Autonomous AI agents that perform tasks independently
shenmintao
A library-science-inspired personal knowledge management system with LLM agents
anemoi-ai
A working AI agent built in C from scratch — no frameworks, no SDK. ReAct loop, tool system, filesystem sandboxing, 200+ tests.
...morerty90
Android Agent Reliability Runtime A debugging and safety runtime for mobile GUI agents: detect readiness, block unsafe actions, verify progress, diagnose failures, and save reproducible traces.
...moreFramework adapters for the Agent Governance Toolkit (LangChain, CrewAI, OpenAI Agents, and more)
Retrieval access control and vector store policy enforcement for RAG pipelines
Practical Mind
Version control for LLM prompts. Zero dependencies, works offline, embeds in any project.
gakwaya
Lemon AI Agent — spawn specialist agents from Node.js APIs with tools, streaming, and structured output
tomer_veto
The Veto CLI. Tell an AI agent what to buy. Veto decides if it's safe.
tamilselvan89
Token-aware rate-limit queue proxy for the Anthropic Claude API. Agents never see a 429.
lc708
A Unified Virtual Filesystem For AI Agents
airkyzzz
LangChain/LangGraph integration for Credat — authenticate AI agents with trust and delegation
wuchenfan
AI Agent 通用流程编排框架 — 声明式 YAML 驱动，任何 LLM Agent 即插即用
GitHub Actions
TypeScript CLI for the chump coding assistant
longhuaw
🚀 Multi-Model Terminal AI Agent — Doubao · DeepSeek · Claude
zwbigi
Pi Agent xY - Web UI for the pi coding agent
legostin
Local-first knowledge base built by an agent over a chosen directory.
RSN DB Contributors
Rust-powered embedded database for Python: encryption, GraphRAG, MemPalace AI memory, and an agent-friendly CLI
Privacy-preserving audit framework for multi-agent AI systems. Detects cross-agent data leaks, inference attacks, and compliance violations — without accessing raw content.
...morePlug & Play skill framework — connect any LLM to your PC in 3 lines
Observability for Claude Code agentic runs — live TUI dashboard for Claude Code sessions
Decimal AI
An open spec for A/B benchmarking Claude Code skills via declarative test suites.
helix-harness
TypeScript Agent execution-layer SDK. You write the model and tools, it runs the loop.
Azamat771
Self-hosted single-page content studio for niche Instagram bloggers. Idea bank + AI generator + SMM/UGC agents with live trends. MIT.
...moreaaronjmars
The most autonomous agent framework. No approval loops. No babysitting. Configure once, forget forever.