GitHub projects

Framework for building stateful AI agents in Go. !GitHub Repo stars

Local-first managed agent runtime with persistent sessions, sandboxed execution, MCP tools, audit, replay, and a human console. !GitHub Repo stars

Self-programming AI agent framework where agents create and refine their own workflows, with multi-agent orchestration, persistent sessions, sandboxed execution, and desktop and web interfaces. !GitHub Repo stars

Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability. !GitHub Repo stars

Out-of-process governance control plane for autonomous AI agents — pre-dispatch policy enforcement, approval gates, and signed audit trails for production governance. !GitHub Repo stars

Autonomous agent framework that runs unattended via GitHub Actions, with self-healing skills, output quality scoring, persistent memory, and reactive triggers. !GitHub Repo stars

Simple Python framework for production-ready AI agents — 2-line creation, functions as tools, 12 lifecycle hooks, plugin system, multi-agent networking with trust !GitHub Repo stars

Let AI agents message, watch, and spawn each other across terminals. Claude Code, Gemini CLI, Codex, OpenCode. !GitHub Repo stars

An overlay network stack that gives AI agents virtual addresses, encrypted UDP tunnels, NAT traversal, and mutual trust. Zero dependencies, written in Go. !GitHub Repo stars

Open-source production-ready RAG platform with built-in agentic reasoning, hybrid search, and multimodal support. !GitHub Repo stars

A Evolve Agent Development Framework. From atomic components and development frameworks to core scenario Agents !GitHub Repo stars

Open Source framework for voice and multimodal conversational AI. !GitHub Repo stars

A complete solution for agent memory, from extraction and vector search to automated optimization, with a REST API, MCP, CLI, and insights dashboard out-of-the-box.

A comprehensive framework for building AI agents that run anywhere, with full local-AI and WASM support.

Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.

Self-improving agents that learn from execution feedback. LangChain integration for agents that curate their own context. !GitHub Repo stars

A model-driven approach to building AI agents in just a few lines of code. !GitHub Repo stars

Bleeding-Edge Multi-Agent Orchestration Framework for Enterprise Applications !GitHub Repo stars

Stop wrestling with countless APIs and complex integrations. AgentDock provides the open-source foundation to build, manage, and deploy production-ready AI agents and workflows, frictionlessly. !GitHub Repo stars

Mastra is an opinionated TypeScript framework that helps you build AI applications and features quickly. !GitHub Repo stars

Reliable agent framework that supports MCP. !GitHub Repo stars

Reliable agent framework built on top of the latest OpenAI Assistants API. !GitHub Repo stars

Start building LLM-empowered multi-agent applications in an easier way. !GitHub Repo stars

A framework for Claude Opus to intelligently orchestrate subagents. !GitHub Repo stars

Provides a flexible framework that simplifies the process of building custom multi-agent environments for LLMs !GitHub Repo stars

AG2 (from AutoGen creators) is an open-source programming framework for building AI agents and facilitating cooperation among multiple agents to solve tasks. !GitHub Repo stars

The Multi-Agent Meta Programming Framework: Given one line Requirement, return PRD, Design, Tasks, Repo and CI !GitHub Repo stars

Design and Deploy Large Language Model Apps !GitHub Repo stars

Open-source platform for building & deploying virtual developers’ agents

Dynamic AI agent automation platform that orchestrates instruction following and complex task management. !GitHub Repo stars

The building blocks for building chatbots !GitHub Repo stars

Claude Code skill for public SEC EDGAR + market data: /analyze, /score, /compare. MIT.

Git-Native Agent Protocol: coordinate AI agent teams with 4 JSON files in a git repo. No server, no database. Any agent that can git push can participate. MIT licensed.

Paper

Documentation

X

Documentation

</details>

Paper

Paper

</details>

Project page

</details>

Discord

Blog

Kaveen Kumarasinghe - founder of GPT Discord - website

Authors: Emil Ahlbäck, Lonis

</details>