MassGen: Multi-Agent Scaling System for GenAI#
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
MassGen is a cutting-edge multi-agent framework that coordinates AI agents through redundancy and iterative refinement. Agents tackle the full problem, observe and build on each other’s work across cycles of refinement and restarts, then vote — and the best collectively validated answer wins. This lays the groundwork for principled multi-agent scaling and self-improvement.
See visual comparisons between MassGen and single-agent solutions, highlighting how MassGen unifies different agentic approaches for better outcomes.
Use MassGen from Claude Code, Codex, Copilot, Cursor, and other AI coding agents.
How Does MassGen Compare?#
MassGen vs LLM Council: While LLM Council follows a fixed 3-stage pipeline, MassGen agents autonomously decide to contribute new answers or vote for others, reaching consensus organically. Plus, MassGen agents can use tools, execute code, and read/write files in your codebase — backed by active development with regular releases. See full comparison →
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
Rich terminal UI with real-time streaming, multi-turn conversations, and YAML configuration.
pip install uv # if needed
uv venv && source .venv/bin/activate
uv pip install massgen
uv run massgen --web # Open http://localhost:8000
Browser-based UI with real-time agent streaming, vote visualization, and workspace browsing.
from dotenv import load_dotenv
load_dotenv() # Load OPENROUTER_API_KEY from .env
import litellm
from massgen import register_with_litellm
register_with_litellm()
response = litellm.completion(
model="massgen/build",
messages=[{"role": "user", "content": "Your question"}],
optional_params={"models": ["openrouter/openai/gpt-5", "openrouter/anthropic/claude-sonnet-4.5"]}
)
print(response.choices[0].message.content)
Standard OpenAI-compatible interface for seamless integration with existing applications.
Video Tutorials#
Learn how to install, configure, and run your first multi-agent collaboration with MassGen.
Explore how to build custom agents and tools with MassGen.
Key Features#
Use Claude, Gemini, GPT, Grok together - each agent can use a different model.
Multiple agents work simultaneously with voting and consensus detection.
Model Context Protocol for web search, code execution, file operations, and custom tools.
Full async Python API and LiteLLM integration for seamless application embedding.
Real-time terminal display showing agents’ working processes and coordination.
Interactive conversations with context preservation across turns.
Integrate external frameworks (AG2, LangGraph, AgentScope, OpenAI, SmolAgent) as tools.
Work directly with your codebase using context paths with granular read/write permissions.
Recent Releases#
v0.1.83 (May 1, 2026) - In-Session Standalone Checkpoint MCP Integration
The standalone checkpoint MCP server can now be exposed inside a normal MassGen run via a new coordination.standalone_checkpoint config block, giving single-agent sessions access to the richer init + checkpoint tools backed by their own reviewer team. Enhanced checkpoint tool card visualization separates primary operations from system tasks.
v0.1.82 (April 29, 2026) - TUI Copy Mode & Checkpoint Quality Improvements
New Ctrl+Shift+S copy mode toggle releases terminal mouse tracking so users can drag-select text natively. Checkpoint standalone improvements: optional workspace context for reviewer agents, enhanced plan quality criteria with selective branch depth scoring, and single-checkpoint agent recovery guidance.
v0.1.81 (April 27, 2026) - Multi-Region Circuit Breaker Failover (Phase 6)
LLM circuit breaker can now fail over to backup regions when the primary trips OPEN, with automatic recovery when the primary returns to healthy. Builds on Phase 4 (distributed store) and Phase 5 (adaptive thresholds).
Supported Models#
Claude (Anthropic) · Gemini (Google) · GPT (OpenAI) · Grok (xAI) · Azure OpenAI · Groq · Together · LM Studio · and more…
