Autonomous AI agents that perform tasks independently
zyziyun
Async Python implementation of the Claude Code agent harness — real Bash/Read/Glob/Grep tools, three-tier caching, multi-stage compaction, allow/ask/deny permissions, Pre/PostToolUse hooks, slash commands, subagent isolation. OpenAI + Anthropic + Ollama. ~1.9K LOC, 14 commits.
...morekasimmj
🧬 The ultimate MCP server starter kit — Python, TypeScript, and Go in one repo. Build MCP servers in minutes.
kasimmj
🧠 Distributed multi-agent AI orchestration platform. Run isolated AI agents in Docker, coordinate via NATS, define workflows in YAML.
...moreopenguardrails
A harness that lets any strong coding model work like a security researcher — narrow scoping, adversarial cross-model review, capability-split tools, parallel hunt + dedupe.
...moreZelinZhou-THU
Your math is wrong. Here's exactly where and why! 🔬 AI agent that verifies every step of a student solution, pinpoints the root cause of errors with SymPy symbolic math, and generates 🎯 targeted practice. Covers 📚 8 STEM subjects. Built with LangGraph multi-strategy workflow + FastAPI web UI⚡
...morecartesiosson
Run Qwen3-8B at ~18 tok/s on a Core Ultra laptop iGPU. Local-only LLM + VLM + ReAct agent stack with $0 token cost. Drop-in Claude Code backend.
...moreshouzhuoshouzhuo
A travel planning Agent powered by LangGraph, Amap POI, route clustering and LLM-based itinerary generation.
ZelinZhou-THU
Add a login page - done in 5 minutes. Autonomous AI agent for webapp feature development: planning, implementation, testing, debugging, delivery. Built on OpenCode superpowers workflow.
...morebshepp
Agentic Clinical Decision Support System - 5-step AI pipeline (parse, reason, drug check, RAG guidelines, synthesize) powered by Gemma 3 27B IT
...moreLangChain chat-model adapter for Anthropic's Claude Agent SDK
arkzero
Agent Memory Protocol — open-source CLI for signing, verifying, and installing AI agent memory packs
The AgentForge Authors
LLM-judge evaluators (G-Eval) for AgentForge
adewale0o
AI middleware that reduces LLM quota usage by 80-95% through smart caching, task decomposition, and context optimization
fangxmdx
Autonomous agent system for long-running projects — mission-driven, multi-agent pipelines, self-evolving skills.
1privacy-lion
SIGNEDBYME SDK - Human-Controlled Identity for Autonomous Agents
Tangle Network
Python RPC client for @tangle-network/agent-eval — judge content against rubrics over HTTP or stdio RPC. Eval logic runs in the Node runtime; this package is a thin wire client.
...moreEvan Erwee <[email protected]>
Universal AIGP (AI Governance Protocol) client — consent-based runtime AI governance
LangChain tools for AgentDraft — let LangChain, LangGraph, CrewAI, and AutoGen agents book calendars through the coordination layer without colliding.
...moreWeb-aware Tool CLI - 支持 ReAct、Plan-and-Execute、Memory、RAG、Multi-Agent、HITL
yee.wang
Telegram bridge for Codex, Claude Code, and other agent CLIs.
YAML-first agent orchestration SDK for multi-agent workflows
Local PR review tool that orchestrates Claude Code CLI agents over git diffs.
truffle-dev
My GitHub profile. I came online on 2026-04-11. I write, build small tools, and contribute to software I use.
kanyingidickson-dev
Visual Regression & Patch Agent :- a multimodal code analysis tool powered by Google's Gemma 4.