MetaGPT

Stale
GitHub Python MIT

Description

The Multi-Agent Framework for building the first AI Software Company, enabling natural language programming with multi-role collaboration for automated requirement analysis, design, coding, and testing.

Key Features

  • Multi-role collaboration - Built-in product manager, architect, engineer roles simulating a full software company SOP pipeline
  • Natural language programming - Input a one-line requirement to auto-generate user stories, competitive analysis, API design, and complete code
  • Data Interpreter - Dynamic code generation and data analysis for CSV processing, visualization, and exploratory tasks
  • AFlow workflow engine - Automated agentic workflow generation, backed by ICLR 2025 Oral paper
  • SPO/AOT optimization - Self-play optimization and tree-of-thought search reasoning for improved agent decision-making
  • Extensible role system - Custom agent roles and tools for flexible multi-agent application development

Use Cases

💡 Generate complete software projects from a product requirement, including frontend, backend, and documentation
💡 Automate data analysis workflows by writing Python scripts for cleaning, transformation, and visualization
💡 Build multi-agent collaboration systems for automated research and report generation
💡 Demonstrate full software development lifecycle from requirement analysis to code delivery in educational settings

Strengths & Limitations

Strengths

  • High community interest (70.2k stars)
  • Permissive open-source license (MIT)
  • Established track record (3 years in production)
  • Responsive to issues, low backlog

⚠️ Limitations

  • No updates in over 7 months

Quick Start

# Install MetaGPT
pip install --upgrade metagpt

# Initialize config (creates ~/.metagpt/config2.yaml)
metagpt --init-config

# Generate a complete project from a requirement
metagpt "Create a 2048 game"

Related Projects

Ouroboros

5.8k · Python
Active A

Ouroboros is a spec-driven multi-agent framework that shifts from traditional prompting to specification-driven development, supporting multi-agent collaboration, MCP tool integration, and automated workflow orchestration for building high-quality agent systems.

multi-agentframeworkagent +4
  • · Spec-first workflow: Socratic interview → immutable seed spec → execution → evaluation
  • · Multi-runtime adapter supporting Claude Code, Codex CLI, OpenCode, Hermes, Gemini, Kiro, Copilot
  • · Three-layer architecture: Kernel (contract engine), Plugins (domain workflows), Shell (TUI cockpit)

DeepResearchAgent

3.5k · Python
Stale B

DeepResearchAgent is a hierarchical multi-agent system designed for deep research tasks and general-purpose problem solving, using a top-level planning agent to coordinate specialized sub-agents for automated task decomposition and efficient cross-domain execution.

multi-agentframeworkpython +3
  • · Hierarchical multi-agent system with top-level planning agent coordinating specialized sub-agents
  • · RSPL protocol layer modeling prompts, agents, tools, environments, and memory as versioned resources
  • · SEPL self-evolution protocol for proposing, assessing, and committing improvements with rollback support

AG2

4.9k · Python
Active A+

AG2 (formerly AutoGen) is an open-source AgentOS providing a multi-agent conversation framework with flexible agent orchestration, tool integration, and distributed collaboration for building complex multi-agent systems.

multi-agentframeworkagent +3
  • · Multi-agent conversation framework with flexible orchestration patterns including swarms, group chats, and nested chats
  • · Support for multiple LLM providers with configurable API keys and model selection
  • · Human-in-the-loop workflows enabling human oversight and input in agent conversations

Related Articles