Autonomous AI agents that perform tasks independently
skill-eval contributors
Framework for evaluating agent skills across OpenCode, Claude Code, and Codex
Eloi Barti
One typed runtime API for Claude, Codex, and Antigravity agent SDKs.
Python SDK for the blockfill agent execution
aimax contributors
Drive Claude Code and Codex TUIs through tmux from Python.
Ali K <[email protected]>
Read and search Codex CLI and Claude Code chat history from the terminal.
qianchuan
Runtime persistence adapters for pi.
ramanshrivastava
The OpenSkill CLI (osm) — search, add, score, and explore AI agent skills from your terminal
ramanshrivastava
The OpenSkill CLI (osm) — search, add, score, and explore AI agent skills from your terminal
Red Duck Labs <[email protected]>
MCP server for coordinating Claude Code instances across multiple projects
June
Unofficial TypeScript port of CrewAI (not affiliated with crewAI, Inc.).
Roger Simoes
Self-curating memory for LLM agents: MeMo-style external memory kept honest by survival-based selection instead of reward models or judges.
...morejvit
A Tabby terminal plugin that adds an AI assistant side panel to terminal tabs, with chat, terminal context sharing, and tools for reviewing and running terminal commands. The command approval mode is configurable in settings, and the panel shows each comm
...moreKodria
CLI to manage Agentic Workflows - install skills, workflows, and processes for AI agents
innei
AI agent editor integration: diff UI, action registry, agent panel plugin
salatov
Portable repository-native foundation for agent memory, skills, handoffs, and knowledge workflows.
Unstruk Data Inc.
Top-level Graphlit tool factories for TypeScript streamAgent applications
PlaiPin
AgenticROS core — platform-agnostic ROS2 transport, types, and config (the dep every AgenticROS skill imports).
PerSQL <[email protected]>
OpenAI Agents SDK session memory backed by PerSQL — durable conversation history in an isolated SQLite database per agent.
...morecraigamcw
Open-source verifiable agent accountability — cryptographic capability receipts and formal proofs for LLM agent activity
kevinchennewbee
蓬莱 Penglai — 住在你飞书和微信里的中文 AI 管家 · Your personal AI butler in Feishu & WeChat (powered by GenericAgent, kernel untouched)
RAmenLch
AI Agent framework on LangChain/LangGraph — multi-backend filesystem, sub-agent scheduling, conversation summarization, security review, and skills system out of the box.
...morematrix1010
darwin arm64 binary for shumai-agent
Damian ONeill
Skills extension for the OpenAI Agents SDK
dugsnodes
Composable primitives for building LLM agents — atoms, protocols, molecules, rendering, organisms