/7d · Python

gpt_nerver is a Chinese-language PyQt6 desktop application for bulk ChatGPT account maintenance, registration, and Plus subscription workflows. The repository has no English guide; its Chinese documentation explains how it coordinates accounts, email sources, proxies, virtual cards, redemption codes, and several maintainer-run services.

SetupDocsCommunityMaturity

Verdict Our gpt_nerver run installed 45 packages and built successfully, but 2 of 32 tests failed in the session-refresh path that account maintenance relies on. Treat it as research material, not an account-operations product: its workflows hold sensitive credentials, depend on private services, and automate areas where provider rules can change.

Full review →

163

outlook-auto-register

lxf746/outlook-auto-register · ★ 802 ▲67/7d · Python

Outlook Auto Register is a Chinese-first Python tool for creating Outlook accounts in batches through Microsoft's web endpoints instead of a browser. A full English README exists, and the project combines CAPTCHA solving, residential proxies, recovery proofs, token collection, account storage, and liveness checks in one console.

SetupDocsCommunityMaturity

Verdict Our sandbox installed 47 packages in 13 seconds and built Outlook Auto Register in 4 seconds, but it exposed no automated test target. Use it only as code to inspect during authorized protocol research, on a host where port 8890 and the credential database stay private.

Full review →

164

AutoHedge

The-Swarm-Corporation/AutoHedge · ★ 6.1k ▲427/7d · Python

AutoHedge is a Python program that sends a market prompt through several AI agents for thesis, sentiment, risk, and order drafting. The repository also contains Solana swap functions, but its default command is an interactive research loop rather than the continuous autonomous trading service promised by the README.

SetupDocsCommunityMaturity

Verdict Our AutoHedge run installed 130 packages and found 12 known vulnerabilities, while the repository supplied no test target, so it should not control real money. The 51-file project is useful as readable agent-orchestration source and a starting point for experiments.

Full review →

165

Polymarket-Telegram-Bot

Cleverfuxaqo1668/Polymarket-Telegram-Bot · ★ 170 ▲1/7d · JavaScript

Polymarket-Telegram-Bot is the public landing repository for a hosted Telegram bot that alerts users to large Polymarket trades and offers one-tap betting and copy trading. The repository does not contain that bot: it has a README, an MIT license, and a small WebSocket feed example.

SetupDocsCommunityMaturity

Verdict Our 3-CPU, 8 GB sandbox did not run commit 8ea5e5c because the lab found no supported ecosystem and no Dockerfile, so this repository cannot substantiate the bot it advertises. Do not choose it as an open-source, self-hosted trading bot or as auditable wallet software.

Full review →

166

Polymarket-Telegram-Bot

techcomet122583/Polymarket-Telegram-Bot · ★ 125 · JavaScript

Polymarket-Telegram-Bot is a public page for a hosted Telegram trading bot that advertises whale alerts, one-tap bets, copy trading, and a built-in Polymarket wallet. The repository does not contain that bot: it contains the README, an MIT license, and a short JavaScript WebSocket feed example.

SetupDocsCommunityMaturity

Verdict The repository contains 1 JavaScript feed example and no Telegram bot implementation, so it cannot support an independent code review of the wallet or trading claims. Use the example as a tiny WebSocket reference if it saves you time.

Full review →

167

iready-tool

Restdritower/iready-tool · ★ 110 · JavaScript

iReady Tool is a browser extension, userscript, and bookmarklet that tries to skip i-Ready lessons, alter recorded minutes, answer questions, and bypass diagnostics. Its stated use directly interferes with an educational platform's assessments and activity records.

SetupDocsCommunityMaturity

Verdict Our sandbox did not run iReady Tool because it exposes no supported runnable ecosystem or Dockerfile, and the repository has 0 releases and 0 open issues or pull requests to substantiate compatibility. Do not use it on a student account: its purpose is to falsify educational activity, and the recommended silent MSI download comes from an unrelated domain.

Full review →