=================================================
MassGen: Multi-Agent Scaling System for GenAI
=================================================
.. raw:: html
.. raw:: html
|
.. raw:: html
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 โ and the best collectively validated answer wins. This lays the groundwork for principled multi-agent scaling and self-improvement.
.. raw:: html
See visual comparisons between MassGen and single-agent solutions, highlighting how MassGen unifies different agentic approaches for better outcomes.
.. raw:: html
Use MassGen from Claude Code, Codex, Copilot, Cursor, and other AI coding agents.
.. note::
**For AI agents and crawlers:** This site publishes a curated `llms.txt `_ index following the `llmstxt.org spec `_, plus a concatenated `llms-full.txt `_ dump of the user guide and reference docs.
How Does MassGen Compare?
-------------------------
MassGen sits in a different design space than typical multi-agent frameworks. The core differentiator across the board is *parallel attempts with voting and consensus* โ agents tackle the same task in parallel, observe each other, and converge on a winner โ backed by tools, code execution, filesystem integration, and active development.
- :doc:`MassGen vs LLM Council ` โ dynamic voting / consensus vs a fixed 3-stage pipeline (responses โ ranking โ chairman synthesis).
- :doc:`MassGen vs CrewAI ` โ parallel refinement on one task vs role-based decomposition into sub-tasks.
- :doc:`MassGen vs LangGraph ` โ a pre-built parallel + voting protocol vs a low-level graph runtime you author yourself.
- :doc:`MassGen vs AutoGen / AG2 ` โ parallel attempts with collective validation vs conversation-based multi-agent message passing.
Quick Start
-----------
.. tabs::
.. tab:: CLI
.. code-block:: bash
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.
.. tab:: WebUI
.. code-block:: bash
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.
.. tab:: LiteLLM
.. code-block:: python
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.
:doc:`quickstart/installation` ยท :doc:`quickstart/running-massgen` ยท :doc:`quickstart/configuration`
Video Tutorials
---------------
.. raw:: html
Learn how to install, configure, and run your first multi-agent collaboration with MassGen.
.. raw:: html
Explore how to build custom agents and tools with MassGen.
Key Features
------------
.. grid:: 2
:gutter: 3
.. grid-item-card:: ๐ค Cross-Model Synergy
Use Claude, Gemini, GPT, Grok together - each agent can use a different model.
.. grid-item-card:: โก Parallel Coordination
Multiple agents work simultaneously with voting and consensus detection.
.. grid-item-card:: ๐ ๏ธ Tools & MCP
Model Context Protocol for web search, code execution, file operations, and custom tools.
.. grid-item-card:: ๐ Python & LiteLLM
Full async Python API and LiteLLM integration for seamless application embedding.
.. grid-item-card:: ๐ Live Visualization
Real-time terminal display showing agents' working processes and coordination.
.. grid-item-card:: ๐ฌ Multi-Turn Sessions
Interactive conversations with context preservation across turns.
.. grid-item-card:: ๐ Framework Interoperability
Integrate external frameworks (AG2, LangGraph, AgentScope, OpenAI, SmolAgent) as tools.
.. grid-item-card:: ๐ Project Integration
Work directly with your codebase using context paths with granular read/write permissions.
Recent Releases
---------------
**v0.1.92 (June 1, 2026)** - Orchestrator Collaborator Refactor & Parallel Search MCP
Refactors the monolithic orchestrator into 49 lazy collaborators with stable delegator call sites, splits focused Textual display helpers into sibling modules, adds characterization coverage for extraction seams, and introduces a Parallel Web Search MCP registry entry plus runnable example config.
**v0.1.91 (May 27, 2026)** - Config Reliability & Hook Safety
Hardens release-critical YAML configuration paths with centralized coordination, timeout, and orchestrator runtime parsing; strict unknown-key validation for typo detection; checklist runtime control wiring; and safer Gemini/Codex native hook path permission precedence.
**v0.1.90 (May 25, 2026)** - Discriminative Criteria Refinements & Checklist Calibration
Improves checklist-gated refinement quality with discriminative-power pruning, per-criterion feedback carried into the next round, position-bias counterbalancing, deterministic tie-breaking, a unified checklist gate on a single 0-10 scale, shared score parsing utilities, and fast-iteration config updates.
**v0.1.89 (May 22, 2026)** - Antigravity CLI Full Integration & Hardening
Completes the follow-up Antigravity integration pass with workflow-mode parity, early auth and binary health checks, reliable workspace writes via ``--add-dir``, workspace-root ``.antigravitycli/`` anchoring, standalone ``hooks.json`` support with ``enableJsonHooks``, and prompt guardrails that hide subagent affordances when subagents are disabled.
**v0.1.88 (May 20, 2026)** - Antigravity CLI Backend
New ``antigravity_cli`` backend wraps Google's ``agy`` binary as a MassGen backend, with workspace-local ``.antigravity/`` config isolation, Antigravity MCP config translation, native hook adapter support, and runnable configs for single-agent Antigravity and mixed Gemini API + Antigravity fast-iteration runs.
**v0.1.87 (May 15, 2026)** - Documentation: Framework Comparisons & ``llms.txt``
Three new "MassGen vs ..." comparison pages (CrewAI, LangGraph, AutoGen/AG2), a curated ``llms.txt`` index plus a full-corpus ``llms-full.txt`` dump for AI agents and crawlers (per `llmstxt.org `_ spec), and a one-line ``refine=False`` fix for the ``bootstrap_subagent`` discriminator.
**v0.1.86 (May 13, 2026)** - ``bootstrap_subagent`` Discriminator + Codex MCP Approval Fix
The critic-driven criteria path is now functional: ``orchestrator.coordination.criteria_mode: bootstrap_subagent`` runs an in-process LLM discriminator between rounds, merges proposed criteria into the accumulator, and augments the next round's checklist automatically. Codex MCP tool calls under ``codex exec`` now get the non-interactive approval bypasses needed for external workflow tools.
**v0.1.85 (May 11, 2026)** - Discriminative Criteria Emergence (``criteria_mode``)
New ``orchestrator.coordination.criteria_mode`` option lets evaluation criteria emerge from observed gaps across rounds instead of being pre-authored. The ``bootstrap_inline`` variant is fully functional on all backends with checklist tool support โ agents emit ``proposed_criteria`` alongside ``submit_checklist``, the accumulator dedupes/caps, and the next round's checklist is augmented automatically.
:doc:`Full changelog โ `
Supported Models
----------------
**Claude** (Anthropic) ยท **Gemini** (Google) ยท **GPT** (OpenAI) ยท **Grok** (xAI) ยท **Azure OpenAI** ยท **Groq** ยท **Together** ยท **LM Studio** ยท :doc:`and more... `
Documentation
-------------
.. grid:: 3
:gutter: 2
.. grid-item-card:: ๐ Getting Started
* :doc:`quickstart/installation`
* :doc:`quickstart/running-massgen`
* :doc:`quickstart/configuration`
.. grid-item-card:: ๐ User Guide
* :doc:`user_guide/concepts`
* :doc:`user_guide/skills`
* :doc:`user_guide/webui`
* :doc:`user_guide/tools/index`
* :doc:`user_guide/integration/index`
.. grid-item-card:: ๐ Reference
* :doc:`reference/cli`
* :doc:`reference/python_api`
* :doc:`reference/yaml_schema`
* :doc:`examples/basic_examples`
.. toctree::
:maxdepth: 2
:hidden:
:caption: Getting Started
quickstart/installation
quickstart/running-massgen
quickstart/configuration
.. toctree::
:maxdepth: 2
:hidden:
:caption: User Guide
user_guide/concepts
user_guide/skills
user_guide/task_planning
user_guide/backends
user_guide/webui
user_guide/tools/index
user_guide/files/index
user_guide/sessions/index
user_guide/integration/index
user_guide/advanced/index
user_guide/validating_configs
user_guide/logging
.. toctree::
:maxdepth: 2
:hidden:
:caption: Reference
reference/python_api
reference/cli
reference/yaml_schema
reference/mcp_server_registry
reference/configuration_examples
reference/timeouts
reference/supported_models
reference/comparisons
glossary
.. toctree::
:maxdepth: 2
:hidden:
:caption: Examples
examples/case_studies
examples/basic_examples
examples/advanced_patterns
examples/available_configs
.. toctree::
:maxdepth: 2
:hidden:
:caption: Development
development/contributing
development/writing_configs
development/architecture
development/roadmap
changelog
api/index