Open-Source Agent Observability & Evals for AI Platform teams. Trace, test, route and govern every agent & coding assistant in the company.
Repository Index
142,273 visible repositories in the index
313–336 of 1,660 · Most stars
🔬 Harness Vibe Research with Self-evolving AI Scientists
- ai-agent
- ai4science
- multi-agent-system
- vibe-research
Agenta is a workspace where you and your team build agents and automations.
- agent-builder
- agent-observability
- agent-orchestration
- agent-workspace
Platform for building and running AI agents across the full lifecycle — build, test, deploy, monitor, improve. Hosts your agents, runs their tools, and coordinates them over an event mesh, with sessions, artifacts, auth, evaluators, and observability built in.
- agents
- ai-agents
- agentic-ai
- framework
A minimalistic ClojureScript interface to React.js
Paper list of multi-agent reinforcement learning (MARL)
- multiagent-reinforcement-learning
- multi-agent-learning
Beautiful, AI-native markdown IDE and LLM wiki
- 2nd-brain
- agent-skills
- claude
- codex
Structured multi-perspective deliberation for hard decisions. Run full councils, focused triads, or duo debates across Claude Code, Codex, Gemini CLI, and OpenCode.
- ai-agents
- claude-code
- decision-making
- deliberation
TranslatedAn open-source AI agent for social media — discover trends, create content, publish everywhere, and learn what works across Xiaohongshu, Douyin, Zhihu, Bilibili, and more.🎨
- agent
- agent-skill
- content-automation
- content-creation
Open-source observability for AI agents. Find where your agents fail, dispatch your coding agent to fix it, and verify the fix against real traces.
- llm-observability
- agent-monitoring
- agent-observability
- ai-error-monitor
Curated list of Agent Skills centered on people, relationships, commemorative scenes, and methodological perspectives
- awesome
- awesome-list
- agent-skills
- persona-distill
Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks from beginner to power user!
A protocol for connecting any editor to any agent
TranslatedMakes Chinese written by AI read like a specific person speaking. A general-purpose writing and revision Skill, ready to use out of the box.
- agent-skills
- chinese-writing
- creative-writing
- writing-skill
Open-source AI teammates in Slack, Teams, Discord, Telegram and Mattermost. Bring Claude Code, Codex, Gemini (Antigravity), Cursor, GitHub Copilot or your own agent on any model, and connect them to GitHub, Jira, Notion, Linear, Google Workspace and more. Self-hosted multi-agent orchestration with MCP.
agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes and reinforcement learning (RL).
- kubernetes
- agent
- ai
- rl
Koog is a JVM (Java and Kotlin) framework for building predictable, fault-tolerant and enterprise-ready AI agents across all platforms – from backend services to Android and iOS, JVM, and even in-browser environments. Koog is based on our AI products expertise and provides proven solutions for complex LLM and AI problems
- agentframework
- agentic-ai
- agents
- ai
Use pstack with claude, codex, pi - Skills and principles for rigorous AI-assisted engineering
- agentskills
- pstack
- pstack-claude
- skills
A simple yet powerful agent framework that delivers with open-source models
- agent-framework
- agents
- openai-agents
- python
Antigravity, Claude Code, Codex, Copilot, DeepSeek Harness, Gemini, Grok Build, Kimi Code, MiniMax Code, Muse, OMP, OpenCode, Pi, Prime Agent, etc versions of Poteto's pstack. Rigorous agent workflows with Cursor primitives translated for other harnesses.
Manage multiple Claude Code, OpenCode agents from either TUI or Web for easy access on mobile. Also supports Mistral Vibe, Codex CLI, Gemini CLI, Pi.dev, Copilot CLI, Factory Droid Coding.
TranslatedOpenClaw Chinese tutorial (4,500+ Stars · printed book published): installation, configuration, Skills, Feishu integration, and pitfalls to avoid | For the author's new GPT-6 / Codex / Claude Code projects, see the top of the README
- openclaw
- openclaw-skills
- agent-skills
- ai-agent
Full toolkit for running an AI agent service built with LangGraph, FastAPI and Streamlit
- agents
- langgraph
- streamlit
ADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude & Codex Agent SDK. Fans out parallel divergent thoughts under different cognitive frames, scores, prunes traps, deepens the survivors. The no-brainer skill for creative and interdisciplinary work.