multi-agent
Tracked open-source repos tagged multi-agent, sorted by stars.
- #61
Backtestable AI trading agents and Python algorithmic trading strategies for stocks, options, crypto, futures, forex, SEC filings, FRED macro data, and real brokers.
★ 2,033+25Star change over the last 7 days - #62
You're the boss, agents are your team. They handle tasks on their own, message each other, and review each other's work. You just watch the kanban board and give high-level commands. Codex/Claude/OpenCode/Cursor/Grok/GitHub Copilot/Kiro/Z.AI/MiniMax/Kimi(200+ models, 75+ LLM providers, free models no auth). Build your AI company with multiple teams
★ 2,025+30Star change over the last 7 days - #63
[ICML 2026] Video generation via code
★ 2,013+4Star change over the last 7 days - #64
🤖 A comprehensive list of 1,500+ resources and tools related to AI agents.
★ 1,961+6Star change over the last 7 days - #65
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.
★ 1,922+9Star change over the last 7 days - #66★ 1,818+19Star change over the last 7 days
- #67
A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.
★ 1,760+12Star change over the last 7 days - #68
An open-source, code-first Java toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
★ 1,711+3Star change over the last 7 days - #69★ 1,664+5Star change over the last 7 days
- #70
A compilation of the best multi-agent papers
★ 1,664+6Star change over the last 7 days - #71
Open-source multi-agent AI desktop client — build and command your AI agent team through conversation. A commander LLM dispatches sub-agents in parallel or in series; agents self-evolve via reflection and skill crystallization. Local-first, BYO LLM keys (Claude · OpenAI · Gemini · DeepSeek · Kimi · GLM · Qwen). macOS / Windows / Linux.
★ 1,635+111Star change over the last 7 days - #72
Cross-platform local MCP capabilities for ChatGPT with Chrome integration, Goal, Compact & Resume, and durable multi-agent workflows.
★ 1,563+913Star change over the last 7 days - #73
ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.
★ 1,560+1Star change over the last 7 days - #74
FinnewsHunter: Multi-agent financial intelligence platform powered by AgenticX. Real-time news analysis, sentiment fusion, and alpha factor mining.
★ 1,488+1Star change over the last 7 days - #75
Cross-vendor messaging for CLI AI coding agents — let Claude Code, Codex, Gemini & Copilot talk to each other in one team. Bash + SQLite, no daemon, no framework.
★ 1,477+6Star change over the last 7 days - #76
Samurai-inspired multi-agent system for Claude Code. Orchestrate parallel AI tasks via tmux with shogun → karo → ashigaru hierarchy.
★ 1,420+1Star change over the last 7 days - #77
Agent-driven automated CVE discovery platform for source code auditing, vulnerability verification, and report generation.
★ 1,386+39Star change over the last 7 days - #78★ 1,382+3Star change over the last 7 days
- #79
An open-source, code-first Typescript toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
★ 1,381+7Star change over the last 7 days - #80
TAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and what gets recorded — in YAML
★ 1,325+7Star change over the last 7 days - #81
🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.
★ 1,323+3Star change over the last 7 days - #82
Open-source room for humans + cross-vendor AI agents. Every agent gets its own name, memory, skills, and workstation. Any runtime, your infra — no per-agent fees.
★ 1,323+0Star change over the last 7 days - #83★ 1,297+2Star change over the last 7 days
- #84★ 1,292+0Star change over the last 7 days
- #85
An intelligent assistant serving the entire software development lifecycle, powered by a Multi-Agent Framework, working with DevOps Toolkits, Code&Doc Repo RAG, etc.
★ 1,291+1Star change over the last 7 days - #86
The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular, and production-ready, it lets developers build, run, and manage intelligent agents across local, cloud, and edge environments.
★ 1,289-1Star change over the last 7 days - #87
The multi-agent harness that checks the work: verifies agent runs by artifacts (stop-hook gates, independent judges, append-only event logs) across Claude Code, Codex, Cursor, and 10+ runtimes.
★ 1,261+7Star change over the last 7 days - #88
The open-source, multi-agent alternative to Claude Tag. @ any agent, wherever work happens, they work alongside your team, learning as they go.
★ 1,230+625Star change over the last 7 days - #89
A collection of autonomous agents 🤖️ powered by LLM.
★ 1,225+2Star change over the last 7 days - #90
LightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing, lifecycle hooks, multi-agent collaboration, and workflows.
★ 1,215+1Star change over the last 7 days