SaaSHub helps you find the best software and product alternatives Learn more →
Top 23 Python multi-agent Projects
-
deer-flow
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
Project mention: Running Gemma 4 26B at 5 tokens/SEC on a 13-year-old Xeon with no GPU | news.ycombinator.com | 2026-07-15 -
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
MetaGPT
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
-
CowAgent
Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-model, multi-channel. Lightweight, extensible, one-line install. (formerly chatgpt-on-wechat)
-
GitHub Link: https://github.com/agentscope-ai/agentscope Summary: Agentscope is an agent-oriented programming library that makes it easier to build LLM applications. It's designed to be "developer-centric" with features like asynchronous execution, parallel tool calls, and real-time steering. It offers a transparent approach where prompt engineering and API invocation are fully visible and controllable. Why it's important: Agentscope, along with its related libraries like agentscope-runtime and agentscope-studio, provides a comprehensive toolkit for not only developing but also deploying and visualizing agent-based applications.
-
adk-python
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Project mention: Building a Document-RAG Agent on GCP's Agent Development Kit (ADK) | dev.to | 2026-07-14Google's Agent Development Kit (ADK)
-
Now extend this pattern to something that should terrify you. HKUDS/Vibe-Trading is a GitHub repository with 24,000 stars, trending at +721 stars per day as of this writing. It is an autonomous trading agent powered by LLMs that executes trades on broker APIs -- including perpetual futures on platforms like Hyperliquid where leverage amplifies losses.
-
agent-framework
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
Project mention: What We Learned Scanning Microsoft's Public Agent Framework Repository | dev.to | 2026-06-13Clear Code Intelligence scanned a public Microsoft repository: microsoft/agent-framework.
-
PraisonAI
PraisonAI 🦞 — Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous self-improving agents that research, plan, code, and execute tasks. Deployed in 5 lines of code with built-in memory, RAG, and support for 100+ LLMs.
-
solace-agent-mesh
An event-driven framework designed to build and orchestrate multi-agent AI systems. It enables seamless integration of AI agents with real-world data sources and systems, facilitating complex, multi-step workflows.
Project mention: Ditch the Monolith: Build Scalable AI Teams with Solace Agent Mesh | dev.to | 2025-10-10View the Project on GitHub
-
AG2 (formerly AutoGen) changes that. It provides a shared runtime where specialized agents with defined roles, tools and conversation patterns can collaborate as one coordinated team across models and even frameworks.
-
rlcard
Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.
-
agentUniverse
agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent applications.
-
gym-pybullet-drones
PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
-
-
-
-
ChatArena
ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.
-
skrl
Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments
-
AgileRL
Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary hyperparameter optimization.
-
maro
Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.
-
-
ainativelang
AINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflows that need multiple steps, state and memory, tool use, repeatable execution, validation and control, and lower dependence on long prompt loops. AINL is a compact, graph-canonical, AI-native programming system for (READ: README)
And to consider AI agents are still mostly entirely limited to generating code in programming languages designed to be written, tested and debugged by humans.
Here are two experimental exceptions:
https://github.com/vercel-labs/zerolang
https://github.com/sbhooley/ainativelang
-
TL;DR: ClawMaster is an open-source OpenClaw companion with a setup wizard, channel and model management, cost observability, Skill hosting, and PowerMem-backed memory. Install with two commands, then open http://localhost:16223.
Python multi-agent discussion
Python multi-agent related posts
-
bernstein 3.x recap: deterministic replay, evidence bundles, tournament runs, and a run you can walk away from
-
The (no longer) missing multi-agent pattern: triggering dynamic workflows from an agent
-
Why Is SoloEngine the Ideal Implementation of Loop Engineering?
-
Vibe-Trading: Your Personal Trading Agent
-
SoloEngine: The Best Practice for Loop Engineering, Building Your First Autonomous AI Loop from Scratch
-
What We Learned Scanning Microsoft's Public Agent Framework Repository
-
From MiMo Code to MiMo SoloEngine: Xiaomi's Dual-Agent Strategy
-
A note from our sponsor - SaaSHub
www.saashub.com | 21 Jul 2026
Index
What are some of the best open-source multi-agent projects in Python? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | deer-flow | 77,199 |
| 2 | MetaGPT | 69,384 |
| 3 | CowAgent | 46,024 |
| 4 | agentscope | 27,981 |
| 5 | adk-python | 20,645 |
| 6 | Vibe-Trading | 18,900 |
| 7 | agent-framework | 12,187 |
| 8 | PraisonAI | 8,451 |
| 9 | solace-agent-mesh | 4,964 |
| 10 | ag2 | 4,783 |
| 11 | rlcard | 3,508 |
| 12 | agentUniverse | 2,308 |
| 13 | gym-pybullet-drones | 2,082 |
| 14 | on-policy | 2,060 |
| 15 | MAgent | 1,761 |
| 16 | concordia | 1,564 |
| 17 | ChatArena | 1,549 |
| 18 | skrl | 1,081 |
| 19 | AgileRL | 935 |
| 20 | maro | 913 |
| 21 | neuro-san-studio | 828 |
| 22 | ainativelang | 822 |
| 23 | powermem | 757 |