OpenManus

Active
GitHub Python MIT

Description

OpenManus is an open-source AI Agent framework from the MetaGPT team, delivering Manus-like autonomous task execution without any invite code. Supports MCP tool calls and multi-agent flow.

Key Features

  • Autonomous task execution — Agents plan and execute complex tasks end-to-end without step-by-step human input
  • MCP tool integration — Connect external tools and services via Model Context Protocol
  • Multi-agent collaboration — Flow mode coordinates multiple agents working together on shared workflows
  • Data analysis agent — Built-in DataAnalysis Agent with data visualization and chart generation

Use Cases

💡 Automate daily office tasks such as document organization, data analysis, and report generation
💡 Build RAG-enhanced knowledge Q&A bots that answer domain-specific questions from your knowledge base
💡 Extend agent capabilities with MCP tools for browser automation, code execution, and other advanced workflows

Strengths & Limitations

Strengths

  • Actively maintained, recent updates
  • High community interest (58.2k stars)
  • Permissive open-source license (MIT)
  • Responsive to issues, low backlog

Quick Start

# Clone repo and install dependencies
git clone https://github.com/FoundationAgents/OpenManus.git
cd OpenManus && uv venv --python 3.12 && source .venv/bin/activate
uv pip install -r requirements.txt

# Configure your LLM API key
cp config/config.example.toml config/config.toml

# One-liner start
python main.py

Related Projects

MetaGPT

70.2k · Python
Stale B

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.

multi-agentframeworkpython +2
  • · 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

LazyLLM

3.9k · Python
Active A+

LazyLLM is a lightweight multi-agent LLM application framework offering the easiest way to build multi-agent LLM apps, with built-in RAG, knowledge graph, fine-tuning, and integration with LangChain and LlamaIndex ecosystems.

multi-agentframeworkrag +3
  • · Low-code multi-agent application assembly with built-in data flow and functional modules like Lego blocks
  • · One-click deployment with lightweight gateway for POC and Kubernetes packaging for production
  • · Cross-platform compatibility across bare-metal, Slurm clusters, and public clouds without code changes

GenAI Agents

24.1k · Jupyter Notebook
Active A+

GenAI Agents is a comprehensive collection of 50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems.

tutorialmulti-agentconversational-ai +1
  • · 50+ runnable tutorials — complete tech stack from simple chatbots to complex multi-agent systems
  • · Multi-agent system implementations — full code examples for agent collaboration, task decomposition
  • · RAG technique integration — demonstrates multiple RAG application patterns in agents

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)

Related Articles