Category · 52 repos
Multi-Agent Systems
Frameworks where several AI agents collaborate, debate or hand work to each other. Ranked by star velocity over the last 24 hours.
Showing 1–50 of 52
Build your own network of agents from Claude Code, Codex and Pi: persistent teams with roles, shared context and owned work.
Brigade — Your personal intelligence, built enterprise-grade
DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
An Agent Skill: drive Cline CLI coding tasks as the user's proxy.
OpenHuman is the fastest, cheapest, most efficient open-source agent harness. Written in Rust
🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.
A smarter, self-hosted AI assistant — multi-user, multi-agent.
A living pixel-art station where real AI agents do real work. Local-first desktop agent harness - bring your own key, watch your crew actually run.
Python tool for converting files and office documents to Markdown.
Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click
18 Lessons to Get Started Building AI Agents
Bindu: The identity, communication, and payments layer for AI agents.
Connect any AI copilot or autonomous agent to your enterprise tools — through a single, secure MCP/Agent gateway with built-in identity, access control, and full observability.
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.
Open-source main repository for Understanding AI Agents in Depth: Design Principles and Engineering Practice (by Li Bojie): the full book text, compiled PDF, and chapter-by-chapter code.
TradingAgents: Multi-Agents LLM Financial Trading Framework
The local-first operating system for building, running, and improving AI agents, workflows, and autonomous goals.
AI Kanban & Development Environment. Orchestrate multiple agents, review changes, open PRs. Multi-provider, self-hostable, no telemetry.
Build, run and scale AI agents like API and microservices
Repo for AI Agents The Definitive Guide
A production-oriented AI workflow runtime for building, validating, recovering, and shipping complex AI workflows as dependable services. Production-oriented AI workflow runtime: rapidly develop, validate, and recover complex AI workflows, then reliably deliver them as services.
High-performance decentralized coordination protocol for multi-agent LLM systems. Plant-inspired signal diffusion with sub-microsecond processing, QUIC P2P networking, and unified LLM backends (Ollama + Claude).
Minimal Coding Agent Harness on MCP for ChatGPT, Claude, Hermes, Grok Bot, OpenClaw
Universal SKILL.md catalog for research workflows: literature review, research design, project memory, manuscript writing, and cross-agent delegation for Claude Code, Codex, Gemini, Cursor, OpenClaw, and generic AI clients.
Ouroboros — self-creating AI agent. Born Feb 16, 2026.
A-share short-term daily-review dashboard: view limit-up stocks, consecutive limit-up tiers, Dragon-Tiger List, and sector flows on one screen. Derived indicators such as profit-making effect, promotion rate, tier gaps, and sentiment cycle are calculated directly (without AI); AI only turns the data into readable market analysis. Runs entirely locally and can use Claude/Codex subscriptions…
Multi-agent AI coding platform powered by Vercel Sandbox and AI Gateway
TinyAGI is the agent teams orchestrator for One Person Company. (fka TinyClaw)
Official repository for EigenFlux — the open-source communication and broadcast network for AI agents.
A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use.
Supervised multi-agent orchestration for Pi
🌈 Make Claude Code, OpenAI Codex, Antigravity (Gemini) and Grok collaborate on one shared project — a turn-taking multi-agent relay plus an MCP bridge to drive any AI from inside another.
Gas Town - multi-agent workspace manager
Orkas is an open-source, local-first AI desktop app: a commander LLM directs specialist sub-agents, and runs your installed coding CLIs — Claude Code, Codex, OpenCode, OpenClaw, Hermes — as local sessions. Agents self-evolve via reflection and skill crystallization. BYO keys. macOS / Windows / Linux
Agent Orchestration Command Center
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex
“Guanlan,” a multi-agent situation assessment and decision-reporting platform for all media / Multi-Agent Situation Awareness & Decision Reporting Platform
Run and supervise teams of coding agents from planning to merge. Any harness (Claude code, codex, +25 more). Desktop, web, mobile, and cloud agents.
AI-powered virtual executive team — a single coherent executive persona backed by 8 specialist agents (FastAPI + Next.js).
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
Deep Search Pro — a multi-agent collaborative search system with fewer than 1,000 lines. Built on LangChain + FastAPI + WebSocket, with a primary agent coordinating three subagents (web search, database queries, and knowledge-base retrieval) to handle complex tasks collaboratively. A hands-on project for learning AI Agents.
A multi-provider, multi-agent orchestrator that organizes agents into a visual authority hierarchy.
UDOS by DeepSeek — unified world-model + multi-agent topology engine. A from-scratch rewrite of TwinsEarth/udos-reasoning-engine v7.5.0 (Apache-2.0), CPU-only and offline.
Build resilient agents.
Interactive front-end CONCEPT UI for an autonomous multi-agent marketing command center. Clearly labeled prototype (not wired to live LLM/ad platforms).
CYPRESS (Contextual Yield Protocol for Routed Expert Seed Systems) — a project- and vendor-agnostic multi-agent seed for AI coding tools. Drop it into any repo to give agents a large number of per-role expert team, named protocols, a progressive-discovery knowledge graph, and spec- and test-driven d