Autonomous AI agents that perform tasks independently
GitHub Actions
npx installer for Team Agent
renejes
Node-based architecture spec that lives in your repo. AI-readable, AI-writable, git-diffable.
bereilhp
Local-first sandbox for isolated, observable and traceable execution of AI agents.
GAMKERS
AI-powered cybersecurity CLI with web research, local LLM support, and intelligent agents
facetai
Facet Terminal payment-rail adapter for Stripe (Cards, ACH, wallets). Implements FacetPaymentRailAdapter on top of the official stripe npm package. PaymentIntents with reserve-capture, refunds, disputes, and webhook signature verification.
...morePydantic AI Channels Contributors
Production-ready Telegram and Slack channels for Pydantic AI agents.
Agentic Beacon Contributors
Agentic Beacon CLI - Distribute knowledge contexts and skills for AI-assisted development teams
SDK for building OpenHospital contest doctor agents.
Cofound
An AI cofounder in your terminal — leads, plans, and writes to a local canvas. Built on Claude.
A flexible calculation toolbox designed for LLM Function Calling
AI Layer for Lexigram Framework - Native LLM, Vector, RAG integration
AI session management for the Lexigram Framework — branching, checkpointing, multi-agent sessions
OpenChatBI - Natural language business intelligence powered by LLMs for intuitive data analysis and SQL generation
Argosvix Python SDK = AI agent observability (cost / latency / tokens / errors) for OpenAI / Anthropic / Gemini / Mistral
...moreLLM Prompt Injection Detection CLI — 3-layer detection (Vigil + DistilBERT ONNX + Rules)
DapplePot Python SDK for AI agent security observability — instruments LangChain/LangGraph, OpenAI, and Anthropic
A harness for delegating coding work to LLMs while keeping your main agent clean. Structured artifacts, long-running support, and swappable backends.
...moreJosephOIbrahim
MCP server bridging Claude Code to Unreal Engine 5.7 — 56 tools across 14 modules for scene understanding, world-building (spatial + lighting), materials, animation, and editor control
...moreiyuenan3
桌面小红书 AI 运营工具 — Electron + Go MCP 浏览器自动化，AI 驱动发布/评论/点赞/数据采集/定时工作流
boblabs-eu
Self-hosted multi-agent AI platform. Persistent labs, 40 sandboxed tools (code, web, RAG, GPU dispatcher, web3), private Qdrant + LightRAG, sandboxed code execution per lab, anti-loop detection, Ollama/vLLM/OpenAI/Anthropic adapters. Two-command Docker deploy. Apache 2.0.
...moreachappey
Backend implementing the Agent Framework for orchestrating agent workflows and message exchange. Acts as a content and response wrapper between Vercel-based clients and Microsoft systems, providing structured request/response handling, routing, and lifecycle management without embedding AI logic itself.
...moreMerkyorLynn
开源桌面 AI Agent & CLI· 长期记忆 · 多 Agent/CLI Fleet · 语音TTS/ASR · 0 API Key · Open-source desktop AI agent & CLI — long-term memory, multi-agent, voice & a CLI worker fleet
...moreDav31012
Agentic coding CLI for a-Shell
Cristophereasygoing927
Compare code reviews across models in Claude Code with ranked todos and subagent dispatch via MCP.