Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.
Repository Index
75,859 visible repositories in the index
1–15 of 15 · Most stars
An AI-powered custom node for ComfyUI designed to enhance workflow automation and provide intelligent assistance
Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai
- agent
- agentic-ai
- agentic-framework
- agentic-workflow
The World's First Virtual Terminal for AI Agents
- agent-sandbox
- agent-tools
- ai-agents
- bash
An open-source research agent system for your Zotero library.
- academic-paper
- literature-analysis
- llm-agent
- zotero-plugin
One-stop shop for building AI-powered products and businesses with Stripe.
- llm
- llm-agents
- python
- typescript
The open-source cybersecurity harness. Includes a web interface for code analysis, pentesting, vulnerability research, reverse engineering, verification, and fixing + CLI and MCP for agents.
- llm-agents
- security-research
- security-tools
- application-security
When Claude Code hits its usage limit, Codex picks the task up from the same memory. Sno Station puts Codex, Claude Code, Cursor, Hermes Agent and OpenClaw on one squad: they hand work to each other and review each other's code. Open source, runs on your computer.
TranslatedAI Werewolf game. You take one seat, LLM players fill the rest. AI Werewolf.
OrcaReplay — Time travel for AI agents. Record, replay, fork, and debug any agent run with any model. Built by the OrcaRouter.ai team.
TranslatedDSH plugin — free OpenCode Zen models for DeepSeek Harness (DSH). Free LLM API, no API key needed.
- cordis
- cordis-plugin
- dsh
- dsh-plugin
50x your usage with cheap-ag. Opus/Astra plans, a dirt-cheap model writes every line, and tests decide what ships. Your $20 plan stops hitting limits. One MCP server for Claude Code & Codex.
Co-manage memory with your coding agent across sessions. A local workbench for Claude Code, Codex, Pi and OpenCode.
Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.
- ai-safety
- ai-security
- claude-code
- llm-agent
An open-source studio for teams of AI agents, from marketing squads to dev teams to research crews. Deploy a team, then watch them delegate and collaborate live. Self-hosted, one command.
- agent-framework
- agent-harness
- agent-orchestration
- agentic-ai