mrkeyoor.com
_
Repos
Libs
MCP
Guides
Trends
Ask
Sat 14 Nov 12:15 UTC
Evaluations
Open-source projects, reviewed the honest way — including who should skip them.
All
Automation
LLM Tools
Self-Hosted
Dev Tools
Data
Web
AI Tools
AI Tools
★ 1.7k · JavaScript
Papermorph
Papermorph is DozenTwelve's MIT-licensed agent skill for turning textbooks into narrated, interactive web lessons and stories into animated books. Its documented workflow plans chapters, scripts and storyboards before producing narration and animation, then delivers a static book folder.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 34k · Python
mcp-for-blender
MCP for Blender connects an AI client to a live Blender scene through a Python process and a Blender add-on. Siddharth Ahuja's independent integration lets the assistant inspect the scene, change objects and materials, and execute Blender Python.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 5 · Python
EvoVLM
EvoVLM searches prompts, image preprocessing, generation budgets and answer extraction around frozen vision-language models for scientific chart understanding. The supplied overview and runtime guide are in English, and the overview includes a Chinese summary.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 80 · Python
academic-deai
Academic DeAI 3.1.0 is an open-source, model-agnostic skill for Chinese and English academic editing. It supplies editing instructions and optional checking tools; the host agent and selected model perform the revision.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.6k ·
Charakuru
Charakuru is Nano's Japanese-led kit for turning a character illustration into a rigged VRM avatar, with English documentation and interface support. You review images, choose model candidates and inspect movement while an agent handles Tripo and Blender operations. It is source-available under redistribution and business-use restrictions.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 2.3k · TypeScript
mesh-avatar-studio
Mesh Avatar Studio turns an illustration into a moving 2D character with help from a coding agent and a local editor. Its English README explains creation, streaming and app playback, with Japanese and Simplified Chinese translations linked. You inspect the prepared rig and correct it before exporting the avatar.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 79k · Rust
photocraft
PhotoCraft is a free, open-source image editor for layered photos, masks, text and Photoshop documents. It offers Photoshop-style controls on the desktop and in a browser, with CLI and MCP interfaces for automation. The project calls itself early alpha.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.4k · Python
VisionHOPE
VisionHOPE is a research visual backbone that turns images into features for classification, object detection and segmentation. Its memories and update rules adapt within an image; the current public SRNL interface resets memory between forward calls.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 2.7k · C
muse-gadget-sdk
Muse Gadget SDK connects your own ESP32 hardware or Linux computer to Meta's hosted Muse assistant. You can add a physical screen, button or sensor, or give Muse commands on a Linux machine. The SDK code is Apache 2.0, while access to Muse follows separate token terms.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 246 · Python
ComfyUI-VDN-H3
ComfyUI-VDN-H3 changes how MiniMax-H3 keeps track of nearby and distant frames while generating video in ComfyUI. It adds Video DeltaNet hybrid attention to an existing H3 model, so you still need the base model, text encoder and video/audio decoders.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 9.3k · TypeScript
pocketpal-ai
PocketPal AI runs language models on iOS and Android so you can chat after downloading a model, without a backend account. It also supports voice and tools, with optional online features that change which data stays on the phone.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 2.2k · TypeScript
ohmygame
OhMyGame is a beta game-making application that combines an AI agent, a design canvas and media tools. Its README describes keeping design documents, generated assets and game code together, with plugins for existing engines and connections to external coding agents.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 2.5k · Rust
ooosplat
OOOSplat is a local desktop application that turns videos or photo sequences into 3D Gaussian Splatting projects you can preview, edit and export. It joins media preparation, COLMAP camera reconstruction and Brush training in one workspace. An English README and English interface are available, though supplied issue and pull-request evidence documents untranslated Brush training messages.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 28k · TypeScript
dexter
Dexter is an autonomous financial research agent that turns questions into research steps and uses tools to gather financial data. It documents per-query logs that let you inspect retrieved results and the model's interpretation, with use restricted to educational and informational purposes.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 2.5k · TypeScript
oh-my-ppt
Oh My PPT is a desktop workbench for generating HTML slide decks with AI, editing their elements and exporting presentations. Its main README is Chinese, with an English README available; it is aimed at people who want to revise generated slides instead of accepting a fixed output.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 2.5k · TypeScript
Agentero
Agentero brings research papers, linked notes and AI-assisted reading into a desktop workbench. Its main README and getting-started guide are in Chinese, and an English README is available. It aims to reduce the copying between a paper library, a notes app and an AI conversation.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 9.6k · Python
mini-swe-agent
Mini SWE Agent is a Python coding agent that asks a language model to work through tasks using bash commands. Its default loop keeps a linear message history and executes each action independently, giving developers and researchers a small control flow to inspect and change.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 21k
▲479/7d
· Python
claude-video
Watch, from bradautomates/claude-video, gives coding agents timestamped video frames and transcripts from URLs or local files. It documents local extraction and a Gemini engine, with native captions preferred over optional speech transcription.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 25k
▲22/7d
· TypeScript
nextai-translator
NextAI Translator is a desktop app and browser extension for translation, polishing and summarization through configured language-model providers. Its README also documents screenshot translation, text-to-speech and vocabulary books. These are documented capabilities, not workflows verified in our sandbox.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 22k
▲611/7d
· TypeScript
Toonflow-app
Toonflow is an AI workspace for writing scripts, organizing references and generating images and video clips on an infinite canvas. Its main README is in Simplified Chinese, and English documentation exists. It connects your chosen model services to the creative workflow for short dramas, animated comics and short videos.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 5.7k
▲323/7d
· TypeScript
AutoRAG
AutoRAG Agent is a personal librarian that searches files and connected sources, reads supporting documents and produces answers with citations. The current TypeScript application also has a Lite MCP retrieval mode, while the original Python RAG pipeline optimizer lives under legacy/.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 5.2k
▲97/7d
· TypeScript
MonkeyCode
The chaitin/MonkeyCode repository's current README introduces MonkeyAI as a team workspace for AI-assisted office, programming and design tasks. Its Chinese documentation describes shared models, MCP tools and resource permissions. The retained English MonkeyCode introduction describes the original development platform. Our measured backend build does not verify the current workspace deployment.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 136
▲24/7d
· JavaScript
grok-bot-templates
Templates for Grok Bot is an independent collection of profiles that define a bot's job, sources, deliverables and approval boundaries. Users copy a profile into Grok Bot and connect its named plugins. The repository supplies configuration and optional catalog tooling; our run did not verify hosted bot behavior.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 3.0k
▲183/7d
· JavaScript
WorkDaddy
WorkDaddy is a desktop enhancement helper for WorkBuddy and CodeBuddy. Its documented features include account switching, session migration, model management and automation. It connects through local debugging interfaces and requires a matching official client. Chinese, English and Japanese guides are available.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 7.0k
▲54/7d
· TypeScript
T3MP3ST
T3MP3ST is an offensive-security framework that connects an existing coding agent or a local model to security tools through a browser War Room, CLI, HTTP API and MCP server. It is intended for authorized testing. Its README explicitly says coordinated end-to-end swarm exploitation is unbenchmarked and still unreliable; our sandbox run covered repository commands, not a security mission.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 68k
▲29/7d
· Python
annotated_deep_learning_paper_implementations
Labml.ai Deep Learning Paper Implementations is a collection of PyTorch neural-network and algorithm implementations with explanatory notes beside the code. It helps readers connect a paper's equations to the operations a program actually performs.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 30k
▲277/7d
· HTML
guizang-ppt-skill
Guizang PPT Skill is a Chinese-first skill for Claude Code, Codex and other coding agents, with an English README available. It generates browser-based HTML presentations using supplied visual templates and also documents optional visuals, covers and presenter tools.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 11k
▲30/7d
· Python
copilot-cli
GitHub Copilot CLI is a terminal coding assistant that can discuss code, edit files and work with GitHub repositories, issues and pull requests. It supports Model Context Protocol (MCP) connections for additional tools and data. The public repository does not make the software freely modifiable: its license explicitly withholds modification and derivative-work rights.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 12k
▲22/7d
· Python
kornia
Kornia is a PyTorch library for processing images and working with camera geometry. Many operations preserve the gradients a learning system needs to adjust its parameters, so you can include them inside a training pipeline rather than moving images into a separate processing step.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 3.8k
▲217/7d
· Python
skills
Scenario Agent Skills gives coding agents instructions and scripts for creative work, including workflows through the Scenario MCP service. A separate set of expert-tool families drives installed creative applications and game engines. It helps you give an agent a specific production procedure, though our run did not evaluate finished assets.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 9.9k
▲62/7d
· Rust
anarlog
Anarlog is a desktop meeting notetaker that captures device audio, transcribes speech and turns meeting text into editable notes. Its community application stores notes and transcripts locally. Transcription and summaries have separate provider settings, so local storage alone does not establish that meeting content stays on the device.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 16k
▲505/7d
· Python
pr-agent
PR-Agent is a community-maintained AI code-review tool that can describe pull requests, suggest changes and answer questions about a diff. It is the open-source project formerly maintained by Qodo, separate from Qodo's current product. You choose a model and connect the tool to your code-hosting platform through an action, CLI or service.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 5.7k
▲313/7d
· Python
agent-sprite-forge
Agent Sprite Forge is a set of skills for Claude Code, Codex and Grok that turns an approved character image into animated sprite assets. It coordinates image and video generation, then uses Python tools to remove backgrounds, align frames and package actions for game projects. The documentation requires visual review and says editor imports are unverified.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 4.9k
▲96/7d
· Python
KiroCrew
Kiro Crew is an open source development workspace that runs on hardware you control. Its README describes persistent sessions, memory and scheduled work, accessible through a desktop app, web dashboard, CLI and connected messaging services. Our run checked setup steps, not persistence or unattended task completion.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 9.3k
▲226/7d
· JavaScript
Orkas
Orkas is a desktop application whose Commander agent coordinates specialists and installed CLI agents such as Claude Code and Codex. Its README describes projects that retain goals, rules, memory and files between conversations. Our sandbox did not verify completed agent work or project continuity.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 30k
▲1.1k/7d
· TypeScript
hypit
Hypit gives coding agents such as Claude Code and Codex a workflow for creating videos with captions, footage and effects tied to spoken words. It keeps the composition editable so you can change a presenter, script or product and reuse suitable existing material. Its published license adds conditions to Apache 2.0, including restrictions on hosted services and commercial redistribution.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 16k
▲187/7d
· TypeScript
Paradev
Paradev is a desktop workspace for CLI coding agents, terminals, code review and browser previews. It gives tasks separate Git worktrees. Its source is available under Elastic License 2.0, which restricts providing substantial functionality as a hosted or managed service to third parties.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 5.7k
▲116/7d
· Python
see-through
See-through is a research pipeline that separates a single anime character illustration into editable layers and exports a layered PSD. It uses layer generation and depth estimation to help recover hidden parts and infer drawing order. The output is a starting point for an artist's work, with rigging explicitly outside the project's scope.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 29k
▲90/7d
· Python
Resume-Matcher
Resume Matcher is a self-hosted resume editor that tailors a master resume to individual job descriptions. You can review suggested wording, check the resulting document and export a PDF, using a remote model, a local model or a coding-agent workflow.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 7.5k
▲1.1k/7d
· TypeScript
openbot
OpenBot is a desktop workspace for persistent AI agents, with separate conversations and workspaces, queues, file transfers and an embedded browser. Its current README calls it a development preview and warns that agents operate with broad host access without per-action confirmations after first-launch consent.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 11k
▲101/7d
· TypeScript
inkos
InkOS is an AI writing system for fiction and other story projects, with a Chinese primary README and separate English documentation. It documents chapter generation, persistent story state and revision through a browser workbench or terminal commands. English creation is documented, but our run stopped during dependency installation before any writing could be evaluated.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 2.0k
▲57/7d
· Python
skills
Higgsfield AI Skills gives coding agents Markdown instructions for creating media and brand assets through Higgsfield's CLI and service. It works with agents including Claude Code and Codex, and groups tasks such as generation, product photography and brandbooks into separate workflows. You get instructions and supporting tools for an authenticated service workflow, not a local model engine.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 5.3k
▲88/7d
· Python
obsidian-second-brain
Obsidian Second Brain gives AI agents workflows for saving, finding and maintaining linked Markdown notes in an Obsidian vault. The supplied README describes agent commands for capture, retrieval, ingestion and note revision; those descriptions are not evidence that the workflows succeeded in our sandbox.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 10k
▲255/7d
· TypeScript
infinite-canvas
Infinite Canvas is an image-creation workspace that combines a visual canvas, AI generation, reference-image editing, prompts and assets. A local Canvas Agent connects the canvas with coding assistants through MCP. The supplied main and Canvas Agent README extracts are primarily Chinese; an English operating guide was not assessed.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 41k · Python
ColossalAI
Colossal-AI supplies components for distributing model training and inference across accelerators. It helps engineers divide computation and memory use when a model or training job outgrows a simpler PyTorch setup.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 12k
▲342/7d
· TypeScript
genoffice
GenOffice is a desktop suite for editing Word documents, spreadsheets, presentations and PDFs, with AI editing alongside the file. It also handles Markdown and HTML, and supplies a command line and agent integrations for working on Office files without manually opening each editor.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 6.6k
▲784/7d
· Rust
hex
HEX is a local voice dictation app from anomalyco. Its main Mac release targets Apple silicon and macOS 15 or newer, with separate Windows and Linux betas. It transcribes speech locally and pastes text into the active app. Optional OpenCode rewriting sends text and application context to a configured model provider.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 7.1k
▲149/7d
· Python
open-duet
Open Duet is a workspace for named AI agents with their own instructions, conversations, memory and assigned folders. It lets one operator organize delegated work and recurring prompts while bringing a separately configured model engine.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 11k
▲121/7d
· Python
drawio-skill
Drawio Skill is an agent skill that turns descriptions, code, and infrastructure definitions into editable draw.io diagrams. It helps a coding assistant maintain the diagram after the first draft, including source synchronization and different views of the same architecture model.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 16k
▲21/7d
· Python
docker-android
Docker-Android runs Android emulators in Docker containers so you can see their screens in a browser and control them remotely. It gives developers a reusable Android workspace for app debugging and automation, with separate MCP and sponsor-only AI agent options.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.8k
▲189/7d
· JavaScript
CozyClay
CozyClay is a browser-based studio for arranging a 3D scene, posing characters and setting camera shots before handing references to an AI video model. It exports frames, reference clips and prompts, and lets an AI assistant control the scene through an in-app panel, MCP or a terminal.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 8.2k
▲75/7d
· Python
seedance-2.0
Seedance 2.0 Skill OS is an agent skill for planning shots, binding references and continuing from an accepted clip. Your provider generates the video and handles its costs. The supplied README identifies v6.7.0; our sandbox measurements concern commit 4668457.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 2.4k
▲68/7d
· Rust
Beav
Beav is an AI-assisted workspace for collecting source material, drafting social content, and preparing media and publishing packages. The project is primarily Chinese-language, with an English README available. Its public code is a 2.5.0 snapshot, while current desktop installers are maintained separately.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 5.0k
▲11/7d
· TypeScript
PilotDeck
PilotDeck is an AI assistant that organizes ongoing work into projects with their own files, memory, and skills. It provides English and Chinese documentation and lets you inspect and edit remembered information. It targets recurring work that needs more continuity than a single conversation.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 8.3k
▲708/7d
· TypeScript
rakazo
Consider Rakazo for a bounded trial if you need persistent AI bots and can operate their database, storage and computer providers. Rakazo is an open source, self-hosted AI assistant with persistent bots, conversations, memory and computer access. Its README labels it beta. Our run on 2026-10-17 at commit e55263f installed and built the source, but did not verify a working assistant deployment.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 2.4k
▲251/7d
· TypeScript
BeefTV
BeefTV is a desktop video-creation workspace that connects prompts, reference material, and generated media on a freeform canvas. Its README and linked quick-start guide are Chinese, with no English edition linked there. It keeps a local workspace while letting you configure the model services that generate content.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 6.6k
▲104/7d
· TypeScript
OpenDots
OpenDots is a customizable workspace for persistent AI assistants, with editable documents, chat, optional computer access, and connections to external tools. It helps developers build a single-owner assistant application, while conversations depend on CopilotKit Intelligence and a configured model provider.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 2.0k
▲104/7d
· JavaScript
reelmimic
ReelMimic is a local web app that studies a reference video's pacing and visual style, then coordinates coding agents to make a new animated video from your brief. You approve a storyboard before production and can request changes at specific moments in the finished video.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.2k
▲45/7d
· Python
easyread
EasyRead is a local paper reader that translates PDFs, keeps the original page beside the translation, and attaches notes and AI discussion to passages. Its main documentation is Chinese, with an English README and English interface available. You can also read the original without translating it.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.4k
▲21/7d
· Python
motion-video-kit
Motion Video Kit is a Claude Code skill with instructions, reference notes, and helper scripts for making business commercials. It helps organize storyboards, code-built animation, audio, and independent critique, but you still supply the renderer, assets, and judgment.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 553
▲4/7d
· Python
livecanvas
LiveCanvas is a Chinese-first agent skill that turns a brief into an animated visual and Apple Live Photo resources; an English README exists, while detailed production guides remain in Chinese. It guides a coding assistant through research, animation, and packaging so you can deliver an editable project alongside the preview.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 21k
▲53/7d
· TypeScript
voyager
Voyager is a browser extension that adds folders, reusable prompts, message timelines, and other controls to AI chat websites. It helps you find and reuse work inside Gemini, AI Studio, ChatGPT, Claude, and DeepSeek, with different features available on each site.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 7.6k
▲10/7d
· TypeScript
superdesign
Superdesign is the original IDE extension for generating and previewing interface drafts beside your code. Its README says this version is no longer actively maintained and directs users to a web app and a separate coding-agent skill.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 558
▲12/7d
· Python
V3R1T4S
Use V3R1T4S if you want to supervise a coding agent investigating checkable research problems and can review its evidence yourself. Avoid relying on it for peer-reviewed findings: its citation guide says there has been no outside expert review. V3R1T4S combines open-problem definitions, computational objects and a contributor workflow; our sandbox run covered only a generator subtree.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.0k
▲43/7d
· JavaScript
superdesign-skill
Superdesign Skill gives coding agents a workflow for designing interfaces, presentations, and graphics through the Superdesign canvas. It helps an agent use the existing application as design context, but requires a separate CLI and a hosted-service login.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 9.7k
▲135/7d
· Python
universal-modder
Universal-modder gives coding agents game-modding instructions, a Python toolbox, and shared notes about specific games. It helps connect engine research, asset preparation, and in-game verification, with fal MCP support for generating art and sound.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 291
▲3/7d
· C++
DeepEP-Ascend
DeepEP-Ascend moves data between Huawei Ascend chips during training and inference, especially when a mixture-of-experts model sends work to different experts. Its README opens in Chinese and provides an English introduction and detailed English operating instructions. It is a hardware-specific communication library for infrastructure engineers.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 639
▲6/7d
· C++
DeepGEMM-Ascend
DeepGEMM-Ascend is a library of matrix-multiplication kernels for Huawei Ascend processors used in AI workloads. It gives model and kernel developers a familiar DeepGEMM interface while handling hardware-specific data layouts and execution details.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 527 · Python
hypoarena
Hypoarena is an offline workbench for checking how hypothesis-generation pipelines handle evidence, debate, and ranking on synthetic material. The README is in English, while detailed documentation, including its limits and grounding rules, is largely in Chinese.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 440
▲6/7d
· Python
jeeves
Jeeves is a self-hosted model that answers yes/no, multiple-choice, and rating questions about text, returning probabilities your application can use. It can generate reasoning before choosing an answer and provides an API compatible with Jev-style decision workflows.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 27k
▲127/7d
· Python
faster-whisper
Faster-whisper is a Python library that turns audio into text using Whisper models on your own machine. It uses the CTranslate2 inference engine and gives an application control over CPU or NVIDIA GPU execution, batching, and timestamps.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 3.4k
▲36/7d
· TypeScript
HeliosGen
HeliosGen is a desktop canvas for connecting prompts, reference media, and image or video generators into reusable workflows. It keeps your project database and saved media on your computer, while its default generation service, kie.ai, receives jobs over the internet.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.7k
▲192/7d
· TypeScript
anidoodle
Anidoodle is a coding-agent skill and TypeScript engine for making drawn illustrations, animations, and interactive web art as editable code. It helps keep a picture and its moving versions in the same source instead of treating each export as a separate asset.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.6k
▲8/7d
· Python
jeff
Jeff is a local model that takes a situation and a list of choices, then returns a probability for each choice. It helps applications route requests or classify text without generating and parsing a written answer.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 840
▲23/7d
·
Offensive-Security-AI-Models
Offensive-Security-AI-Models is an English-language reading list of open-weight models for authorized security research, with links and comparison tables. It helps you shortlist models by task, format, and tool support, but supplies no runnable application.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 2.0k
▲255/7d
·
awesome-claude-video-skills
Awesome Claude Video Skills is a directory of video-making skills and toolkits for Claude Code, Codex, and other coding agents, with English and Simplified Chinese READMEs. It groups projects by the videos they make and links to previews, source code, and README-based security grades.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.5k
▲14/7d
· Rust
ollaya
Ollaya runs local models that turn messages or other data into choices, scores, and probabilities without generating a written answer. It downloads models by name and serves them through a local API, including a format compatible with TypeSafe clients.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 6.8k
▲493/7d
· HTML
logo-design-skill
Logo Design Skill gives Claude Code and other compatible agents a process for developing logos, from the brief to editable SVG artwork and delivery files. It combines design instructions, a searchable reference library, and Python helpers for inspecting and presenting concepts.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 15k
▲785/7d
·
awesome-opus5-5-videos
Awesome Opus 5.5 Videos is a curated collection of code-made animations, creator posts, and shared prompts, with links to live remakes. It helps you find a visual direction to try with a coding agent, though some entries contain only partial directions rather than a reproducible recipe.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 16k
▲2.0k/7d
· JavaScript
lemo-opuscar
Lemo-Opuscar is a library of code-made short films, reusable style directions, and a Claude Code skill for creating your own. It gives a coding agent examples and production guides so a film can be drawn and assembled with local tools rather than a video-generation service.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 425
▲2/7d
· TypeScript
product-film-skill
Product Film is a Claude Code skill that turns your product's components and design rules into a scripted promotional video. It guides the brief, music edits, scene creation, and export so you can keep a product film alongside the application code.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 3.2k · Python
Fuxi
FuXi is a terminal AI coding assistant that reads a project, edits files, and runs commands using a model provider you choose or FuXi-managed models. English and Chinese documentation are available, but the agent's source is proprietary: the public repository contains documentation, installers, and an issue tracker.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 2.3k
▲54/7d
· Python
jarvis
Jarvis is a desktop voice assistant that can use recent room conversation and saved personal memory to answer requests through local models. It also supports text chat, dictation, and connected tools. Its source is available under a noncommercial license, with a separate license required for commercial use.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 34k
▲89/7d
· Python
fish-speech
Fish Speech turns text and reference recordings into synthetic speech, including scenes with several characters. Its current Drama 3 model supports revising a performance and editing part of an audio recording, giving developers and studios control beyond reading text aloud.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 4.1k
▲144/7d
· Python
onetake
onetake is a Claude Agent Skill for product launch films, teasers and feature demos built around continuous transitions. Try the public edition for noncommercial experiments if you can inspect the finished export yourself. Our sandbox record establishes setup outcomes, not rendering quality.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.0k
▲36/7d
· Python
awesome-claude-5-5-videos
Use Awesome Claude 5.5 Videos to find production references and trace their sources before choosing tools for a video. It collects source-linked examples, research data and maintenance scripts. Our run on October 14, 2026 used commit 87e5cbf; it did not test video production or establish a model ranking.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 181 · Python
interference-search
Interference Search explores several possible solutions at once, merges repeated states, and uses a judge to decide which branches deserve more work. It is a research codebase for arithmetic puzzles and generated programs, useful for studying how search can reduce repeated reasoning.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 384
▲3/7d
· TypeScript
shipvideo
Shipvideo, called LaunchVideo in its README, turns a URL or text prompt into an animated launch video. A language model writes an HTML scene, then a browser renderer and ffmpeg produce an MP4 inside an OpenComputer session.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 237 · TypeScript
storycast
Storycast turns a topic and chosen character into a narrated animated film, coordinating writing, images, speech, music, and editing through fal. It gives you a browser interface for that workflow, using your own fal key rather than local generation.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 477
▲7/7d
· Rust
omarchy-meeting-recorder
Omarchy Meeting Recorder records your microphone and computer audio, then turns the meeting into an editable transcript with audio playback. It is built for the Omarchy Linux desktop and helps you revisit a call without inviting a recording bot.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 34k
▲135/7d
· TypeScript
AionUi
AionUi is a desktop workspace where AI agents read and change files, generate documents, and show their output beside the conversation. It includes a built-in agent and can bring tools such as Claude Code into one interface, with browser access and scheduled tasks for work away from the desktop.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 27k
▲47/7d
· Python
MiniCPM-V
MiniCPM-V is a family of models for asking questions about images, documents, and video on local devices or servers. The repository also contains MiniCPM-o for speech interaction, and provides English and Chinese documentation.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 31k
▲252/7d
· Python
Unlimited-OCR
Unlimited-OCR is Baidu's document-parsing model project, with English instructions for turning images and PDF pages into parsed text. It includes examples for processing several pages together and a separate batch script that handles pages individually.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 467
▲15/7d
· TypeScript
bridgeclip
BridgeClip is a desktop app that finds moments in long videos and exports captioned clips. It renders locally while sending audio and transcripts to AI services through your credited OpenRouter account, with optional social publishing through Zernio.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 731
▲69/7d
· Markdown
ai-engineering-course
AI Engineering Course is an English reading curriculum that links to lessons about building and operating AI systems. It gives developers an ordered path through model foundations, retrieval, agents, and deployment, with articles on Outcome School and videos for some topics.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 3.2k
▲19/7d
· Python
CLM
CLM scores a supplied set of answers or actions against the situation you describe, then ranks them or returns a typed decision. It is meant for choosing among existing candidates, such as support departments or proposed agent actions, rather than generating an unrestricted answer.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.4k
▲36/7d
· Go
FounderOS
FounderOS is a business dashboard for a solo founder, with communication, client work, and AI agents in one operator console. It aims to reduce the effort of coordinating a small business across separate tools, while letting you control which connections and actions are enabled.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 674
▲9/7d
· Python
3dicon
Consider 3dicon for generated animated app icons if you can use hosted generation and review each result before shipping. It is a Claude Code plugin that produces animated WebP artwork through image generation, video generation and background removal. Our run on October 12, 2026, at commit 9539d3a recorded installation and build outcomes, but did not establish paid generation success or output quality.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.3k
▲6/7d
· Python
mini-AGI
mini-AGI is an experimental language model that trains on a stream of bytes and can keep learning from new files or conversations. It moves model components between disk, memory, and the GPU so researchers can study growing models on limited hardware. The README calls its current capabilities toy-level.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 4.2k
▲42/7d
· TypeScript
OpenIntelligentUI
OpenIntelligentUI is a chat application that turns agent answers into interactive explanations, comparisons, and small tools. It combines a web frontend with a Python agent so a user can change inputs inside an answer instead of asking for another paragraph.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 529
▲4/7d
· Python
jev-chat-jarvis-mac
Jarvis for Mac reads supported chat windows and suggests replies in a floating panel, with sending left to you. Its main documentation is Chinese, and there is no separate English README in the repository. It helps you draft responses without replacing your chat application.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 3.1k · Python
deepopen
DeepOpen is a Python engine that assigns predefined labels, ratings, or true-or-false probabilities to text and structured records. Its documentation is substantially Chinese, with an English introduction and detailed English API guidance available in the same README. It aims to support local routing decisions without generating free-form answers.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 887
▲11/7d
· Python
jev-chat-windows
JevChat-Windows reads a supported chat window with local text recognition and suggests replies that you can insert and send yourself. Its main documentation is Chinese, with an English guide for KakaoTalk support rather than a full English manual. The interface supports Simplified Chinese and Korean, and model judgment and drafting use configured external services.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 8.4k
▲72/7d
· Kotlin
jev-chat-jarvis
Jev reads chats on Android and suggests replies that it can fill into the message box for you to send. The repository contains a Chinese edition and a separate English WhatsApp edition, with English documentation for both. It helps you choose a response and check it for unwanted commitments before sending.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 28k
▲191/7d
·
pm-skills
PM Skills is a collection of instructions and guided workflows that help an AI assistant with product discovery, planning, and launch decisions. It gives product managers a repeatable way to question assumptions and draft working documents inside tools such as Claude Code and Cowork.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 6.6k
▲31/7d
· Python
Decepticon
Decepticon is an autonomous red-team system that uses language-model agents to plan authorized security engagements and run tools inside a Kali Linux sandbox. It coordinates work across an engagement, including interactive shells and stored findings, for operators who can review the plan and its results.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 10k
▲535/7d
· TypeScript
cindy
Cindy is a desktop and mobile assistant that lets AI agents work with your files and applications while sharing context across providers. Its recent issue discussions and release notes are predominantly Chinese, but English README and contributor docs exist. This repository contains the clients and shared packages, while the backend is separate.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 49k
▲132/7d
· Python
Umi-OCR
Umi-OCR is an offline desktop tool for extracting text from screenshots, batches of images, and scanned documents, with a Chinese primary README and an available English guide. It gives you a local interface for selecting text, cleaning up reading order, and producing searchable PDFs without sending documents to a hosted OCR provider.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.8k
▲223/7d
· Python
Hy-MT2
Hy-MT2 is Tencent's family of translation models for text that also has terminology, style, or formatting instructions. English and Chinese documentation are available, while much of the issue discussion is Chinese. The repository includes IFMTBench to check whether translators obey those constraints.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 19k
▲40/7d
· Python
lingbot-map
LingBot-Map turns a sequence of camera images into a three-dimensional reconstruction and estimates where the camera moved. It processes incoming frames while retaining geometric context, which makes it relevant to researchers working with long videos and robot perception.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 16k
▲18/7d
· Rust
burn
Burn is a Rust tensor library and deep-learning framework for training and running models from one codebase. Its main appeal is a common model API that can target CPU, CUDA, ROCm, Metal, Vulkan, WebGPU, remote devices, browsers, and some embedded environments.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 873
▲38/7d
· Rust
Mimi
Mimi's primary README is Chinese, and maintained English setup and usage guides are available. It is a desktop and Android app that turns computer or microphone speech into floating original-language or translated subtitles, using cloud speech providers or supported Apple on-device services.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 13k
▲1.8k/7d
· TypeScript
codex-security
Codex Security is a command-line scanner and TypeScript SDK that uses coding agents to find, validate, and help fix vulnerabilities in source repositories. It can turn a repository, path, Git diff, or imported alert backlog into findings with evidence, coverage records, patches, and machine-readable exports.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 19k
▲1.3k/7d
· TypeScript
video-shotcraft
Video Shotcraft is a Claude Code and Codex skill for making product promos with Remotion, real interface captures, reusable shot recipes, and a browser editing workbench. It gives an agent a production process and working motion code, rather than generating a finished video from one prompt by itself.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 146
▲1/7d
· JavaScript
dasheng
Dasheng (大声读 · ReadAloud) is a Next.js English reading-practice app with Chinese-language documentation. It aligns a speech transcript with a passage and combines word matching, completeness, pace arithmetic, and Jev text judgments into feedback. It does not assess pronunciation, stress, or accent. Our recorded run verified dependency installation, a build, and the selected test command, not a live reading session.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1 · TypeScript
Northstar
Northstar is a Chinese-language, Windows-first personal strategy workspace, and the repository provides no English guide. It turns long-term goals into weekly capacity, daily actions, reviews, guarded AI proposals, memories, and growth records, with a browser build and an unfinished Tauri desktop path.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 339
▲4/7d
· TypeScript
crush-monitor
Crush Monitor is Chinese-first; an English README exists, but the interface and analysis labels remain Chinese. It runs a local web app that sends pasted two-person chats to Jev or a text model, then labels emotions and intentions, scores signs of affection, and grades the user's replies.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 8.4k
▲72/7d
· Kotlin
jev-chat-jarvis
Jev Chat is an Android reply assistant written mainly in Kotlin, with English documentation plus Chinese and Vietnamese translations. It reads the open chat through Android accessibility APIs, asks models to judge intent and risk before drafting replies, then fills your chosen text into the message box without sending it.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 2.2k
▲29/7d
· Python
Qwen-Image-2.1
Qwen-Image-2.1 is a downloadable image model for creating pictures from text and editing one or more reference images. Its English documentation covers transparent output, local edits, multi-image composition, and several third-party runtimes, while this repository itself mainly supplies examples and a separate prompt-rewriting utility.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 363
▲20/7d
· Markdown
ai-engineer-roadmap
AI Engineer Roadmap is a Markdown reading list that orders AI topics from basic terminology through machine learning, language models, agents, inference, safety, deployment, and interviews. It solves the blank-page problem for beginners, but it is a publisher-led syllabus rather than a hands-on course or neutral survey.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 95 · PowerShell
Deepseek-Harness-Easy-Setup
DeepSeek Harness Easy-Setup is a Chinese-language Windows installer project for DeepSeek Harness, and the repository does not provide an English README. It bundles the upstream command-line package with a portable Node runtime, then adds shortcuts that start its local web interface or stop the process.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 8.7k
▲112/7d
· TypeScript
ZCode
ZCode's primary README is written in Simplified Chinese, and the repository includes a detailed English README. ZCode is an AI coding workspace that puts the same agent behind desktop, browser, and terminal interfaces, with local and remote project support.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 2.8k
▲6/7d
· Go
paperless-gpt
Paperless-GPT connects to Paperless-ngx and uses an LLM to suggest titles, tags, correspondents, dates, custom fields, and links between related documents. It can also run vision-based OCR, create searchable PDFs, and send approved changes back to the archive.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 12k
▲110/7d
· TypeScript
G0DM0D3
G0DM0D3 is an open-source chat interface that sends one prompt to several hosted or local language models, compares their replies, and returns a winner. Its main use is red-team prompt research, with a single-file browser app plus optional Next.js and Express surfaces.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 20k
▲4/7d
· Python
olmocr
olmOCR converts PDFs and page images into readable Markdown using a 7-billion-parameter vision-language model. It is built for documents whose tables, equations, handwriting, columns, headers, and reading order are hard for plain text extraction, with local GPU, remote inference, Docker, and S3 batch paths.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 336
▲2/7d
· Python
embodied-jev
Use EmbodiedJev if you want to inspect model decisions in simulated manipulation and can follow Chinese technical guides. EmbodiedJev is a browser workbench that uses MuJoCo to simulate a Franka Panda arm. Our run checked npm installation and the front-end build; it did not validate a working simulator session.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 299
▲4/7d
· Rust
underclass
Underclass combines several ChatGPT/Codex and GitHub Copilot subscriptions behind one local OpenAI-compatible address. It keeps sessions on the same account, removes exhausted accounts from rotation, and brings them back when their quotas reset.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 609
▲4/7d
· JavaScript
minecraft-agent
Minecraft Agent is a JavaScript Minecraft Java 1.16.5 experiment that combines Astra or Sol planning, JEV action selection, and Mineflayer execution on a fixed, surveyed route. It is useful for studying bounded model control. The supplied evidence does not establish general play on unknown worlds or isolate the models' contribution to completion.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.6k
▲7/7d
· Python
laya-coreml
Laya-CoreML runs specialized decision models locally on Apple Silicon and returns choices, scores, or yes/no probabilities instead of free-form text. It is for apps that need a small, predictable decision step without sending input to a hosted model API.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 651
▲2/7d
· Rust
CometixCode
CometixCode is an unofficial Rust reimplementation of Anthropic's Claude Code terminal assistant. It follows the published Claude Code interface and file structure closely, aiming to provide familiar coding-agent behavior in a native binary.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 306
▲1/7d
· Python
openJev-verdict-2.0
Use openJev-verdict-2.0 as a research reference if you can verify the model artifacts and investigate failing checks before integrating it. Our October 7, 2026 sandbox run at commit bff2856 recorded a failing pytest command. It did not validate Verdict 2.0 deployment, browser inference, training, or published performance claims. The repository distinguishes the GLiClass-based Verdict checkpoint from the separate Verdict 2.0 architecture for typed software workflows.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 72
▲2/7d
· Python
editaplot2026
EditaPlot's main README is written in Simplified Chinese, and the repository also provides a full English README. It is a Codex skill that inspects scientific tables, asks the user to confirm what each column means, then drives Origin 2026 to produce an editable OPJU project plus PNG, PDF, and TIF exports.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 267
▲4/7d
·
post-production-skill
Post Production Skill's README is in Simplified Chinese, with no English README, although the bundle includes an English master prompt. It is a narrow Codex skill that rewrites an idea or reference into a Seedance 2.5 prompt for one warm 1990s studio look, with a stable presenter, moving cameras, CRT hardware, and three-dimensional editing interfaces.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 7.1k
▲25/7d
· Python
laya-mlx
Choose Laya-MLX for local typed decisions on Apple Silicon if you can evaluate it on your target Mac. It answers choice, rubric-score and yes/no questions with probabilities rather than generated prose. Our run on October 6, 2026, at commit ca5940a reached test collection in a Debian sandbox but could not import mlx; it did not establish inference performance or correctness on supported hardware.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 317
▲2/7d
· Python
jev-align
jev-align is an experimental Python CLI for turning labeled examples into reusable Jev decision functions. It finds uncertain rows, asks a person to label them, and uses GEPA plus a separate reflection model to propose a better typed definition without accepting that proposal automatically.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 745
▲14/7d
·
awesome-jev-tools
awesome-jev-tools is a curated index of projects and practices built around TypeSafe AI's Jev typed-decision model. It helps developers find Jev examples by use case, while explicitly declining to verify that listed projects build, pass tests, reproduce their claims, or permit reuse.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 7.0k
▲426/7d
· Python
geo-sleuth
Geo-sleuth's working skill instructions and script output are written in Chinese, while the repository provides a full English README and says the agent can reply in your language. It gives coding agents a photo-geolocation workflow built from metadata, OCR, maps, terrain, satellite imagery, street views, and geometric checks, then asks for coordinates with an error radius and evidence image.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 322 · Python
Covalent-MAS
Covalent-MAS is a small Python interface layer for wiring molecule generators, optimizers, docking tools, and trajectory records into a covalent-drug design workflow. The repository currently supplies data contracts, JSONL storage, a sequential AutoDock Vina adapter, and a CLI for already prepared ligands, not the generation and optimization models described in its results section.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 786
▲5/7d
· Python
openjev
OpenJev is a self-hosted decision server that answers yes-or-no, multiple-choice, and scored questions with probabilities instead of free-form text. It speaks TypeSafe Jev's wire protocol and can use DiffusionGemma or four smaller open models, giving developers a typed alternative to parsing an LLM response.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 963
▲27/7d
· TypeScript
agency-agents-app
Agency Agents App is a native desktop installer and tracker for personas from the separate agency-agents catalog. Its README describes browsing source personas, rendering files for coding tools, recording managed installs and detecting outside edits. The coding tools execute the personas; this app does not run agents.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 9.2k
▲18/7d
· Cuda
DeepGEMM
Consider DeepGEMM if you maintain an LLM pipeline on NVIDIA SM90 or SM100 hardware and can validate its tensor layouts and numerical results. DeepGEMM is a CUDA kernel library for matrix multiplication, fused mixture-of-experts operations and other LLM computations. Our run on October 6, 2026, at commit 057ca59 did not establish a working GPU installation, kernel accuracy or throughput.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 940
▲23/7d
· Python
guizang-product-video-skill
Guizang Product Video Skill is a Chinese-first Claude Code and Codex skill. The repository documentation is in Chinese, and the README does not link an English version. It turns a software repository or changelog into a code-rendered product promo, including the story, product UI, animation, music, sound effects, MP4, and editable project.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 2.3k
▲16/7d
· Python
nimble
Nimble is a Python recipe and local model for making typed decisions about text. You provide a flat schema of boolean or multiple-choice questions, and it returns one allowed answer per field with candidate probabilities instead of generating prose.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 844
▲1/7d
· TypeScript
localjev
LocalJev is a Bun and TypeScript service that accepts typed Jev decision questions and sends them to a local model through an OpenAI-compatible chat endpoint. It solves a specific compatibility problem for developers who want Jev-shaped choices, scores, and confidence values without running OpenJev's patched vLLM backend.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 331
▲3/7d
· Python
jev-visual
Jev Visual is an English-language educational project, with a Simplified Chinese README too, that uses a small vision-language model on Apple Silicon to answer typed questions about an image. It reuses shared visual context and scores candidate answers directly, giving you a local UI, CLI, and HTTP API for learning the technique.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 252
▲3/7d
· TypeScript
jev-review
Jev Review gives coding agents structured quality scores. Consider it for advisory checkpoints inside an agent workflow if you can send selected code context to TypeSafe's remote API. It does not explain why a score is low. Our run on October 5, 2026, at commit 57690af installed and built successfully, but the test command failed before establishing a passing suite. We did not test a live Jev evaluation.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 36k
▲274/7d
· Python
laya
Consider Laya for local typed decisions if you can evaluate its answers on your own labelled data. Laya accepts choice, ordinal-score and yes/no questions and returns structured answers. Our run on October 5, 2026, at commit 8a6e132 established installation and command outcomes, not inference accuracy or production readiness.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 41k
▲1.1k/7d
· Rust
artcraft
ArtCraft offers free creative and productivity apps such as PhotoCraft and FilmCraft, alongside a separate Studio for generative images and video. Launcher installs and updates the Crafting Apps, whose familiar layouts aim to reduce the effort of switching editors.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 436
▲16/7d
· JavaScript
ZeroScript-Free
ZeroScript-Free connects a supported AI chat website to Roblox Studio through a browser extension and a local Python bridge. It lets the chat read or edit scripts, run Luau, inspect a place, and control play tests through Studio's MCP server. You avoid an API key, but the workflow depends on provider webpages that can change without notice.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 2.9k
▲20/7d
· Go
awesome-ai-agents
Awesome AI Agents is a curated directory of public agent projects, frameworks, memory systems, evaluation tools, guardrails, and MCP software. It helps builders find candidates by category while showing repository ownership, submission provenance, maintainership evidence, stars, and recent star growth.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 412 · TypeScript
jev-experiments
Use Jev Experiments to study how Agent Assist separates model judgments from support policy before evaluating the live integration yourself. Agent Assist uses Jev to select handwritten replies. Our run on October 5, 2026, at commit c469e5b checked installation, build and tests in our sandbox. It did not validate live Jev responses, browser interaction, deployment or support-classification accuracy.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 592
▲1/7d
· Python
OrcaBonsai-27B-Uncensored
OrcaBonsai is a runtime add-on that reduces refusal behavior in the separate Ternary Bonsai 2 27B model without rewriting its compressed weights. It is research tooling for Apple Silicon and a particular model pack, not a new model checkpoint or a general chat application.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 2.6k
▲8/7d
· Python
NanoJev
NanoJev is a 0.6B-parameter model that scores supplied choices, Boolean claims, and ordered levels without generating an answer token by token. It packages one checkpoint, training data, an HTTP inference service, and browser replays for four game tasks so researchers can inspect how direct probability-based decisions behave.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 383
▲5/7d
· Python
uplifting-biomolecular-modeling
Uplifting Biomolecular Modeling is a reference collection of 36 optimization kits for protein and genomics model inference. Each kit pins one upstream tool, adds faster or lower-memory execution modes, and documents the exact software, GPU, weights, and patches needed to compare its optimized path with stock behavior.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 545
▲6/7d
· JavaScript
procedural-film
procedural-film is an agent skill for making short animated films or a browser platform game from JavaScript-generated pictures and sound. Its detailed pipeline coordinates research, storyboards, scene-writing subagents, automated visual checks, browser rendering, audio synthesis, and MP4 export.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 703
▲3/7d
· TypeScript
jev-review
Jev Review is a local TypeScript workflow that asks TypeSafe Jev to review a Git branch diff or scan a JavaScript and TypeScript codebase. It screens files first, spends extra model calls on the strongest signals, and saves findings to a local dashboard for human review.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.6k
▲19/7d
·
Dream-RSI
Dream-RSI is a research paper and project page that evaluates a new coding-agent exploration method across 8 tasks. It treats the tree of earlier attempts as a replayable world, then tests new branching and stopping policies against recorded outcomes before using a revised policy online.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 463
▲1/7d
· Python
typesafe-mario
TypeSafe Mario lets the Jev model choose controller moves in the original Super Mario Bros. from structured emulator data instead of screenshots. It turns RAM and telemetry into JSON about Mario, nearby threats, terrain, timing, and recent actions, then records each choice for inspection.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 5.0k
▲17/7d
· Python
SemIf-OpenJev
SemIf, formerly OpenJev, uses an open language model to score a set of choices directly instead of generating an answer and parsing it back into a decision. It is aimed at small runtime judgments such as routing a request or checking whether evidence supports a claim, with local GPU, Apple Silicon, CPU, and browser paths.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.4k
▲1/7d
· Python
jevlike
Jevlike is a small Python model for choosing among a list of text options that can change with each request. It returns one probability per option in a single pass, which suits routing and menu selection when generating a prose answer would be wasteful.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.3k
▲13/7d
· Python
NeuralScreen
NeuralScreen is a Windows desktop overlay that applies NVIDIA neural rendering and optional frame generation to a whole display or one window. It can also capture screenshots, record processed video with sound, convert local media, and publish frames to OBS through Spout2.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 558
▲4/7d
· Python
video-generator-client
Video Generator Client is an async Python wrapper that puts Seedance, Kling, MiniMax/Hailuo, and Wan behind one interface. It includes a CLI, a local FastAPI web screen, and a small MCP server, so one prompt workflow can submit jobs, poll status, and download results across providers.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 228 · Swift
claude-siri-ai
Claude for Siri is an experimental macOS 27 app that puts a signed-in Claude Code account in Spotlight's native Ask menu. A local Swift bridge sends text prompts to the Claude CLI and streams the reply back into Apple's response interface.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 2.0k · Go
ARTEX
ARTEX is a Chinese-language, self-hosted system that lets multiple AI agents plan and carry out penetration-testing work inside an asset and evidence dashboard. Its README and sole file in `docs/` are in Chinese, and the repository has no separate English README or English documentation file. It tracks targets, tool calls, traffic, findings, approvals, and the chain of evidence behind each task.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 13k
▲23/7d
· Python
chandra
Chandra is an OCR model and Python toolkit that turns images and PDFs into Markdown, HTML, or JSON while retaining page layout. It is aimed at documents that ordinary text extraction handles badly, including tables, handwriting, forms, diagrams, and mathematical notation.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 10k
▲68/7d
· Python
production-agentic-rag-course
Production Agentic RAG Course is a seven-week Python course built around an arXiv research assistant. It teaches the whole path from PostgreSQL and keyword search to hybrid retrieval, a local Ollama model, tracing, caching, LangGraph decisions, and a Telegram bot.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 670
▲6/7d
· HTML
GPT-as-Policy
GPT-as-Policy provides evaluation code and a bilingual report comparing direct GPT control with a hybrid policy that reviews π0.5 actions. Use it to inspect the selected comparison or rebuild the report. MrKeyoor's stored run supports the frontend build, not reproduction of the robotics experiment.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.3k
▲13/7d
· Python
NeuralScreen
NeuralScreen is a Windows desktop overlay for NVIDIA neural rendering and optional frame generation over a whole display or one window. The README documents screenshots, processed recording and Spout2 output. Our recorded Debian run checked repository commands at commit e7dd41d, not Windows rendering quality or GPU compatibility.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.8k
▲42/7d
· Kotlin
mural
Mural is a native iPhone and Android language-learning app built around spoken conversations with an AI tutor. It saves transcripts, vocabulary, and learning observations on the phone, then revisits words in later conversations instead of presenting a fixed lesson path.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.1k
▲3/7d
· HTML
recurrent-looped-tranformer
Recurrent Looped Transformer is a research report and project website for an experimental language-model architecture that carries a hidden state from one token to the next. The repository explains the design and publishes papers, figures, and reported results, but it does not contain a runnable training or inference implementation.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 217
▲4/7d
· Python
gpu-time
gpu-time is a local neural parser that turns short English or Spanish time phrases into dates, ranges, and recurrence rules. It runs in JavaScript on CPU or WebGPU, so reminder fields and command bars can interpret a schedule without sending the text to a server.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.2k
▲19/7d
· Python
OpenWAM
OpenWAM is a research stack for training robot policies that learn from video, state, and action data. It gives researchers interchangeable model parts, dataset adapters, training code, deployment tools, and benchmark clients so they can compare world-action model designs without rebuilding the whole pipeline.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 195
▲1/7d
·
xialingguo-ip
xialingguo-ip and all of its documentation are written in Chinese, with no English guide in the repository. It is an instruction pack for asking an image-capable AI assistant to make article covers for a Chinese AI creator, using nine named visual styles and a short intake form.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.2k
▲12/7d
· JavaScript
reelbench-skills
Reelbench Skills is a Chinese-first set of three Claude Code and Codex skills for analyzing video shots, compositing shot notes beside footage, and removing video metadata. English README and per-skill documentation exist, while the main skill instructions and much of the source commentary are Chinese.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 3.7k
▲23/7d
· TypeScript
SoL-Pi
SoL-Pi is an extension for the Pi coding agent that tries to cut repeated tool calls, replayed output, long diagnostic logs, and stale task context. It adds four opt-in mechanisms without patching Pi itself.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 145 ·
flybook
Stonkfly feeds Coinbase price charts into a simulated fruit-fly nervous system, then turns selected neural activity into buy, sell, or hold proposals. It can paper trade or place guarded spot orders, but the project states plainly that profitable learning has not been demonstrated.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 465 · Python
crypto-rag
Crypto RAG is an Indonesian-language command-line assistant for crypto concepts, live market data, alerts, and portfolio tracking; it does not provide English documentation. It keeps explanatory material in a local retrieval index and fetches changing prices, funding, TVL, sentiment, and network data from public APIs when you ask.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 3.3k
▲151/7d
· TypeScript
anything2explainer
anything2explainer is a Claude Code and Codex skill for producing narrated, horizontal motion-graphics explainers in English or Chinese. It supplies a Remotion template plus a nine-stage method for research, narration, speech, storyboarding, shot construction, rendering, subtitles, and visual review.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 183 · Python
cek-probe-model
Cek Probe Model is an Indonesian-language set of Python scripts for checking OpenAI-compatible model endpoints; it does not provide English documentation. It lists available models, sends identity or logic prompts, and prints a summary intended to flag unavailable endpoints or suspicious model labels.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 544
▲10/7d
· Cuda
DeepSelect
Consider DeepSelect when you need specialized TopK kernels for sparse attention or sampling and can validate them on your target hardware. DeepSelect supports NVIDIA CUDA and Huawei Ascend. Our run on October 1, 2026, at commit bfa4507 did not establish a working kernel installation, correctness or runtime performance.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.8k
▲59/7d
· Python
Microduck-build-tutorial
Microduck is a compact biped-robot build whose primary README opens in Chinese and later repeats the guide in English. It combines Raspberry Pi deployment code, printable parts, wiring instructions, a prebuilt SD-card image, and a MuJoCo reinforcement-learning environment for training the included ONNX walking policy.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.2k
▲60/7d
· Rust
Choruz
Choruz is a local-first, Slack-like workspace where people and command-line AI agents share messages, threads, tasks, and files. It runs real Claude Code, Codex, Grok, or plugin-supplied agent sessions in separate workspaces, giving a team one place to assign work and inspect what those agents send back.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 268 ·
haiming-app-monetization
Haiming App Monetization is a Chinese-language agent skill for reviewing mobile onboarding, paywalls, purchase options, and competitor pricing; it has no English documentation. It reads an app project or supplied screenshots and produces a product plan, with code changes allowed only when the user explicitly asks for implementation.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 2.5k
▲56/7d
· Python
lieflat-gongwen
Lieflat Gongwen is a Chinese-language agent skill for drafting seven kinds of Chinese government and Party-affairs material; it has no English documentation. It gives Codex, Claude Code, Moxt, and other agents.md-compatible tools genre-specific writing rules plus a Python checker, while explicitly excluding fixed-format statutory documents.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 34k
▲27/7d
· JavaScript
netron
Netron opens machine-learning model files as interactive graphs, so you can inspect layers, connections, shapes, and stored values without writing a loader for each framework. It runs in a browser, as a desktop app, or from Python, which makes it useful for checking an unfamiliar model before you wire it into an application.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 43k
▲77/7d
· Python
BettaFish
BettaFish is a Chinese-first multi-agent system for collecting online discussion, analyzing sentiment, and producing public-opinion research reports. An English README and contribution guide exist, though the main documentation, issue activity, and bundled report templates are primarily Chinese. It combines web and social collection, private database analysis, several model roles, agent discussion, and HTML, PDF, or Markdown report generation.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 2.7k
▲78/7d
· Python
UniMate
UniMate is an English-language research system that turns a text description into motion for humanoids, animals, and other rigged 3D objects. One model handles different skeleton layouts, then exports motion data and rendered previews that can be applied back to a mesh.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 2.3k
▲2/7d
· JavaScript
unigit-ecosystem
UNIGIT Ecosystem is the public brand, vision, and partner-intake repository for a proprietary AI workbench. It explains what UNIGIT wants to build and screens public contributions, but it does not contain the product runtime or an extension SDK.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 7.6k
▲380/7d
· HTML
handraw-style
Handraw Style is a Chinese-language skill and visual catalog for turning numbered drawing styles, layouts, and colors into image-generation prompts. Full English documentation exists. It helps creators choose a repeatable visual direction without knowing the usual art and composition vocabulary.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 732
▲1/7d
· Kotlin
souchastnik
Souchastnik is a Russian-language Android keyboard that uses a local model to flag possible Russian legal consequences while you type. Its README, interface, and developer notes are in Russian, and we found no English documentation. It also inserts labels for named organizations and people from local dictionaries, without requesting internet access.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 5.2k
▲81/7d
·
dlssg_for_sm86
DLSSG for SM86 is a Chinese-language Windows mod that enables NVIDIA DLSS Frame Generation on RTX 20-series and RTX 30-series cards. A full English README is available. It places a proxy DLL beside a game's executable so supported D3D12 games can expose frame-generation modes normally reserved for newer GPUs.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 87 · HTML
glm-flash-offline-client
GLM Flash Offline Client presents itself as a Windows desktop app for running GLM-5.3-Flash locally. The repository is a documentation and landing-page shell, however: its two named source files are empty, and GitHub has no release containing the client described in the README.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 190 · Python
cyber-resume-reviewer-skill
Cyber Resume Reviewer is an Agent Skill that tells an AI assistant how to critique, tailor, score, or rewrite IT and cybersecurity resumes without inventing evidence. It can produce a Markdown report and a matching PDF, but it is a set of instructions, references, templates, and local helpers rather than a standalone hiring app.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 663
▲16/7d
· JavaScript
RuiC-card-skill
RuiC Card Skill's primary README is Chinese, and the repository also provides a full English README. It gives a multimodal coding agent a recipe and scripts for turning layered artwork into an interactive holographic card website, an editable Blender project, renders, and a browser verification report.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 1.2k
▲9/7d
· Python
itsgiving
It's Giving is a local webcam effect that recognizes 14 facial expressions or poses and places a matching meme over your head. It can publish the altered frame as a virtual camera for Zoom, Google Meet, Teams, Discord, or OBS. A calibrated second script learns your neutral face for seven seconds so fixed thresholds are less likely to misread you.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 277
▲2/7d
· JavaScript
holo-card
Holo Card is a Codex skill that turns supplied artwork into an interactive layered card with tilt, depth, flip, moving background, and contour glow. It guides image generation and repair, then assembles the approved layers into self-contained HTML and a ZIP; an optional local API covers agents without native image tools.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 9 · Python
Awesome-OKF
Awesome-OKF is a 29-entry catalog of tools, plugins, Claude Code skills, proposals, and documentation for Google's Open Knowledge Format. It also supplies a Python CLI, a content converter, and an MCP server so people and agents can search the same YAML catalog. The practical goal is to make agent-readable knowledge projects easier to discover and turn ordinary documents into OKF bundles.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 31k
▲70/7d
· Python
facefusion
FaceFusion is a face-manipulation application with interactive, headless, batch and queued-job commands. Its documented automation options make it worth evaluating for repeatable media work, but our September 30, 2026 sandbox run at commit 7247081 did not establish working media processing or production readiness.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 45k
▲1.2k/7d
· Python
iFixAi
iFixAi is a Python diagnostic that probes whether an AI agent follows the business rules, permissions, evidence standards, and escalation paths defined for it. It produces a scorecard and grade from fixed inspections, while marking checks inconclusive when the adapter cannot expose enough evidence.
Setup
Docs
Community
Maturity
Verdict inside
AI Tools
★ 2.1k
▲229/7d
· JavaScript
dream-loop
Dream Loop is an agent skill that turns a generated target image into a visual specification, then asks a coding agent to keep revising a game, app, or 3D scene toward that image. It solves the vague feedback problem in visual builds by giving the builder a fixed screenshot and, in Pro mode, a separate critic with a scoring rubric.
Setup
Docs
Community
Maturity
Verdict inside