Evaluations

Open-source projects, reviewed the honest way — including who should skip them.

LLM Tools★ 13k · RustironclawIronClaw is a Rust personal AI assistant with a browser interface, messaging channels and persistent memory. It can run scheduled work and connect to tools, including Model Context Protocol servers. Its documented WebAssembly permissions and credential controls are reasons to evaluate it carefully, not security guarantees established by our run.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 424 · RustinfinityHydro Project Infinity is a Rust framework for agents that yield while external tools run and resume when messages arrive. Its repository also includes Reactive Agent Protocol (RAP), with a documented MCP compatibility layer, and Infinity Code, a coding agent built around concurrent work and stacked sandboxes.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 30k · ShellClaude-Code-Game-StudiosClaude Code Game Studios is a template that adds game-development roles, slash commands and project rules to Claude Code. It organizes design decisions and implementation work around a configurable studio workflow for Godot, Unity or Unreal projects. You still choose the direction and supply the game engine and Claude Code environment.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 83k · TypeScriptOmniRouteOmniRoute is a self-hosted AI gateway that gives clients a shared endpoint for connected model providers. It manages provider selection and fallback, and exposes management interfaces including MCP. You bring your own eligible provider accounts and credentials.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 3.8k · PythonharnessrouterHarnessRouter gives applications one API for agent backends such as Codex and Claude Code. It handles the surrounding task lifecycle, including sessions, streamed progress and files, so a product can integrate several harnesses through a shared interface.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 4.1k · TypeScriptpi-subagentspi-subagents is an extension that lets the Pi coding agent delegate work to child sessions. It separates tasks such as code review and codebase scouting, and can run children in the foreground or in a detached background runner.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 8.1k · TypeScriptkimi-codeKimi Code CLI is a terminal coding agent that reads and edits files, runs commands and uses their results to continue a task. It works with Kimi models or other compatible providers, and can connect to editors through the Agent Client Protocol. Its approval settings determine how much work happens without your confirmation.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 24k ▲195/7d · PythonRAG-AnythingRAG-Anything adds document parsing and image, table and equation processing to LightRAG. It is a Python framework for developers building retrieval applications, with separate parser and model choices.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 3.1k ▲529/7d · RustuzuUzu is a Rust inference engine for running AI models inside an application, with Swift, Python, and TypeScript bindings. Its documented workflow covers model downloads and chat sessions. The public FAQ limits device support to Apple Silicon on iOS and macOS, and the README describes a project-specific model format.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 2.9k ▲361/7d · JavaScriptdsh-imDSH-IM connects messaging bots to DeepSeek Harness. It has an English README and an English interface option, with Chinese as the fallback language. Telegram, Slack, and WhatsApp are among its documented channels.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 693 ▲20/7d · RustsmgShepherd Model Gateway, or SMG, routes requests across existing language-model servers and cloud providers. It manages workers and routing policies, including a documented cache-aware policy that considers workers' cached prompt content.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 3.9k ▲313/7d · TypeScriptdsh-contextdsh-context is a DeepSeek Harness plugin that shows what occupies an agent conversation, how it changes between requests, and which sessions consume usage. English and Chinese documentation are available, with dashboards for request content, estimated costs, and agent-family activity.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 14k ▲5.0k/7d · JavaScriptdsh-purgedsh-purge is a Chinese-first plugin for changing local DeepSeek Harness prompts and host policy during controlled security evaluation; a full English README is available. The current branch uses commercial terms, so it should not be treated as an MIT open-source dependency.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 583 ▲120/7d · GoAIStudio2APIAIStudio2API is a Go proxy that translates Google AI Studio's web protocol into OpenAI, Responses, Anthropic and Gemini-compatible APIs. Its documentation describes account import, saved Google login state and a management interface. These are documented capabilities; the supplied sandbox run measured installation, build and test outcomes.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 512 ▲19/7d · PythonGLM-5.3-Flash-EXL3-2x-DGX-Sparks-TensorFoldThis repository is a deployment recipe for serving the GLM-5.3-Flash language model across two NVIDIA DGX Spark systems using a patched TensorFold runtime. It supplies setup scripts, configuration, and operating checks for a local model API, rather than a model that runs on an ordinary development laptop.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 1.6k ▲44/7d · PythonlivenerfLiveNERF repeatedly asks a fixed set of questions to detect changes in a hosted AI model's answers after launch. Its current workflow uses Claude Code and a frozen evaluation protocol, so it measures a particular serving path rather than every use of the underlying model.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 2.1k ▲36/7d · GoscionScion runs teams of AI agents in separate working environments and gives them ways to delegate tasks, exchange messages, and report progress. It lets you coordinate existing coding tools across a laptop or hosted infrastructure while choosing which files and credentials each worker receives.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 1.4k ▲75/7d · Goopencode2apiopencode2api is a Go gateway that adapts OpenCode Zen and Zen Go to familiar chat and messaging APIs. Its original WebUI is Simplified Chinese, with English documentation and interface translations available, while the detailed management guide is Chinese. It handles upstream keys, proxies, and routing behind a local API.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 184 ▲2/7d · IQuest-Q1IQuest-Q1 is a text-only language model for coding agents, reasoning, and tool use. This repository documents the model and how to serve it through a compatible inference engine, rather than supplying a small application you can start on a laptop.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 401 ▲26/7d · PythoniCodeiCode is a terminal coding assistant that connects your chosen models to repository files, shell commands and configurable agents. It gives you diffs, rollback previews and workflow views so you can inspect what the assistant does.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 2.8k ▲47/7d · PythontokenspeedTokenSpeed runs open language models on your own GPU servers and exposes an API that existing chat clients can call. It focuses on the repeated generation requests used by coding agents, with separate scheduling and model-execution components for engineers who need to tune serving behavior.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 352 ▲61/7d · PythonNaive-N0.5-FlashNaive-N0.5-Flash is an open-weight language model for coding and AI research. It uses a mixture-of-experts network and sparse attention to process long inputs, with a small Python repository accompanying much larger model weights.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 36k ▲3.7k/7d · C++StrataStrata runs Qwen3.8-Flash-Next locally by sharing model work across your graphics card, system memory, and processor. It gives you browser chat and local API routes for coding assistants, provided your PC has enough memory for the model.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 1.5k ▲60/7d · PythonAnyJevAnyJev turns a language model into a decision function that chooses among supplied answers and returns probabilities for them. It is useful for jobs such as routing a support request where you need a fixed answer and a confidence signal instead of a paragraph to parse.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 405 ▲16/7d · HTMLMuseAI-SkillsMuseAI-Skills is a partial archive of skill instructions, connector permission files, and Linux runtime material from a Muse/Hatch agent environment. Its primary README is Chinese, and an English README is available. It is useful for studying workflow design, but the archive does not supply a complete deployable assistant.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 34k ▲66/7d · TypeScriptopenclaudeOpenClaude is a terminal coding assistant that connects cloud or local models to file editing, shell commands, and conversation history. It helps you keep one workflow while changing model providers. Its license notice limits the MIT grant to contributor modifications and discloses a lack of authorization to distribute the derived proprietary source.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 3.0k ▲34/7d · TypeScriptagent-skillsSupabase Agent Skills gives coding agents written guidance for Supabase application work and Postgres database changes. Its skill folders contain instructions and SQL references that an agent can load when a task needs them.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 26k ▲4.8k/7d · GomagpieMagpie lets you choose the models used by coding assistants through one local app and gateway. It rewrites each assistant's configuration and routes requests to your API providers, local models, or supported subscriptions, reducing the work of maintaining separate setups.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 610 ▲12/7d · GoM365-Copilot2APIM365-Copilot2API is a self-hosted gateway that lets familiar AI clients send requests through a Microsoft 365 Copilot account using a private Microsoft chat protocol. Its main README is Chinese, with an English translation available. It provides an account and key management console for people who want to operate that relay themselves.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 41k ▲147/7d · C++BitNetBitNet is Microsoft's runtime for running language models trained with very low-precision weights on local hardware. It supplies native inference code and Python helpers for supported models, so developers can explore CPU inference without a hosted model service.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 1.3k ▲82/7d · Pythonhermes-jev-skillsHermes Jev Skills adds model routing and other bounded decisions to an existing AI agent through the Jev cloud service. It helps the agent choose a model, a useful memory passage, or an installed skill while leaving answer writing to the agent's usual model.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 1.0k ▲34/7d · Astroawesome-jevAwesome Jev is an independent catalog of projects that use Jev or implement similar typed decisions, such as choosing an option or judging a statement. It links readers to implementation evidence and includes an Astro website for browsing the catalog, with a separate sponsorship-payment system.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 596 ▲3/7d · Pythonawesome-jevAwesome-jev is a source-attributed catalog of public Jev examples, organized by the decisions an agent needs to make. Its searchable site, MCP server, and Claude Code skill help you find relevant code while preserving caveats about what was read and what remains untested.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 311 ▲1/7d · JavaScriptAstra-AresAstra-Ares adjusts how much a Codex coding model thinks between generations, using Jev to choose the next reasoning effort. It keeps the coding model fixed and provides an experimental patched CLI for developers studying adaptive effort.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 2.2k ▲5/7d · Gounreal-agentUnreal Agent is a Go library for running AI agents, with a command-line runner and a terminal chat interface. It records session history and separates tool requests from asynchronous operations so developers can build their own agent runtime.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 397 ▲1/7d · Pythonagent-jevAgentJev is a local model that scores decisions you describe, such as which tool an agent should use next or how risky an action looks. It returns probabilities over supplied options rather than writing prose. You supply the workflow, candidate actions, and rules for using the result.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 549 ▲10/7d · PythonJevHarnessJevHarness turns a task description into saved code that asks Jev focused questions and uses the answers to choose actions. It lets you inspect and optionally improve that decision strategy instead of asking an authoring model to rethink every action.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 3.4k ▲615/7d · TypeScriptbillion-contextBillion-context is a proxy and plugin system that shortens a coding agent's conversation history into summaries and lets it retrieve earlier details. It helps long coding sessions fit inside the model's context limit, with English and Chinese documentation available.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 597 ▲48/7d · GoCodeAFCodeAF is a coding agent that keeps conversations and delegated tasks for several projects in one terminal interface. It can split work into separate repository copies, track questions, and bring checked changes back to your working branch.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 37k ▲48/7d · JavaScriptone-apiOne API is a self-hosted gateway that lets applications access multiple model providers through an OpenAI-style interface, with shared token and quota management. Its primary documentation is Chinese, and an English README exists but identifies itself as an AI translation.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 952 ▲19/7d · Pythonrizzo-flowRizzo Flow is a local decision server that turns text or JSON state into booleans, choices, scores, and numeric estimates with probabilities. It reads the model's next-token scores instead of generating prose, which removes JSON repair from the path but does not make the decisions automatically correct or calibrated.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 11k ▲274/7d · Pythongpt-instructgpt-instruct is a Chinese-first project, with a full English README, that packages custom Codex instructions and the evaluation machinery used to compare them. It tries to make Codex act on complex requests earlier, preserve work across turns, verify artifacts, and keep a runnable rollback.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 413 ▲3/7d · Pythonminorun-marp-skillminorun-marp-skill is a Japanese-language set of Claude Code skills for planning, drawing, and checking Marp presentation decks. Its README and skill documentation are in Japanese, and the repository includes no English guide. It pairs a dark Marp theme with scripts that inspect exported PDFs, SVGs, reused slides, and repetitive AI-style writing.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 663 ▲14/7d · Pythonjev-skillJev Skill is an English-first, Chinese-translated collection of coding-agent skills for classification, scoring, evidence review, and choosing among bounded actions with Jev. It gives Codex, Claude Code, and OpenCode reusable instructions and JSON templates while leaving evidence gathering and execution to the host agent.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 166 ▲1/7d · TypeScriptjev-prunerjev-pruner is a Claude Code plugin that asks TypeSafe Jev which parts of very long Bash output still matter, then gives Claude the retained lines and archives the original locally. It also has a Codex plugin and skill, but Codex commands must be run through its wrapper because native post-tool hooks cannot replace shell output.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 437 ▲6/7d · Gollm-d-routerllm-d Router decides which Kubernetes model-serving pod should receive each inference request. It can route by model, current load, reusable prompt cache, and priority, while also coordinating split prefill and decode workers through Envoy or the Kubernetes Gateway API.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 4.1k ▲42/7d · PythonRapid-MLXRapid-MLX is a local inference server for running language and media models on Apple Silicon, with OpenAI-compatible and Anthropic-compatible APIs. It is aimed especially at coding agents, adding tool-call parsers, prompt caching, continuous batching, model recommendations, and one-command client setup around Apple's MLX stack.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 628 ▲12/7d · Pythonsimple-jevSimple Jev turns compatible open language and vision models into a local typed-decision API without requiring a separate classifier head. It reuses shared context, scores allowed answer labels from model logits, and returns choices, rubric scores, or truth judgments as JSON instead of generating prose.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 9.7k ▲200/7d · PythonkevKev is a family of self-hosted decision models that read a document, answer yes-or-no, multiple-choice, or rating questions, and return probabilities instead of generated prose. Its server matches TypeSafe's System One API, so an application can move Jev-style classification and routing onto its own hardware.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 333 · Pythonopenjev-sglangopenjev-sglang is a small Python server that copies the Jev decision API on top of Qwen3.6-35B-A3B and SGLang. It scores yes/no, choice, and ordered-score questions by reading first-token probabilities, but its own README now directs new users to SGLang's native decisions endpoint.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 2.3k ▲17/7d · PythonOptMemOptMem is a single-file Python memory log for coding agents. The agent appends short notes, reads a bounded set at startup, and helps compress older notes into a binary tree of summaries. It keeps the raw log on your machine and relies on instructions in AGENTS.md or CLAUDE.md rather than an SDK integration.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 4.9k ▲26/7d · PythonSemIf-OpenJevSemIf, formerly OpenJev, turns a piece of text and a set of named options into probabilities from an open language model. It is meant for small software decisions such as routing or retrying, where generating a prose answer and parsing it back into a branch would be wasteful.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 612 ▲6/7d · HTMLawesome-typesafe-jevAwesome Jev is an independent field guide to TypeSafe's Jev decision model and the projects built around it. The old `awesome-typesafe` address now redirects to `awesome-typesafe-jev`, where a long README, searchable Pages site, JSON directory, code examples, and independent evaluations explain the ecosystem.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 7.8k ▲46/7d · TypeScriptfast-jev-compactionfast-jev-compaction is a TypeScript library and early-access Claude Code plugin that prunes old tool calls and results instead of replacing a session with a prose summary. It asks the hosted Jev decision service what to keep, preserves user and assistant text, and falls back to Claude Code's built-in summary when the hook fails or saves too little.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 14k ▲1.2k/7d · PythonexperientialExperiential is an OpenAI-compatible gateway that routes agent traffic across hosted, bring-your-own-key, and local models. It adds identities, spending limits, provider policies, trace capture, evaluations, and tools for fitting a custom router or model from your own traffic.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 1.5k ▲110/7d · llm-masterLLM-Master is a Chinese-language learning library for programmers moving into large-language-model application work; it does not provide an English documentation track. Its 153-item index covers model APIs, RAG, agents, MCP, fine-tuning, deployment, Transformer internals, AI coding, projects, and interviews.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 5.5k ▲35/7d · TypeScriptobsidian-mindObsidian Mind is an Obsidian vault template that gives Claude Code, Codex CLI, and Gemini CLI a persistent record of projects, decisions, people, and work history. Its hooks and MCP server help agents retrieve and file Markdown notes across sessions instead of rebuilding context from chat history.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 280 ▲1/7d · PythonDeepSeek-v4.1-Flash-EXL3-2x-DGX-SparksThis repository is a deployment kit for serving an EXL3-quantized DeepSeek v4.1 Flash model across two NVIDIA DGX Spark GB10 systems. It wraps custom kernels, split model storage, vLLM, and an OpenAI-compatible API into one highly specific two-node recipe.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 6.8k ▲53/7d · Gowhatsapp-mcpWhatsApp MCP connects Claude Desktop or Cursor to a personal WhatsApp account so the agent can search chats, read messages, download media, and send text or files. A Go bridge handles WhatsApp and local SQLite storage, while a Python MCP server exposes the tools to the model.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 2.7k ▲194/7d · Rustdeepseek-recipeDeepSeek Recipe is a set of Rust libraries and Python bindings that converts Messages, Chat Completions, and Responses requests into a shared conversation form, renders DeepSeek V4 or V4.1 prompts, and converts backend output back into the requested API format. It supplies the translation layer around a model; inference, HTTP transport, and tool execution remain your application's job.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 8.8k ▲1.7k/7d · PythonEdge0Edge0 is a local inference project for sparse mixture-of-experts language models, using SSD-streamed expert weights, trained routing prediction, and LoRA adapters to reduce active memory. The repository now contains separate Python, macOS, iOS, Android, and Windows engines, but they do not yet share the unified interface described in its roadmap.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 17k ▲125/7d · TypeScriptag-uiAG-UI is an event protocol for connecting an AI agent to the interface a person is using. It standardizes streamed messages, shared state, tool calls, and approvals so a frontend does not need a custom event format for every agent framework.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 1.5k ▲52/7d · Pythonawesome-codex-pluginsAwesome Codex Plugins is a curated Git repository and installable marketplace with 249 mirrored community plugin bundles, plus links to official Codex plugins. It helps Codex users browse and install skills, MCP integrations, and workflow packages from one source instead of cloning each publisher's repository separately.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 157 ▲4/7d · claude-style-patchClaude Style Patch is a prose rulebook meant to be appended to `CLAUDE.md` or pasted into Claude custom instructions. It targets dense sentences, announced points, vague antecedents, stock endings, and other habits that make generated writing harder to read.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 3.4k ▲82/7d · Pythonagent-toolkit-for-awsAgent Toolkit for AWS gives coding agents AWS instructions, plugins, and a managed Model Context Protocol server. It helps Claude Code, Codex, Cursor, Kiro, fx, and other clients choose services, inspect documentation, call AWS APIs, and carry out cloud work under your AWS permissions.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 4.4k · Pythonagent-memoryAgent Memory gives Claude Code, Codex CLI, and other shell-capable agents a shared long-term memory store. Memories stay as readable Markdown files, while a disposable SQLite index handles local search and optional vector retrieval.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 1.7k ▲5/7d · Pythoncodex-astra-luna-orchestratorCodex Astra Luna Orchestrator packages project configuration, custom agent roles, and an orchestration skill for Codex. Its six profiles assign a root agent, Luna execution roles, and a separate reviewer. It is a configuration bundle for an existing Codex installation; our recorded setup steps do not establish that Codex itself was installed or that a delegated coding task worked.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 846 ▲9/7d · Gookf-agent-memoryOKF Agent Memory stores project decisions, constraints, and runbooks as Markdown and YAML inside Git, then gives AI agents a CLI and MCP server to search and update them. It is curated project memory rather than automatic conversation recall, which makes every remembered fact reviewable in a pull request.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 23k ▲12/7d · Pythonmlc-llmMLC LLM compiles and runs language models across NVIDIA, AMD, Intel, and Apple GPUs, plus browsers and mobile devices. It gives those targets a shared inference engine with OpenAI-compatible access through a local server and platform-specific APIs, reducing the need to build a separate runtime for each device class.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 53k ▲103/7d · awesome-openclaw-skillsAwesome OpenClaw Skills is an English-language Markdown directory of community skills published on ClawHub. It sorts thousands of links into task categories so an OpenClaw user can find a candidate skill without searching the full registry.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 1.5k ▲64/7d · PythonTensorFoldTensorFold is a local language-model server for a small set of large models on Apple Silicon and NVIDIA GPUs. It exposes OpenAI-style chat and completion routes while using model-specific kernels and speculative decoding to produce the same tokens as its own serial path.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 95 · JavaScriptai-evaluation-frameworkAI Evaluation Framework is a small Node.js harness for comparing model outputs against field-level ground truth. It reports accuracy, request latency percentiles, and estimated token cost, then collects user complaints as candidates for future test cases.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 2.2k ▲9/7d · TypeScriptllm-wiki-compilerllmwiki turns source files and web pages into a local Markdown wiki whose pages retain citations, links, review state, and freshness information. It solves a specific problem for teams that keep asking an LLM to rediscover the same knowledge from raw documents.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 29k ▲314/7d · Pythonclaude-skillsclaude-skills is a large library of reusable instructions, scripts, agents, commands, and plug-ins for Claude Code and other coding assistants. It packages specialist workflows for engineering, product, marketing, research, compliance, finance, operations, and executive advice so users can install a domain instead of writing every instruction from scratch.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 22k ▲688/7d · PythonHumanizer-zhHumanizer-zh is a Chinese-language Claude Code skill for editing stiff, repetitive, or templated Chinese prose without changing its facts or level of certainty. Its README and skill instructions are written in Chinese, and the repository does not provide an English documentation file.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 3.0k ▲154/7d · Goagent-beaconBeacon records coding-agent sessions from Claude Code, Cursor, Codex, OpenCode, and other harnesses in one local event format. It lets you inspect what agents did, forward those records to security tools, and turn reviewed lessons into project memory that other agents can retrieve.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 14k ▲15/7d · TypeScriptMiMo-CodeMiMoCode is a terminal coding agent that can edit files, run commands, use Git, call MCP servers, and remember project decisions between sessions. Xiaomi built it from OpenCode and added checkpointed memory, subagents, goal judging, repeatable workflows, and a large set of built-in skills.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 739 ▲20/7d · JavaScriptpi-claude-bridgepi-claude-bridge is a Pi extension that lets Claude Code act as a model provider inside Pi, with tool calls displayed in Pi's terminal interface. It can also add an AskClaude tool so another provider can hand a question or coding task to Claude Code.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 6.7k ▲634/7d · PythontregTreg is a registry and credential-injecting proxy for agent tools, with more than 3,000 catalogued endpoints across over 60 providers. An agent gets one Treg token, while provider keys stay on the server and teams can mix Treg-funded calls with their own accounts, CLIs, skills, and MCP clients.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 13k ▲536/7d · Pythontrain-llm-from-scratchTrain LLM From Scratch is an educational PyTorch repository for following a language model from pretraining through supervised fine-tuning, reward modeling, DPO, PPO and GRPO. The current README documents both a classic Transformer and a modern architecture, plus a laptop CPU track with its own BPE tokenizer. Our recorded execution covers an older commit, not those newer additions.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 7.8k ▲14/7d · Rustmistral.rsmistral.rs runs language, vision, audio, image-generation, and embedding models on your own hardware. It gives you a command-line chat tool, a local web interface, OpenAI- and Anthropic-shaped APIs, plus Rust and Python libraries around the same engine.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 8.6k ▲36/7d · TypeScriptflueFlue is a TypeScript framework for defining AI agents as functions with an explicit model, tools, skills, instructions, and working environment. It adds persistent conversations, failure recovery, subagents, MCP connections, telemetry, and deployment targets for Node.js and Cloudflare.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 15k ▲34/7d · PythonTensorRT-LLMTensorRT-LLM is NVIDIA's open-source runtime and Python toolkit for serving language and visual-generation models on NVIDIA GPUs. It handles model loading, GPU-specific optimization, and request scheduling, with both an OpenAI-compatible server and an in-process Python API.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 21k ▲97/7d · Pythonpydantic-aiPydantic AI is a Python library for building agents that call models and tools while checking inputs and outputs with Pydantic types. It gives one agent definition several front ends, including ordinary Python calls, a CLI, web chat, realtime voice, and durable job runners.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 15k ▲73/7d · TypeScriptcc-hahaClaude Code Haha is a desktop workspace that puts Claude Code sessions, Git worktrees, diffs, browser previews, permissions, MCP servers, and subagents into one interface. It also connects other model providers and messaging services, aiming to replace the loose collection of terminals and dashboards around an autonomous coding setup.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 19k ▲40/7d · Pythonagent-lightningAgent Lightning is a Python framework for improving an existing AI agent through reinforcement learning while the agent keeps using its real tools and control flow. It places a model gateway between the agent and trainer, records what happened, assigns rewards, and turns those interactions into training data.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 9.0k ▲59/7d · Pythonharness-sdkStrands Agents is an in-process SDK for building AI agents in Python or TypeScript. It supplies the loop around a model: tools, limits, sessions, memory, streaming, MCP, provider adapters, traces, and multi-agent patterns. Teams use it when a hand-built tool-calling loop has started to need production controls.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 2.4k ▲9/7d · JavaScript12306-mcp12306-mcp is a Chinese-first MCP server for searching China's 12306 rail service. Its README has an English summary and setup commands, while the detailed operating notes are in Chinese. It gives an AI client tools for dates, station codes, direct tickets, transfers, and route stops.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 6.3k ▲16/7d · PythonouroborosOuroboros is a local Python workflow layer for AI coding agents. It interviews you about a task, writes the answers into a fixed specification called a Seed, hands work to an existing coding runtime, records what happened, and checks the result through staged evaluation. English is the primary README, with Korean and Simplified Chinese versions also available.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 2.5k ▲442/7d · MarkdownheadcountHeadcount is a Claude Code plugin marketplace that packages 172 operating playbooks as 16 company departments, covering work such as engineering, finance, security, hiring, and marketing. Each skill is a set of instructions Claude loads when a matching request appears. It solves the problem of maintaining one oversized prompt by letting you install only the departments your work needs.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 379 ▲13/7d · TypeScriptuseagentuseAgent gives a team one web workspace for Claude Code, Codex, OpenCode, and Pi. Each task gets an isolated computer with repositories, a terminal, and a browser, while the control plane keeps the conversation, files, approvals, team knowledge, and integration credentials outside that worker.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 12k ▲84/7d · Pythonclaude-skillsClaude Skills is a Claude Code plugin containing 67 specialist instruction sets for software work, plus nine commands for running projects through Jira and Confluence. It gives the coding agent reusable methods and reference material for particular languages, frameworks, security reviews, testing, and operations.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 30k ▲147/7d · Jupyter NotebookRAG_TechniquesRAG_Techniques is an English-language collection of 42 Jupyter notebooks that teach ways to retrieve better context for language-model answers. It helps you compare methods such as chunking, reranking, Graph RAG, and evaluation before choosing what to build. It is a teaching library rather than an installable RAG product.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 3.1k ▲56/7d · JavaScriptux-ui-agent-skillsUX/UI Agent Skills is a reusable instruction and knowledge kit that gives Claude structured guidance for design systems, accessibility, component design, and interface code. It solves the consistency problem teams hit when an AI assistant produces attractive but disconnected screens without shared tokens, states, or quality gates.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 5.3k ▲52/7d · TypeScriptdictionary-of-ai-codingDictionary of AI Coding is an English-language glossary for the terms developers meet while working with coding agents. It explains models, tokens, context, tools, failure modes, handoffs, memory, review, and agent-friendly development in plain language with usage examples.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 4.4k ▲22/7d · Pythongemini-skillsGemini Skills is a set of instruction files and helper scripts that teaches coding agents how to use current Gemini APIs and SDKs. It covers ordinary API work, live audio and video sessions, and Gemini Omni video generation so an agent is less likely to produce code from outdated model knowledge.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 1.8k ▲54/7d · JavaScriptreversaReversa installs a collection of coding-agent skills into an existing project, then guides an agent through extracting business rules, architecture, data relationships, and gaps from the code. It is meant for teams that inherited a system without dependable specifications and want traceable working documents before they change or rebuild it.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 9.9k ▲866/7d · PythonClaude-RedClaude-Red is a library of ready-made instruction files that guide Claude through authorized offensive-security work. It gives operators structured methods for 78 topics, so they do not have to rebuild a testing checklist for every engagement.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 34k ▲1.1k/7d · Pythonknowledge-work-pluginsKnowledge Work Plugins is Anthropic's collection of 11 role-based plugin packs for Claude Cowork and Claude Code. Each pack combines instructions, slash commands, sub-agents, and MCP connectors so Claude can follow a repeatable workflow for jobs such as sales, finance, support, data analysis, or bio-research.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 27k ▲44/7d · C++llamafilellamafile packs a large language model and its runtime into a single executable file that runs on Windows, macOS, Linux, and BSD without installation. It also includes whisperfile, a single-file speech-to-text tool built on whisper.cpp. The goal is to make open LLMs easy to distribute and run locally.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 1.3k · JavaScriptOpenContextOpenContext keeps project notes and decisions in a local library so coding assistants can reuse them across sessions and repositories. Its command-line tool, desktop interface, and Model Context Protocol server let Cursor, Claude Code, and Codex find or update that material without replacing the coding agent you already use.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 4.2k ▲92/7d · PythonhyperresearchHyperresearch is a Python package that turns Claude Code into a multi-stage research runner and keeps gathered sources in a reusable Markdown vault. It searches, drafts, criticizes, checks citations, and resumes interrupted work instead of treating each report as a disposable chat.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 40k ▲775/7d · TypeScriptprompt-optimizerPrompt Optimizer is an application for rewriting system and user prompts, comparing results and saving reusable prompts with examples. English documentation is available alongside a Chinese README. It gives repeated prompt editing a workspace across web, desktop and extension interfaces, with an MCP service for compatible clients.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 2.3k ▲31/7d · Goagent-routerAgent Router, formerly Envoy AI Gateway, puts a common API in front of hosted AI models, self-hosted inference and Model Context Protocol servers. Platform teams use it to keep provider credentials, routing rules and quotas in one place while Envoy carries the traffic.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 3.5k ▲48/7d · TypeScriptllm-for-zoterollm-for-zotero puts an AI assistant inside Zotero for asking questions about papers, comparing sources, inspecting figures, and saving research notes. Its optional agent can also search and change a library, while MCP, Codex, Claude Code, WebChat, and local model connections let users choose where the model runs.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 2.5k ▲52/7d · RustwebcodexWebCodex is an open-source Rust tool that gives AI assistants like ChatGPT and Claude a local, permission-bounded development environment on your own machine. It solves the problem of moving a repository into a hosted AI workspace by keeping code, Git, tests, and developer tools where they already live, connected over MCP or HTTPS.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 29k ▲29/7d · C#semantic-kernelSemantic Kernel is Microsoft's software kit for connecting applications to language models and organizing assistants, tools, memory, and multi-agent workflows. It supports Python, .NET, and Java, but Microsoft now identifies Microsoft Agent Framework 1.0 as its production-ready successor, so new adopters must weigh current capability against a future migration.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 16k ▲88/7d · Gocc-connectCC-Connect is a Go bridge between local AI coding agents and messaging platforms. Its README lists agents including Claude Code, Codex, Cursor Agent, Gemini CLI and Kimi CLI, alongside chat services such as Slack, Discord, Telegram, Feishu/Lark, DingTalk and WeCom. These are documented capabilities, not integrations verified in our sandbox run.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 13k ▲160/7d · Pythonno-ai-slopNo AI Slop is an English-language editing skill for ChatGPT, Claude Code, Codex, and other coding agents. It asks the agent to remove more than 20 recurring writing habits while preserving the writer's wording and voice, and it has a separate mode that flags patterns without claiming to detect AI authorship.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 26k ▲215/7d · TypeScriptdistillyDistilly turns selected writing, transcripts, public pages, and working material into a versioned profile of how a person thinks and communicates. An agent can load that profile for one run or install an approved copy as a lasting local Skill, with the source material and history kept on the user's machine.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 67k ▲24/7d · Pythongpt4freeGPT4Free, also called g4f, puts hosted AI providers and local model backends behind Python clients, a web interface and an OpenAI-compatible API. It helps developers try different text and media services through common interfaces, although each provider keeps its own login requirements and behavior.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 30k ▲124/7d · Pythonopenai-agents-pythonThe OpenAI Agents SDK is a Python library for applications in which a language model calls tools or passes work to another agent. It supplies the execution loop, conversation history and approval mechanisms so you can spend less code connecting those pieces.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 55k ▲9/7d · RustChatGPTlencx/ChatGPT is an unofficial desktop application for using ChatGPT on Mac, Windows, and Linux. Its older release adds shortcuts, reusable prompts, and conversation export, while the current README directs new users toward the successor, Noi.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 4.1k ▲25/7d · TypeScriptnotfair-pluginNotFair Plugin is a collection of 45 open-source marketing procedures for Claude Code, Codex, Cursor, Gemini CLI, and compatible agents. It gives an agent detailed instructions for SEO, analytics, and paid-media work, while a hosted MCP connection supplies live account data and approved write actions.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 3.1k ▲90/7d · Pythonfreecad-mcpFreeCAD MCP lets an AI client such as Claude Desktop create and inspect models inside the FreeCAD desktop app. A Python server translates the client's requests into FreeCAD operations, so the model can add parts, edit properties, take views, and run scripts without the user clicking through every command.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 5.1k ▲31/7d · TypeScriptchat-on-steroidsChat On Steroids is an Electron desktop app and local MCP server that lets ChatGPT read files, patch code, run shell commands, retain transcripts, and coordinate worker chats on your computer. It closes the gap between a browser conversation and local development tools, with approved folders and per-capability switches defining what ChatGPT may do.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 629 ▲5/7d · Pythonmy-free-codeMy Free Code presents itself as a local Python gateway that lets Claude Code and other coding agents send requests through different hosted or local model providers. Commit 3fea11e also wires the documented start command to an unexplained Windows-only loader that downloads Python over plain HTTP and executes it in memory, so the checked-out project is unsafe to run.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 54k ▲204/7d · Jupyter Notebookclaude-cookbooksClaude Cookbooks is Anthropic's collection of code examples and guides for building with the Claude API. Its mostly Python recipes show how to connect tasks such as tool use and document retrieval to your own application.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 1.3k ▲11/7d · GoagentdockAgentDock connects AI assistants to computers and servers so they can edit files, run commands, and work across machines through MCP. It has an English README, while the compatibility release notice is in Chinese.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 339 ▲5/7d · Rustagentic-apiAgentic API is a Rust gateway that adds conversation state, tool loops, and OpenAI Responses or Anthropic Messages protocol handling in front of vLLM. It lets Codex, Claude Code, SDKs, and custom clients use self-hosted models without making every client manage history and server-side tools itself.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 583 ▲3/7d · RustfunesFunes turns past Claude Code, Codex, pi, and Hermes sessions into a searchable local memory that an AI coding agent can query later. It solves the familiar problem of decisions, dead ends, and useful findings disappearing when a session closes, while optionally sharing that history through a Hugging Face dataset.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 7.6k ▲69/7d · TypeScriptcodex-with-chatgptCodex with ChatGPT is an unofficial TypeScript bridge that lets the ChatGPT web app read selected files and Git state while Codex keeps control of edits and commands. It targets people who want ChatGPT to plan and review coding work without sending a whole repository or using an API key. The README opens in Chinese and English, then provides detailed English instructions and links a full Simplified Chinese guide.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 28k ▲114/7d · PythonskillsOpenAI Skills is an English-language catalog of instruction folders, scripts, and reference material that Codex can load for repeatable tasks. Its README now marks the repository deprecated and directs new authors to OpenAI Plugins and the current Codex skill documentation.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 5.4k ▲17/7d · GoaxonhubAxonHub is a self-hosted AI gateway. Its README describes routing supported OpenAI, Anthropic and Gemini API requests across providers, with tracing, role-based access control, quotas, load balancing and cost tracking. These are documented capabilities, not results established by our sandbox run. The primary README is Chinese and links to English and Japanese versions.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 31k ▲77/7d · TypeScriptsupermemorySupermemory is a memory service that extracts facts from conversations and retrieves them alongside documents for AI applications. It provides user profiles, an API and integrations for assistants, including an MCP endpoint and Claude Code plugins. Its local server is distributed as a binary whose source, according to the self-hosting docs, is outside the public repository.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 37k ▲510/7d · Pythonbook-to-skillbook-to-skill turns books and document folders into reusable notes that a coding agent can consult while you work. It extracts text locally, then gives your agent instructions for writing chapter files, a glossary and practical reference material. Use it when the same source keeps coming up and searching the original interrupts the job.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 4.7k ▲8/7d · TypeScriptOB1Open Brain is a personal memory backend that lets several AI clients save and retrieve the same information. It combines a Supabase database, semantic search, an MCP server, and optional recipes so your notes are no longer trapped inside one assistant.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 76k ▲71/7d · PythonLlamaFactoryLlamaFactory lets you fine-tune open language and multimodal models through a command line or browser interface. It puts dataset configuration, training methods, and model export in one project so you can run experiments without writing each trainer yourself.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 24k ▲64/7d · Pythonverlverl is a Python framework for reinforcing and fine-tuning large language models after their initial training. It coordinates training backends, rollout engines, rewards, model placement, and distributed workers so research teams can run PPO, GRPO, and related methods on their own GPU infrastructure.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 1.8k ▲21/7d · Rustskills-hubSkills Hub is a desktop manager for Agent Skills used by Claude Code, Codex, Cursor, and dozens of other coding assistants. It keeps one central copy of each skill, then links or copies it into global and project folders so users can install, tag, update, enable, and remove skills from one interface.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 5.6k ▲112/7d · TypeScriptaidlc-workflowsAI-DLC Workflows is an AWS Labs framework that makes coding agents follow a recorded software-development process instead of jumping straight from a prompt to code. One shared TypeScript engine supplies staged planning, specialist agents, human approvals, audit records, and resumable state to 7 supported coding assistants.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 20k ▲97/7d · Pythonnotebooklm-pynotebooklm-py is an unofficial Python client for Google's NotebookLM, now branded Gemini Notebook. It lets applications, shell scripts, MCP clients, and coding agents create notebooks, add sources, ask cited questions, generate media or study material, and download the results.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 17k ▲84/7d · TypeScripta2uiA2UI is a protocol and set of renderer libraries for letting an AI agent describe an interactive interface as JSON. The client maps that description onto a catalog of approved components, which gives remote agents forms, cards, and other UI without executing code they generated.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 19k ▲26/7d · TypeScriptweb-llmWebLLM runs supported language models inside a web browser with WebGPU, so prompts and generated text can stay on the user's device after model assets arrive. Its TypeScript API resembles OpenAI chat completions and includes streaming, JSON output, workers, browser caching, and custom MLC model support. It solves the server-cost and data-routing problem for web apps whose users have suitable hardware.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 85k ▲882/7d · Pythonhello-agentsHello-Agents is a Chinese-first course on building language-model agents, with an English README and English chapters. It teaches Python developers how agents choose tools, keep context, and work through larger tasks, with code to inspect and modify.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 11k ▲133/7d · Pythongeo-seo-claudeGEO-SEO Claude Code is a Claude Code skill that audits websites for visibility in AI answers while also checking familiar SEO basics. It turns page fetching, crawler rules, schema checks, content scoring, and report generation into slash commands for people who already work inside Claude Code.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 7.7k ▲154/7d · RustOpenResearchOpenResearch is a local workspace for sending coding agents through literature review, hypothesis development, experiments, and research writing. It solves the messy coordination problem around parallel agent sessions by keeping their code, evidence, runs, and outputs together on your machine.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 9.0k ▲58/7d · RustrigRig is a Rust library for adding language models, tools, memory, and retrieval to an application without writing a separate client for every provider. It supplies shared interfaces and an agent runtime, while leaving the surrounding product, deployment, and model accounts to you.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 4.7k ▲56/7d · TypeScriptopen-knowledgeOpenKnowledge is a desktop and local web editor that makes Markdown and MDX folders feel closer to Notion while keeping files in an ordinary project directory. It adds graph navigation, Git/GitHub sync, search, and side-by-side work with Claude, Codex, and other agents through MCP, CLI, and skills.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 32k ▲164/7d · PythongraphitiGraphiti is a Python framework for building and querying temporal context graphs for AI agents. It tracks changing facts and their source episodes. Your application supplies the graph database, model services and surrounding service.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 1.7k ▲89/7d · Pythoncve-mcp-serverCVE MCP Server gives an MCP-compatible assistant tools for looking up vulnerabilities, exploitation signals, threat data, and package risk. Its main job is to collect evidence from several security services so an analyst can triage a CVE without opening each service by hand.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 65k ▲256/7d · PythonminimindMiniMind is a Chinese-first project with a full English README that teaches you to train a small language model from scratch. It exposes the model and training code so you can follow how data becomes a model, then try instruction tuning and tool use.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 35k ▲195/7d · JavaScriptSillyTavernSillyTavern is a locally installed interface for language models, image generators and text-to-speech services. Its README lists lorebooks and extensive prompt controls. A separate model backend supplies the replies.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 405 ▲4/7d · PythonHy4-previewHy4 preview is Tencent's open-weight mixture-of-experts language model for coding, analysis, tool use, and long-context work. The repository mainly supplies deployment directions and three fine-tuning paths for a 770B-parameter model, with English and Chinese documentation.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 156k ▲154/7d · PythonlangflowLangflow lets you connect AI models and tools on a visual canvas, then run the resulting workflow from your application or an AI assistant. You can change components in Python when the supplied blocks don't do what you need. It suits developers who want to inspect and share a workflow without writing every connection by hand.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 69k ▲74/7d · RustopeninterpreterOpen Interpreter is a Rust coding agent that lets language models edit files and run commands from your terminal. It supports different providers and agent behaviors in one interface, with editor connections and configurable permissions. The original Python project now lives in a separate community-maintained fork.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 21k ▲233/7d · TypeScriptllm_wikiLLM Wiki is a desktop app that turns imported documents into a linked, searchable wiki maintained with language models. It keeps the source files, generated pages, citations, graph, and chat history on your machine, while letting you choose local or hosted model providers.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 13k ▲331/7d · Pythonpatent-disclosure-skillPatent Disclosure Skill is a Chinese-language Claude Code and Cursor skill for drafting Chinese patent disclosure documents, reading published patents, watching policy changes, and assisting with office-action replies. The primary README, installation guide, and workflow instructions are in Chinese; there is a short English description in the skill metadata, but no full English documentation path.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 4.9k ▲737/7d · Pythonoh-my-hermesoh-my-hermes, or OMH, is an operating layer for NousResearch's Hermes Agent. It installs skills, workflow routing, model preferences, local memory contracts, a terminal display, and guarded handoffs to coding tools such as Claude Code and Codex while trying to distinguish prepared work from observed results.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 37k ▲740/7d · PythonhereticHeretic modifies language-model weights to reduce safety refusals, using an automatic search to choose how strongly to intervene. It helps researchers repeat a model-editing experiment without selecting every setting by hand, while leaving the quality of the resulting answers to separate evaluation.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 5.6k ▲9/7d · GorouterWeave Router is a source-available Go proxy that chooses a model for each request from a coding agent or application. It accepts Anthropic, OpenAI, and Gemini request formats, scores the action locally, and sends it to an enabled provider behind one endpoint.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 6.0k ▲26/7d · Pythonflash-linear-attentionFlash Linear Attention is a Python library of GPU-oriented kernels, layers, and model definitions for linear attention, sparse attention, state-space models, and hybrid language models. It gives researchers a shared implementation base for trying newer sequence architectures without writing every Triton kernel and backward pass themselves.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 4.6k ▲15/7d · Godocker-agentDocker Agent is a Go runtime and Docker CLI plugin for defining AI agents in YAML, giving them tools, and letting them delegate work to other agents. It connects to cloud or local models, accepts MCP tools, can index documents for retrieval, and packages agent configurations in OCI registries.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 16k ▲10/7d · Pythonaisuiteaisuite is a Python library that gives several hosted and local language-model providers one OpenAI-shaped chat interface. It also has an agent runner, tool policies, persistent state, streaming, and MCP connections for developers who want one application to switch among providers.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 13k ▲58/7d · GoeinoEino is a Go framework for applications that call language models and tools. You can wire operations into a fixed sequence or let an agent choose which tools to call, including tools built from those sequences.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 1.1k ▲18/7d · JavaScriptatlassian-mcp-serverAtlassian Rovo MCP Server is Atlassian's cloud-hosted bridge between AI clients and Jira, Confluence, Jira Service Management, Bitbucket Cloud, and Compass. It lets an agent search, read, create, and update work using the user's existing Atlassian permissions; this repository mainly packages connection manifests and reusable skills for the hosted service.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 27k ▲232/7d · TypeScriptpromptfooPromptfoo is a CLI and library for evaluating and red-teaming LLM applications. Its README describes automated prompt tests, comparisons across providers including Ollama, CI checks, and shared results. Our recorded source-checkout run measures dependency setup, build and test commands, and audit output. It does not establish whether the published CLI works or how well Promptfoo evaluates an application.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 34k ▲56/7d · TypeScriptoh-my-codexOh-my-codex adds reusable coding workflows, saved plans, and task state around OpenAI Codex CLI. It helps you carry a coding job across sessions and coordinate workers when the work needs parallel edits, while Codex still performs the code changes.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 568 ▲4/7d · God-inferenceDarkbloom is a public-alpha network that routes OpenAI- and Anthropic-compatible inference requests to Apple Silicon Macs owned by independent providers. It encrypts traffic between a coordinator and attested provider processes, while the coordinator still handles plaintext transiently inside confidential-VM memory for routing and billing.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 5.8k ▲219/7d · RustagentgatewayAgentgateway is an open source proxy for agent-to-LLM, MCP tool, and A2A traffic. Its README describes model routing, authentication, policy, guardrails, budget controls, and OpenTelemetry support, with standalone YAML and Kubernetes controller deployment paths. Those documented capabilities were not all exercised in our recorded run.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 1.8k ▲18/7d · TypeScriptopencode-memOpenCode Memory is an OpenCode plugin for retaining project context and user preferences across sessions. Its README documents local embedded Turso storage with exact cosine vector search, manual memory tools, automatic capture, and a browser interface. Local storage does not mean every operation stays local: automatic capture and profile learning require a configured AI provider.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 33k ▲186/7d · PythoncogneeCognee gives AI agents persistent memory by turning documents, code, and conversations into searchable text and connected facts. It helps an application recover useful context after a conversation ends, with local retrieval that can run without a hosted model key.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 23k ▲133/7d · PythonopikOpik records traces from language-model applications and gives teams a place to inspect calls, compare experiments, manage prompts, run evaluations, and watch production behavior. It can run as Comet's hosted service or as an Apache-2.0 self-hosted platform with Python, TypeScript, OpenTelemetry, and MCP entry points.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 22k ▲47/7d · Pythonadk-pythonGoogle's Agent Development Kit is a Python framework for defining agents, tools, sessions, evaluations, and multi-agent workflows in code. It is built around Gemini but can work with other model providers, and it gives teams a path from a local command-line agent to Cloud Run or Vertex AI Agent Engine.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 28k ▲120/7d · TypeScriptaiVercel's AI SDK is a TypeScript toolkit for model generation, agent tool loops and interfaces that display messages and tool results. Its documentation describes shared generation APIs, framework UI packages and connections through Vercel AI Gateway or direct-provider packages.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 207 · Rustambient-contextAmbient Context is a macOS menu bar app that records text from the focused window into plain Markdown files. It can ask an agent CLI you already use to turn each day into cited notes, then lets Claude Code, Codex, Cursor, and other MCP clients search or read the archive.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 1.2k · JavaScriptnorthcinderNorthCinder is software you run alongside an MCP-capable AI app to compare shopping offers, retain source evidence, and request approval before checkout. Its README describes a local search engine and audit trail, with no NorthCinder account or cloud service operated by the repository owner. Research remains provisional: the README says no host and model combination is qualified for routine research use.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 3.5k ▲7/7d · TypeScriptgrok-bot-0.18-reconstructedGrok Bot 0.18 Reconstructed is an unofficial TypeScript reconstruction of the shipped Grok Bot macOS application, with readable replacements for much of its desktop and agent runtime. It keeps the original minified renderer as a pinned input, then adds provider routing for Cursor, Claude Code, Codex, and OpenRouter plus an optional local Docker execution box.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 18k ▲33/7d · PythonMegatron-LMMegatron-LM is NVIDIA's reference framework for training very large transformer models across many GPUs. Its Megatron Core library supplies reusable model components and several ways to split training work across devices, while the repository adds scripts and examples for researchers running full training jobs.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 35k ▲169/7d · JavaScriptcodex-plugin-ccCodex plugin for Claude Code lets Claude Code users request Codex reviews, delegate coding tasks and transfer conversations. It uses the local Codex CLI and app server, including their authentication and configuration. Our sandbox evaluated commit db52e28, associated with release v1.0.6, but did not establish a working authenticated workflow.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 144k ▲470/7d · Pythonawesome-llm-appsAwesome LLM Apps is an English-language collection of runnable AI examples, including document chat, agents, and coding-agent skills. It helps developers start with an existing interaction and inspect the code instead of assembling every part from scratch.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 31k ▲221/7d · PythondeepagentsDeep Agents is LangChain's Python harness for agents that plan work, use files and delegate tasks. It bundles common agent behavior so developers can start with a working design and replace the pieces their application needs to control.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 4.0k ▲32/7d · PythonmarinMarin is an open Python platform for researching and training foundation models, with data preparation, tokenization, training, evaluation, and cluster execution in one project. It records experiment code, checkpoints, reports, decisions, and failed runs so another research group can inspect how a model was made.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 19k ▲93/7d · GogastownGas Town is a workspace manager for coordinating multiple AI coding agents across Git repositories. Its README describes persistent work tracking through git-backed worktrees and a Beads ledger, with mailboxes, identities, handoffs, and a merge queue. Our recorded run did not verify a working multi-agent deployment.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 37k ▲288/7d · awesome-agent-skillsAwesome Agent Skills is a large, organized directory of instruction packs for Claude Code, Codex, Gemini CLI, Cursor, and other coding agents. It helps developers find a skill for a specific job without trawling through GitHub, while keeping official team entries separate from community submissions.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 2.3k ▲31/7d · Goagent-routerEnvoy AI Gateway is now Agent Router, an Envoy-based control plane that gives applications one OpenAI-compatible route to hosted models, self-hosted inference, and MCP servers. It centralizes credentials, routing, quotas, failover, and usage records while Envoy handles the traffic.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 64k ▲177/7d · PythonnanoGPTnanoGPT is a compact Python project for training text-generating models from scratch or adapting pretrained GPT-2 weights to your own text. It puts the model and training loop in readable scripts, but its README now marks it deprecated and recommends nanochat for new users.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 32k ▲310/7d · JavaScript9router9Router is a local gateway for coding assistants such as Claude Code and Codex. Its README documents provider connections, request-format translation, quota tracking and fallback routes, letting developers manage provider choices behind one endpoint.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 8.9k ▲14/7d · Goadk-goGoogle's Agent Development Kit (ADK) for Go is a code-first toolkit for building, evaluating, deploying, and orchestrating AI agents. Its README describes tools, multi-agent composition, and cloud-native deployment, with Gemini as the optimized model path. The recorded October 12, 2026 sandbox run completed installation, build, and testing successfully; it does not establish production readiness.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 37k ▲302/7d · TypeScriptlangfuseLangfuse records the model calls and application steps behind an AI answer, so teams can investigate failures together. It connects those traces to prompt versions, feedback, datasets, and evaluations.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 19k ▲68/7d · TypeScriptclaude-quickstartsClaude Quickstarts is a collection of 15 small applications and reference implementations for building with Claude. It helps developers move from API documentation to working code for agents, browser automation, computer use, support, data analysis, and Managed Agents, but it is a menu of separate projects rather than one starter kit.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 1.1k ▲22/7d · Pythonsf-skillsSalesforce Skills Library is a large collection of Agent Skills for building and operating Salesforce applications. Its folders give compatible coding agents instructions, scripts, references, and assets for Apex, Flow, SOQL, Lightning, Agentforce, metadata, permissions, integrations, and other Salesforce work.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 11k ▲25/7d · Pythonadk-samplesgoogle/adk-samples is a collection of small agents and larger recipes built with Google's Agent Development Kit. Its curated `core` examples teach patterns such as OAuth, memory, safety, research, and retrieval, while `contrib` holds community examples for particular workflows.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 3.9k ▲13/7d · Rustlean-ctxLeanCTX is a context gateway between AI tools and the information they read. Its Engine runs locally through CLI, MCP, hooks and optional proxy paths. The README describes file selection, command-output compression, session memory, repository graphs and usage records. These are documented capabilities; our recorded run covered source preparation, build and test commands, not a working agent integration or a savings workload.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 40k ▲116/7d · PythonLightRAGLightRAG turns documents into a searchable map of entities and relationships, then uses that map alongside text search to answer questions. It helps when an answer depends on connections scattered across documents, and includes a server, web interface, and Python library.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 14k ▲78/7d · Pythonagent-frameworkMicrosoft Agent Framework is a Python and .NET toolkit for building AI agents and joining them into stateful workflows. It supplies the machinery around model calls, including tools, middleware, checkpoints, streaming, human approval, tracing, and hosting patterns.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 17k ▲39/7d · Gomcp-toolboxMCP Toolbox for Databases is an open source Go MCP server with two uses: prebuilt tools for database exploration and a YAML framework for defining custom database operations. The README describes connection pooling, IAM integration and OpenTelemetry support. Our recorded run covers setup, build and test steps, not database workloads or production access controls.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 7.7k ▲93/7d · GoengramEngram gives coding agents a persistent memory store backed by SQLite and FTS5. A single Go binary exposes that memory through MCP, a CLI, a terminal interface, and an optional HTTP or cloud layer, so work from one session can be found in the next.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 449 · JavaScriptv4-flash-godmode-opencode-goThis project's supplied documentation is primarily in Chinese, and no English documentation is evidenced in the material provided. It is a temporary opencode-go adaptation of an early routing approach intended to improve DeepSeek V4 Flash under guided conditions, but its maintainer says development has ended and directs users to the original project.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 10k ▲51/7d · TypeScriptDesktopCommanderMCPDesktop Commander is an MCP server that lets an AI client read and edit local files, search folders, run terminal commands, manage processes, and work with spreadsheets, PDFs, and Word documents. It turns Claude Desktop, Claude Code, Codex, and other MCP clients into operators of the computer where the server runs.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 3.7k ▲33/7d · TypeScriptletta-codeLetta Code is a coding-agent harness whose agents keep memory, identity, and conversation state across sessions. You can use it in a terminal, desktop app, browser, or messaging channel, with either Letta Cloud or a local backend.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 13k ▲47/7d · JavaScriptclaude-code-system-promptsClaude Code System Prompts is an unofficial, versioned archive of prompt text extracted from Claude Code's compiled npm package. It separates hundreds of system instructions, tool descriptions, agent prompts, reminders, skills, and data blocks into searchable Markdown files so researchers and prompt authors can see what changed.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 1.2k · Pythonbook-to-skillbook-to-skill converts technical books and folders of documentation into structured agent skills with an index, chapter notes, a glossary, patterns, and a cheat sheet. It is meant to solve a familiar retrieval problem: useful material is sitting in a file, but finding and applying the relevant section while working takes too much effort.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 2.8k ▲10/7d · Shellclaudish-to-englishclaudish-to-english is a Claude Code plugin that rewrites assistant messages in plain English before displaying them. It leaves Claude's original response and saved transcript untouched, while using Ollama locally by default or an Anthropic or OpenAI-compatible API to produce a more readable version.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 9.2k ▲131/7d · GobifrostBifrost is a self-hosted gateway that gives applications one API for more than 23 model providers. It centralizes credentials, request translation, retries, fallbacks, budgets, logs, plugins, and MCP tools so each application does not have to implement those controls separately.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 7.0k ▲1/7d · JavaScriptdsh-routing-suitedsh-routing-suite is a Chinese-first extension suite for DeepSeek Harness, with a complete English README available. It combines a runtime plugin injector with presets that classify a task and change the agent's reasoning persona, tool exposure, and reminders during a session.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 23k ▲55/7d · TypeScriptNemoClawNVIDIA NemoClaw is a reference stack for running OpenClaw, Hermes, or LangChain Deep Agents Code inside NVIDIA OpenShell sandboxes. Its CLI combines onboarding, managed inference, network policy, integrations, snapshots, and lifecycle operations so an agent gets bounded host and network access.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 45k ▲1.3k/7d · CcolibriColibri runs open AI models locally by keeping frequently used weights in memory and reading other weights from disk as needed. It gives you a chat interface and APIs for existing apps, with a C inference engine underneath the Python setup tools.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 34k ▲66/7d · TypeScriptopenclaudeOpenClaude is a terminal coding assistant built from the Claude Code codebase and modified to work with hosted APIs and local models. It can read and edit files, run shell commands, call subagents, and connect to MCP tools while keeping one interface as you change model providers. Its LICENSE says the underlying Claude Code source remains Anthropic's proprietary code and was distributed without Anthropic's authorization, which changes the adoption decision.SetupDocsCommunityMaturityVerdict inside LLM Tools★ 12k ▲454/7d · JavaScriptawesome-free-llm-apisAwesome Free LLM APIs is a curated English-language catalog of hosted text-model APIs with recurring free access. It puts signup links, API base URLs, model names, context sizes, output limits, modalities, and quotas in one place, so developers can shortlist providers without opening a dozen pricing pages.SetupDocsCommunityMaturityVerdict inside