MassGen: Multi-Agent Scaling System for GenAI

MassGen: Multi-Agent Scaling System for GenAI#

MassGen Logo MassGen Logo

PyPI GitHub Stars Python 3.11+ License

Follow on X Follow on LinkedIn Join our Discord


MassGen Demo - Multi-agent collaboration in action MassGen Demo - Multi-agent collaboration in action

What is MassGen?#

MassGen is a cutting-edge multi-agent system that leverages the power of collaborative AI to solve complex tasks. It assigns a task to multiple AI agents who work in parallel, observe each other’s progress, and refine their approaches to converge on the best solution to deliver a comprehensive and high-quality result.

How It Works:

  • Work in Parallel - Multiple agents tackle the problem simultaneously, each bringing unique capabilities

  • See Recent Answers - At each step, agents view the most recent answers from other agents

  • Decide Next Action - Each agent chooses to provide a new answer or vote for an existing answer

  • Share Workspaces - When agents provide answers, their workspace is captured so others can review their work

  • Natural Consensus - Coordination continues until all agents vote, then the agent with most votes presents the final answer

Think of it as a “parallel study group” for AI - inspired by advanced systems like xAI’s Grok Heavy and Google DeepMind’s Gemini Deep Think. Agents learn from each other to produce better results than any single agent could achieve alone.

Quick Start#

pip install uv        # if needed
uv venv && source .venv/bin/activate
uv pip install massgen
uv run massgen        # Setup wizard, then ask your first question

Installation · Running MassGen · Configuration

Key Features#

🤝 Cross-Model Synergy

Use Claude, Gemini, GPT, Grok together - each agent can use a different model.

⚡ Parallel Coordination

Multiple agents work simultaneously with voting and consensus detection.

🛠️ Tools & MCP

Model Context Protocol for web search, code execution, file operations, and custom tools.

🐍 Python & LiteLLM

Full async Python API and LiteLLM integration for seamless application embedding.

📊 Live Visualization

Real-time terminal display showing agents’ working processes and coordination.

💬 Multi-Turn Sessions

Interactive conversations with context preservation across turns.

🔗 Framework Interoperability

Integrate external frameworks (AG2, LangGraph, AgentScope, OpenAI, SmolAgent) as tools.

📁 Project Integration

Work directly with your codebase using context paths with granular read/write permissions.

Recent Releases#

v0.1.19 (December 2, 2025) - LiteLLM Provider & Claude Strict Tool Use

LiteLLM custom provider integration with programmatic API (run(), build_config()). Claude strict tool use with structured outputs support via enable_strict_tool_use and output_schema. Gemini exponential backoff for rate limit resilience.

v0.1.18 (November 28, 2025) - Agent Communication & Claude Advanced Tooling

Agent-to-agent and human broadcast communication via ask_others() tool with three modes (disabled, agents-only, human-only). Claude programmatic tool calling from code execution via enable_programmatic_flow flag. Claude tool search for deferred tool discovery via enable_tool_search.

v0.1.17 (November 26, 2025) - Textual Terminal Display

Interactive terminal UI using the Textual library with dark/light theme support. Multi-panel layout with dedicated views for each agent and orchestrator status. Real-time streaming with syntax highlighting and emoji fallback.

Full changelog →

Supported Models#

Claude (Anthropic) · Gemini (Google) · GPT (OpenAI) · Grok (xAI) · Azure OpenAI · Groq · Together · LM Studio · and more…

Documentation#