Git Stars Git Stars

#multi-agent Repositories

239
Total Repositories
1.3M
Total Stars
5,518
Avg Stars/Repo
151
microsoft/maro

Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.

microsoft
โญ 920 Python ๐Ÿ‘ค microsoft Organization ๐Ÿ• Updated 2025-04-24 ๐Ÿ“… Created 2019-12-27
152
keli-wen/agy-staff

Hire Google's Antigravity CLI (agy) as a fast Gemini staffer for Claude Code, OpenAI Codex, and DeepSeek Harness.

keli-wen
โญ 905 JavaScript ๐Ÿ‘ค keli-wen User ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2026-08-18
153
ythx-101/live-panel-skill

Agent skill + renderer: turn a single JSON config (or an Excalidraw file) into an animated architecture diagramโ€”either a terminal-style live panel or a pastel infographicโ€”as an MP4 or looping web page. Animated architecture diagrams / animated agent architecture, optimized for X and Xiaohongshu.

ythx-101
โญ 875 JavaScript ๐Ÿ‘ค ythx-101 User ๐Ÿ• Updated 2026-11-12 ๐Ÿ“… Created 2026-10-03
154
Intrect-io/OpenSwarm

OpenSwarm โ€” Autonomous AI dev team orchestrator powered by Claude Code CLI. Discord control, Linear integration, cognitive memory.

Intrect-io
โญ 870 TypeScript ๐Ÿ‘ค Intrect-io Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-02-23
155
pullboard-dev/pullboard

Autonomous development for real products. You set the standard. Declare your vision. Walk away. It builds.

pullboard-dev
โญ 847 JavaScript ๐Ÿ‘ค pullboard-dev Organization ๐Ÿ• Updated 2026-11-15 ๐Ÿ“… Created 2026-10-07
156
Haervwe/open-webui-tools

Openโ€‘WebUI Tools is a modular toolkit designed to extend and enrich your Open WebUI instance, turning it into a powerful AI workstation. With a suite of over 15 specialized tools, function pipelines, and filters, this project supports academic research, agentic autonomy, multimodal creativity, workflows, and more.

Haervwe
โญ 838 Python ๐Ÿ‘ค Haervwe User ๐Ÿ• Updated 2026-11-11 ๐Ÿ“… Created 2024-11-09
157
AIScientists-Dev/WorldSeed

More is Different. A multi-agent world engine where AI agents live, talk, compete, ally.

AIScientists-Dev
โญ 826 Python ๐Ÿ‘ค AIScientists-Dev Organization ๐Ÿ• Updated 2026-05-08 ๐Ÿ“… Created 2026-04-15
158
go-kratos/blades

Blades is a Go-based multimodal AI Agent framework.

go-kratos
โญ 825 Go ๐Ÿ‘ค go-kratos Organization ๐Ÿ• Updated 2026-11-17 ๐Ÿ“… Created 2025-09-15
159
shuxiachai/academic-commercialization-agent

An AI multi-agent tool that turns research papers into cited commercialization and technology-transfer assessments covering TRL, the patent landscape, markets, and risks. Built with CrewAI + FastAPI, with a reproducible benchmark.

shuxiachai
โญ 819 Python ๐Ÿ‘ค shuxiachai User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-06-25
160
dragon1086/prism-insight

AI-based stock analysis and trading system

dragon1086
โญ 812 Python ๐Ÿ‘ค dragon1086 User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2025-08-15
161
hello-diana/MASCOT

EMNLP 2026 Main Conference Paper: MASCOT: Towards Multi-Agent Socio-Collaborative Companion Systems (https://aclanthology.org/2026.emnlp-main.878/)

hello-diana
โญ 805 Python ๐Ÿ‘ค hello-diana User ๐Ÿ• Updated 2026-08-24 ๐Ÿ“… Created 2026-02-03
162
Abilityai/trinity

Self-hosted AI Agents Platform for AI Native companies. Claude Code, Codex, Gemini, OpenCode agents. Apache 2.0.

Abilityai
โญ 792 Python ๐Ÿ‘ค Abilityai Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2025-12-10
163
thu-nics/C2C

[ICLR'26] The official code implementation for "Cache-to-Cache: Direct Semantic Communication Between Large Language Models"

thu-nics
โญ 783 Python ๐Ÿ‘ค thu-nics Organization ๐Ÿ• Updated 2026-10-28 ๐Ÿ“… Created 2025-10-03
164
dapr/dapr-agents

Build durable, autonomous, resilient, and observable AI agents with built-in workflow orchestration, security, statefulness, and telemetry.

dapr
โญ 778 Python ๐Ÿ‘ค dapr Organization ๐Ÿ• Updated 2026-11-12 ๐Ÿ“… Created 2025-01-02
165
useLexora/Lexora

A self-evolved, sovereign desktop AI agent built for real-world action โ€” beyond model wrappers and coding copilots. / A desktop AI agent that self-evolves through real-world practice.

useLexora
โญ 776 TypeScript ๐Ÿ‘ค useLexora Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-03-30
166
codefuse-ai/CodeFuse-muAgent

An Innovative Agent Framework Driven by KG Engine

codefuse-ai
โญ 776 Python ๐Ÿ‘ค codefuse-ai Organization ๐Ÿ• Updated 2025-01-15 ๐Ÿ“… Created 2024-04-21
167
divar-ir/ai-doc-gen

AI-powered multi-agent system that automatically analyzes codebases and generates comprehensive documentation. Features GitLab integration, concurrent processing, and multiple LLM support for better code understanding and developer onboarding.

divar-ir
โญ 772 Python ๐Ÿ‘ค divar-ir Organization ๐Ÿ• Updated 2026-07-21 ๐Ÿ“… Created 2025-07-19
168
Ar9av/PaperOrchestra

An automated AI research-paper writer based off Google's PaperOrchestra paper's implementation through a skills - benchmark + autoraters using any coding agent (Claude Code, Cursor, Antigravity, Cline, Aider). No API keys, no LLM SDKs.

Ar9av
โญ 767 Python ๐Ÿ‘ค Ar9av User ๐Ÿ• Updated 2026-11-04 ๐Ÿ“… Created 2026-04-09
169
ruvnet/metaharness

๐Ÿ› ๏ธ The meta-harness for AI agents โ€” scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).

ruvnet
โญ 759 TypeScript ๐Ÿ‘ค ruvnet User ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-06-13
170
joelhooks/swarm-tools

๐Ÿ Multi-agent swarm coordination for OpenCode with learning capabilities, agent issue tracking, and management

joelhooks
โญ 754 TypeScript ๐Ÿ‘ค joelhooks User ๐Ÿ• Updated 2026-07-30 ๐Ÿ“… Created 2025-12-08
171
oil-oil/wolfcha

AI Werewolf game. You take one seat, and LLM players fill the rest. AI Werewolf.

oil-oil
โญ 752 TypeScript ๐Ÿ‘ค oil-oil User ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-01-07
172
shannhk/hermes-agent-control-room

Control Room-first template for managing Hermes agents from one VPS agent to specialist teams and orchestrated workflows

shannhk
โญ 740 Shell ๐Ÿ‘ค shannhk User ๐Ÿ• Updated 2026-05-16 ๐Ÿ“… Created 2026-05-15
173
FuRongJun-1999/dsh-memory

Exploring white-box AGI architectures: metacognition (self-awareness loop), continual learning (knowledge flywheel), world model (conditional space + semantic spatiotemporal graph), self-improvement (bootstrap discipline), zero-LLM white-box pipeline, and auditable trust guardrails.

FuRongJun-1999
โญ 734 Python ๐Ÿ‘ค FuRongJun-1999 User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-08-14
174
databufflabs/databuff

DataBuff is an AI-native APM built on OpenTelemetry, with multi-agent troubleshooting out of the box.

databufflabs
โญ 729 Java ๐Ÿ‘ค databufflabs User ๐Ÿ• Updated 2026-10-06 ๐Ÿ“… Created 2026-06-18
175
Nanako0129/pilotfish

Multi-model orchestration layer for Claude Code โ€” the frontier model plans, cheaper models execute, verification guards quality. One-prompt install.

Nanako0129
โญ 718 Python ๐Ÿ‘ค Nanako0129 User ๐Ÿ• Updated 2026-10-09 ๐Ÿ“… Created 2026-07-08
176
swarmclawai/swarmclaw

Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude, GPT, Gemini, OpenRouter, Ollama). A practical Claude Code and LangChain alternative.

swarmclawai
โญ 710 TypeScript ๐Ÿ‘ค swarmclawai Organization ๐Ÿ• Updated 2026-06-30 ๐Ÿ“… Created 2026-02-18
177
BruceLanLan/augur

๐Ÿฆ‰ Augur โ€” A local-first investment research memory system: independent analyses by 18 investor personas + weighted consensus, with time-aware evidence and reproducible runs. CLI / Dashboard / MCP. A local-first research memory system with 18 investor personas.

BruceLanLan
โญ 708 Python ๐Ÿ‘ค BruceLanLan User ๐Ÿ• Updated 2026-11-16 ๐Ÿ“… Created 2026-04-07
178
framerslab/agentos

TypeScript AI agent framework: cognitive memory, dynamic personalities, emergent behaviors, and self-building designs

framerslab
โญ 691 TypeScript ๐Ÿ‘ค framerslab Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2025-10-28
179
WenyuChiou/ai-research-skills

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.

WenyuChiou
โญ 687 Python ๐Ÿ‘ค WenyuChiou User ๐Ÿ• Updated 2026-11-18 ๐Ÿ“… Created 2026-04-25
180
facebookresearch/BenchMARL

BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.

facebookresearch
โญ 687 Python ๐Ÿ‘ค facebookresearch Organization ๐Ÿ• Updated 2026-02-07 ๐Ÿ“… Created 2023-08-22
181
alexsergivan/kwant

Your own team of AI bots in one self-hosted binary: spaces, every account you have, handoffs, approvals and routines. Open-source, self-hosted alternative to Grok Bot, Claude Duet and OpenAI dots. Rust + React.

alexsergivan
โญ 685 Rust ๐Ÿ‘ค alexsergivan User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-10-22
182
AgentTeam-TaichuAI/ScienceClaw

ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stronger security, better transparency, and a more user-friendly experience.

AgentTeam-TaichuAI
โญ 683 Python ๐Ÿ‘ค AgentTeam-TaichuAI User ๐Ÿ• Updated 2026-05-09 ๐Ÿ“… Created 2026-03-13
183
redai-studio/Relax

An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

redai-studio
โญ 678 Python ๐Ÿ‘ค redai-studio Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-04-13
184
mario-andreschak/FLUJO

Multi-Agent + Automation Harness: Graph-based Workflows, MCP, Self-Improving Agents. Next.js + React

mario-andreschak
โญ 675 TypeScript ๐Ÿ‘ค mario-andreschak User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2025-02-26
185
agentscope-ai/agentscope-studio

A development-oriented visualization toolkit

agentscope-ai
โญ 674 TypeScript ๐Ÿ‘ค agentscope-ai Organization ๐Ÿ• Updated 2026-09-02 ๐Ÿ“… Created 2025-07-01
186
JacopoPan/aerial-autonomy-stack

An open harness to simulate and deploy PX4/ArduPilot/Betaflight perception-based drone swarms with ROS2, YOLO, NVIDIA Jetson

JacopoPan
โญ 666 C++ ๐Ÿ‘ค JacopoPan User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2025-06-20
187
aannoo/hcom

Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Cursor CLI, OpenCode, Kilo, Pi, Kimi

aannoo
โญ 665 Rust ๐Ÿ‘ค aannoo User ๐Ÿ• Updated 2026-10-21 ๐Ÿ“… Created 2025-07-21
188
wanghao-SunSky/cs329z-chinese

Stanford CS329Z Engineering AI Agents Chinese tutorial: an AI agent course for Python developers, with 19 lectures and 4 hands-on projects, covering LLMs, RAG, tool calling, memory, multi-agent systems, evaluation, and safety. Complete Markdown, online and offline HTML. Chinese course notes.

wanghao-SunSky
โญ 658 HTML ๐Ÿ‘ค wanghao-SunSky User ๐Ÿ• Updated 2026-11-06 ๐Ÿ“… Created 2026-10-28
189
lofcz/LLMTornado

The .NET library to build AI agents with 30+ built-in connectors.

lofcz
โญ 656 C# ๐Ÿ‘ค lofcz User ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2023-10-08
190
EvovexAI/EvoFlow

An evolving workflow ยท Continuously iterated and self-evolving, powered by AI employees in EvoFlowโ€™s R&D department ยท AI agent employees. Official website: www.evovexai.com

EvovexAI
โญ 646 TypeScript ๐Ÿ‘ค EvovexAI User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-05-11
191
xavierpuigf/virtualhome

API to run VirtualHome, a Multi-Agent Household Simulator

xavierpuigf
โญ 646 Python ๐Ÿ‘ค xavierpuigf User ๐Ÿ• Updated 2026-05-20 ๐Ÿ“… Created 2019-03-25
192
Arvincreator/project-golem

OS-level autonomous AI agent with long-term memory, multi-agent coordination, Titan Chronos scheduler & Moltbot Social Core

Arvincreator
โญ 642 JavaScript ๐Ÿ‘ค Arvincreator User ๐Ÿ• Updated 2026-06-22 ๐Ÿ“… Created 2026-01-30
193
jzjzzzzzzz/agent-me

Distill your knowledge, memories, and decisions into an open-source, inspectable AI Agent Twin.

jzjzzzzzzz
โญ 631 Python ๐Ÿ‘ค jzjzzzzzzz User ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-08-27
194
proroklab/VectorizedMultiAgentSimulator

VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.

proroklab
โญ 631 Python ๐Ÿ‘ค proroklab Organization ๐Ÿ• Updated 2026-05-19 ๐Ÿ“… Created 2022-05-12
โญ 627 TypeScript ๐Ÿ‘ค emo-xiaoyu User ๐Ÿ• Updated 2026-11-06 ๐Ÿ“… Created 2026-09-07
196
pardnchiu/Agenvoy

A local AI agent harness in Go that runs 24/7 with auto-built tools, MCP, and Ollama

pardnchiu
โญ 627 Go ๐Ÿ‘ค pardnchiu User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-02-05
197
koulanurag/ma-gym

A collection of multi agent environments based on OpenAI gym.

koulanurag
โญ 625 Python ๐Ÿ‘ค koulanurag User ๐Ÿ• Updated 2024-07-07 ๐Ÿ“… Created 2019-06-10
198
agentpit-io/hunter-community

HunterCode ยท Community Edition ยท An open-source, local alternative to Tencent WorkBuddy Finance Edition ยท Multi-agent investment research terminal for A-shares/Hong Kong stocks/U.S. stocks ยท Inference runs on your machine ยท Your positions never leave your hard drive ยท BYOK ยท Apache 2.0 ยท Self-hosted with Docker Compose

agentpit-io
โญ 619 Python ๐Ÿ‘ค agentpit-io Organization ๐Ÿ• Updated 2026-11-16 ๐Ÿ“… Created 2026-08-10
199
Enderfga/claw-orchestrator

Run Claude Code, Codex, Antigravity, Grok Build, and OpenCode behind a single runtime, and count a run as complete only when the checks it didnโ€™t write pass. Cross-engine fan-out, councils, session handoff, spend caps, MCP server, ACP agent.

Enderfga
โญ 618 TypeScript ๐Ÿ‘ค Enderfga User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-01-30
200
qybaihe/mu

mu (ฮผ): most of what a coding agent decides isnโ€™t code. mu hands 40 kinds of yes/no decisions to a small model: fewer wasted tokens, fewer approvals on autopilot, fewer runs that stop halfway. Built on pi.

qybaihe
โญ 615 TypeScript ๐Ÿ‘ค qybaihe User ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2026-09-22