MassGen

MassGen

MassGen is an open-source multi-agent collaboration system that runs in the terminal, automatically coordinating cutting-edge models and agents to work together, reason, and generate high-quality results.

MCPDevOpen sourcemulti-agentcollaborationAI
Type
MCP
Transport
stdio
Open source
Yes
GitHub Stars
★ 1.1k
Source
mcp-github

Overview

MassGen is an advanced multi-agent framework that coordinates AI agents to solve complex tasks through redundancy and iterative improvement. Each agent processes the entire problem, observes, critiques, and improves based on each other's work. When agents believe they have a sufficiently strong answer, they vote, and the best answer is collectively validated. This approach of parallel refinement and collective verification lays the foundation for multi-agent scaling, enabling the system to continuously improve its output by leveraging diverse agent perspectives and ensuring quality through consensus. It can be installed via the npx command and integrated with over 40 agents, including Claude Code, Cursor, Copilot, and more.

Capabilities

  • Multi-agent collaboration
  • Parallel processing and iterative improvement
  • Intelligent sharing and consensus building
  • Real-time visualization
  • Support for multiple models and tools

Use cases

Automated handling of complex tasksMulti-agent collaboration to solve problemsImproving the quality of AI outputsEnhancing synergies between agents

Setup

Requires: API KeyPython 3.11+
npx skills add massgen/skills --all

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

How do I get started with MassGen?

After installation, add skills using the npx command and invoke them within supported agents.

Which models and tools does MassGen support?

Supports multiple models and tools; see the documentation for details.

Related skills