
MassGen
π MassGen: An Open-source Multi-Agent Scaling System Inspired by Grok Heavy and Gemini Deep Think. Join the discord channel: https://discord.com/invite/VVrT2rQaz5
Stars: 452

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. The system operates through an architecture designed for seamless multi-agent collaboration, with key features including cross-model/agent synergy, parallel processing, intelligence sharing, consensus building, and live visualization. Users can install the system, configure API settings, and run MassGen for various tasks such as question answering, creative writing, research, development & coding tasks, and web automation & browser tasks. The roadmap includes plans for advanced agent collaboration, expanded model, tool & agent integration, improved performance & scalability, enhanced developer experience, and a web interface.
README:
MassGen is a cutting-edge multi-agent system that leverages the power of collaborative AI to solve complex tasks.
Multi-agent scaling through intelligent collaboration in Grok Heavy style
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. The power of this "parallel study group" approach is exemplified by advanced systems like xAI's Grok Heavy and Google DeepMind's Gemini Deep Think.
This project started with the "threads of thought" and "iterative refinement" ideas presented in The Myth of Reasoning, and extends the classic "multi-agent conversation" idea in AG2. Here is a video recording of the background context introduction presented at the Berkeley Agentic AI Summit 2025.
- Recent Achievements
-
Key Future Enhancements
- Advanced Agent Collaboration
- Expanded Model, Tool & Agent Integrations
- Improved Performance & Scalability
- Enhanced Developer Experience
- Web Interface
- v0.0.24 Roadmap
Feature | Description |
---|---|
π€ Cross-Model/Agent Synergy | Harness strengths from diverse frontier model-powered agents |
β‘ Parallel Processing | Multiple agents tackle problems simultaneously |
π₯ Intelligence Sharing | Agents share and learn from each other's work |
π Consensus Building | Natural convergence through collaborative refinement |
π Live Visualization | See agents' working processes in real-time |
What's New in v0.0.23:
-
Backend Architecture Refactoring - Major consolidation with new
base_with_mcp.py
class reducing ~1,932 lines across backends -
Formatter Module - Extracted message and tool formatting logic into dedicated
massgen/formatter/
module - Massive Code Deduplication - Streamlined chat_completions.py, claude.py, and response.py for better maintainability
- Bug Fixes - Fixed coordination table escape handling on macOS and FastMCP integration
MassGen operates through an architecture designed for seamless multi-agent collaboration:
graph TB
O[π MassGen Orchestrator<br/>π Task Distribution & Coordination]
subgraph Collaborative Agents
A1[Agent 1<br/>ποΈ Anthropic/Claude + Tools]
A2[Agent 2<br/>π Google/Gemini + Tools]
A3[Agent 3<br/>π€ OpenAI/GPT + Tools]
A4[Agent 4<br/>β‘ xAI/Grok + Tools]
end
H[π Shared Collaboration Hub<br/>π‘ Real-time Notification & Consensus]
O --> A1 & A2 & A3 & A4
A1 & A2 & A3 & A4 <--> H
classDef orchestrator fill:#e1f5fe,stroke:#0288d1,stroke-width:3px
classDef agent fill:#f3e5f5,stroke:#7b1fa2,stroke-width:2px
classDef hub fill:#e8f5e8,stroke:#388e3c,stroke-width:2px
class O orchestrator
class A1,A2,A3,A4 agent
class H hub
The system's workflow is defined by the following key principles:
Parallel Processing - Multiple agents tackle the same task simultaneously, each leveraging their unique capabilities (different models, tools, and specialized approaches).
Real-time Collaboration - Agents continuously share their working summaries and insights through a notification system, allowing them to learn from each other's approaches and build upon collective knowledge.
Convergence Detection - The system intelligently monitors when agents have reached stability in their solutions and achieved consensus through natural collaboration rather than forced agreement.
Adaptive Coordination - Agents can restart and refine their work when they receive new insights from others, creating a dynamic and responsive problem-solving environment.
This collaborative approach ensures that the final output leverages collective intelligence from multiple AI systems, leading to more robust and well-rounded results than any single agent could achieve alone.
Core Installation (requires Python 3.11+):
git clone https://github.com/Leezekun/MassGen.git
cd MassGen
pip install uv
uv venv
Optional CLI Tools (for enhanced capabilities):
# Claude Code CLI - Advanced coding assistant
npm install -g @anthropic-ai/claude-code
# LM Studio - Local model inference
# For MacOS/Linux
sudo ~/.lmstudio/bin/lms bootstrap
# For Windows
cmd /c %USERPROFILE%/.lmstudio/bin/lms.exe bootstrap
Using the template file .env.example
to create a .env
file in the massgen
directory with your API keys. Note that only the API keys of the models used by your MassGen agent team is needed.
# Copy example configuration
cp .env.example .env
Useful links to get API keys:
The system currently supports multiple model providers with advanced capabilities:
API-based Models:
- Azure OpenAI (NEW in v0.0.10): GPT-4, GPT-4o, GPT-3.5-turbo, GPT-4.1, GPT-5-chat
- Cerebras AI: GPT-OSS-120B...
- Claude: Claude Haiku 3.5, Claude Sonnet 4, Claude Opus 4...
- Claude Code: Native Claude Code SDK with comprehensive dev tools
- Gemini: Gemini 2.5 Flash, Gemini 2.5 Pro...
- Grok: Grok-4, Grok-3, Grok-3-mini...
- OpenAI: GPT-5 series (GPT-5, GPT-5-mini, GPT-5-nano)...
- Together AI, Fireworks AI, Groq, Kimi/Moonshot, Nebius AI Studio, OpenRouter: LLaMA, Mistral, Qwen...
- Z AI: GLM-4.5
Local Model Support (NEW in v0.0.7):
-
LM Studio: Run open-weight models locally with automatic server management
- Automatic LM Studio CLI installation
- Auto-download and loading of models
- Zero-cost usage reporting
- Support for LLaMA, Mistral, Qwen and other open-weight models
More providers and local inference engines (vllm, sglang) are welcome to be added.
MassGen agents can leverage various tools to enhance their problem-solving capabilities. Both API-based and CLI-based backends support different tool capabilities.
Supported Built-in Tools by Backend:
Backend | Live Search | Code Execution | File Operations | MCP Support | Advanced Features |
---|---|---|---|---|---|
Azure OpenAI (NEW in v0.0.10) | β | β | β | β | Code interpreter, Azure deployment management |
Claude API | β | β | β | β | Web search, code interpreter, MCP integration |
Claude Code | β | β | β | β | Native Claude Code SDK, comprehensive dev tools, MCP integration |
Gemini API | β | β | β | β | Web search, code execution, MCP integration |
Grok API | β | β | β | β | Web search, MCP integration |
OpenAI API | β | β | β | β | Web search, code interpreter, MCP integration |
ZAI API | β | β | β | β | MCP integration |
Parameter | Description |
---|---|
--config |
Path to YAML configuration file with agent definitions, model parameters, backend parameters and UI settings |
--backend |
Backend type for quick setup without a config file (claude , claude_code , gemini , grok , openai , azure_openai , zai ). Optional for models with default backends. |
--model |
Model name for quick setup (e.g., gemini-2.5-flash , gpt-5-nano , ...). --config and --model are mutually exclusive - use one or the other. |
--system-message |
System prompt for the agent in quick setup mode. If --config is provided, --system-message is omitted. |
--no-display |
Disable real-time streaming UI coordination display (fallback to simple text output). |
--no-logs |
Disable real-time logging. |
--debug |
Enable debug mode with verbose logging (NEW in v0.0.13). Shows detailed orchestrator activities, agent messages, backend operations, and tool calls. Debug logs are saved to agent_outputs/log_{time}/massgen_debug.log . |
"<your question>" |
Optional single-question input; if omitted, MassGen enters interactive chat mode. |
Quick Start Commands:
# Quick test with any supported model - no configuration needed
uv run python -m massgen.cli --model claude-3-5-sonnet-latest "What is machine learning?"
uv run python -m massgen.cli --model gemini-2.5-flash "Explain quantum computing"
uv run python -m massgen.cli --model gpt-5-nano "Summarize the latest AI developments"
Configuration:
Use the agent
field to define a single agent with its backend and settings:
agent:
id: "<agent_name>"
backend:
type: "azure_openai" | "chatcompletion" | "claude" | "claude_code" | "gemini" | "grok" | "openai" | "zai" | "lmstudio" #Type of backend
model: "<model_name>" # Model name
api_key: "<optional_key>" # API key for backend. Uses env vars by default.
system_message: "..." # System Message for Single Agent
β See all single agent configs
Configuration:
Use the agents
field to define multiple agents, each with its own backend and config:
Quick Start Commands:
# Three powerful agents working together - Gemini, GPT-5, and Grok
uv run python -m massgen.cli \
--config massgen/configs/basic/multi/three_agents_default.yaml \
"Analyze the pros and cons of renewable energy"
This showcases MassGen's core strength:
- Gemini 2.5 Flash - Fast research with web search
- GPT-5 Nano - Advanced reasoning with code execution
- Grok-3 Mini - Real-time information and alternative perspectives
agents: # Multiple agents (alternative to 'agent')
- id: "<agent1 name>"
backend:
type: "azure_openai" | "chatcompletion" | "claude" | "claude_code" | "gemini" | "grok" | "openai" | "zai" | "lmstudio" #Type of backend
model: "<model_name>" # Model name
api_key: "<optional_key>" # API key for backend. Uses env vars by default.
system_message: "..." # System Message for Single Agent
- id: "..."
backend:
type: "..."
model: "..."
...
system_message: "..."
β Explore more multi-agent setups
The Model context protocol (MCP) standardises how applications expose tools and context to language models. From the official documentation:
MCP is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect your devices to various peripherals and accessories, MCP provides a standardized way to connect AI models to different data sources and tools.
MCP Configuration Parameters:
Parameter | Type | Required | Description |
---|---|---|---|
mcp_servers |
dict | Yes (for MCP) | Container for MCP server definitions |
ββ type
|
string | Yes | Transport: "stdio" or "streamable-http"
|
ββ command
|
string | stdio only | Command to run the MCP server |
ββ args
|
list | stdio only | Arguments for the command |
ββ url
|
string | http only | Server endpoint URL |
ββ env
|
dict | No | Environment variables to pass |
allowed_tools |
list | No | Whitelist specific tools (if omitted, all tools available) |
exclude_tools |
list | No | Blacklist dangerous/unwanted tools |
Quick Start Commands (Check backend MCP support here):
# Weather service with GPT-5
uv run python -m massgen.cli \
--config massgen/configs/tools/mcp/gpt5_mini_mcp_example.yaml \
"What's the weather forecast for San Francisco this week?"
# Multi-tool MCP with Gemini - Search + Weather + Filesystem
uv run python -m massgen.cli \
--config massgen/configs/tools/mcp/multimcp_gemini.yaml \
"Find the best restaurants in Paris and save the recommendations to a file"
Configuration:
agents:
# Basic MCP Configuration:
backend:
type: "openai" # Your backend choice
model: "gpt-5-mini" # Your model choice
# Add MCP servers here
mcp_servers:
weather: # Server name (you choose this)
type: "stdio" # Communication type
command: "npx" # Command to run
args: ["-y", "@modelcontextprotocol/server-weather"] # MCP server package
# That's it! The agent can now check weather.
# Multiple MCP Tools Example:
backend:
type: "gemini"
model: "gemini-2.5-flash"
mcp_servers:
# Web search
search:
type: "stdio"
command: "npx"
args: ["-y", "@modelcontextprotocol/server-brave-search"]
env:
BRAVE_API_KEY: "${BRAVE_API_KEY}" # Set in .env file
# HTTP-based MCP server (streamable-http transport)
custodm_api:
type: "streamable-http" # For HTTP/SSE servers
url: "http://localhost:8080/mcp/sse" # Server endpoint
# Tool configuration (MCP tools are auto-discovered)
allowed_tools: # Optional: whitelist specific tools
- "mcp__weather__get_current_weather"
- "mcp__test_server__mcp_echo"
- "mcp__test_server__add_numbers"
exclude_tools: # Optional: blacklist specific tools
- "mcp__test_server__current_time"
MassGen provides comprehensive file system support through multiple backends, enabling agents to read, write, and manipulate files in organized workspaces.
Filesystem Configuration Parameters:
Parameter | Type | Required | Description |
---|---|---|---|
cwd |
string | Yes (for file ops) | Working directory for file operations (agent-specific workspace) |
snapshot_storage |
string | Yes | Directory for workspace snapshots |
agent_temporary_workspace |
string | Yes | Parent directory for temporary workspaces |
Quick Start Commands:
# File operations with Claude Code
uv run python -m massgen.cli \
--config massgen/configs/tools/filesystem/claude_code_single.yaml \
"Create a Python web scraper and save results to CSV"
# Multi-agent file collaboration
uv run python -m massgen.cli \
--config massgen/configs/tools/filesystem/claude_code_context_sharing.yaml \
"Generate a comprehensive project report with charts and analysis"
Configuration:
# Basic Workspace Setup:
agents:
- id: "file-agent"
backend:
type: "claude_code" # Backend with file support
model: "claude-sonnet-4" # Your model choice
cwd: "workspace" # Isolated workspace for file operations
# Multi-Agent Workspace Isolation:
agents:
- id: "analyzer"
backend:
type: "claude_code"
cwd: "workspace1" # Agent-specific workspace
- id: "reviewer"
backend:
type: "gemini"
cwd: "workspace2" # Separate workspace
orchestrator:
snapshot_storage: "snapshots" # Shared snapshots directory
agent_temporary_workspace: "temp_workspaces" # Temporary workspace management
Available File Operations:
- Claude Code: Built-in tools (Read, Write, Edit, MultiEdit, Bash, Grep, Glob, LS, TodoWrite)
- Other Backends: Via MCP Filesystem Server
Workspace Management:
-
Isolated Workspaces: Each agent's
cwd
is fully isolated and writable - Snapshot Storage: Share workspace context between Claude Code agents
- Temporary Workspaces: Agents can access previous coordination results
β View more filesystem examples
Work directly with your existing projects! User Context Paths allow you to share specific directories and files with all agents while maintaining granular permission control. This enables secure multi-agent collaboration on your real codebases, documentation, and data.
Project Integration Parameters:
Parameter | Type | Required | Description |
---|---|---|---|
context_paths |
list | Yes (for project integration) | Shared directories/files for all agents |
ββ path
|
string | Yes | Absolute path to your project directory or file |
ββ permission
|
string | Yes | Access level: "read" or "write"
|
Quick Start Commands:
# Code analysis and security audit
uv run python -m massgen.cli \
--config massgen/configs/tools/filesystem/fs_permissions_test.yaml \
"Analyze all Python files in this project and create a comprehensive security audit report"
# Project modernization
uv run python -m massgen.cli \
--config massgen/configs/tools/filesystem/claude_code_context_sharing.yaml \
"Review this legacy codebase and create a modernization plan with updated dependencies"
Configuration:
# Basic Project Integration:
agents:
- id: "code-reviewer"
backend:
type: "claude_code"
cwd: "workspace" # Agent's isolated work area
orchestrator:
context_paths:
- path: "/home/user/my-project/src"
permission: "read" # Agents can analyze your code
- path: "/home/user/my-project/docs"
permission: "write" # Final agent can update docs
# Advanced: Multi-Agent Project Collaboration
agents:
- id: "analyzer"
backend:
type: "gemini"
cwd: "analysis_workspace"
- id: "implementer"
backend:
type: "claude_code"
cwd: "implementation_workspace"
orchestrator:
context_paths:
- path: "/home/user/legacy-app/src"
permission: "read" # Read existing codebase
- path: "/home/user/legacy-app/tests"
permission: "write" # Write new tests
- path: "/home/user/modernized-app"
permission: "write" # Create modernized version
This showcases project integration:
- Real Project Access - Work with your actual codebases, not copies
- Secure Permissions - Granular control over what agents can read/modify
- Multi-Agent Collaboration - Multiple agents safely work on the same project
- Context Agents (during coordination): Always READ-only access to protect your files
- Final Agent (final execution): Gets the configured permission (READ or write)
Use Cases:
- Code Review: Agents analyze your source code and suggest improvements
- Documentation: Agents read project docs to understand context and generate updates
- Data Processing: Agents access shared datasets and generate analysis reports
- Project Migration: Agents examine existing projects and create modernized versions
β Learn more about project integration
Security Considerations:
-
Agent ID Safety: Avoid using agent+incremental digits for IDs (e.g.,
agent1
,agent2
). This may cause ID exposure during voting - File Access Control: Restrict file access using MCP server configurations when needed
- Path Validation: All paths are resolved to absolute paths to prevent directory traversal attacks
Claude (Recursive MCP Execution - v0.0.20+)
# Claude with advanced tool chaining
uv run python -m massgen.cli \
--config massgen/configs/tools/mcp/claude_mcp_example.yaml \
"Research and compare weather in Beijing and Shanghai"
OpenAI (GPT-5 Series with MCP - v0.0.17+)
# GPT-5 with weather and external tools
uv run python -m massgen.cli \
--config massgen/configs/tools/mcp/gpt5_mini_mcp_example.yaml \
"What's the weather of Tokyo"
Gemini (Multi-Server MCP - v0.0.15+)
# Gemini with multiple MCP services
uv run python -m massgen.cli \
--config massgen/configs/tools/mcp/multimcp_gemini.yaml \
"Find accommodations in Paris with neighborhood analysis" # (requires BRAVE_API_KEY in .env)
Claude Code (Development Tools)
# Professional development environment
uv run python -m massgen.cli \
--backend claude_code \
--model sonnet \
"Create a Flask web app with authentication"
Local Models (LM Studio - v0.0.7+)
# Run open-source models locally
uv run python -m massgen.cli \
--config massgen/configs/providers/local/lmstudio.yaml \
"Explain machine learning concepts"
β Browse by provider | Browse by tools | Browse teams
Question Answering & Research:
# Complex research with multiple perspectives
uv run python -m massgen.cli \
--config massgen/configs/basic/multi/gemini_4o_claude.yaml \
"What's best to do in Stockholm in October 2025"
# Specific research requirements
uv run python -m massgen.cli \
--config massgen/configs/basic/multi/gemini_4o_claude.yaml \
"Give me all the talks on agent frameworks in Berkeley Agentic AI Summit 2025"
Creative Writing:
# Story generation with multiple creative agents
uv run python -m massgen.cli \
--config massgen/configs/basic/multi/gemini_4o_claude.yaml \
"Write a short story about a robot who discovers music"
Development & Coding:
# Full-stack development with file operations
uv run python -m massgen.cli \
--config massgen/configs/tools/filesystem/claude_code_single.yaml \
"Create a Flask web app with authentication"
Web Automation: (still in test)
# Browser automation with screenshots and reporting
uv run python -m massgen.cli \
--config massgen/configs/tools/code-execution/multi_agent_playwright_automation.yaml \
"Browse https://github.com/Leezekun/MassGen and suggest improvements. Include screenshots in a PDF"
# Data extraction and analysis
uv run python -m massgen.cli \
--config massgen/configs/tools/code-execution/multi_agent_playwright_automation.yaml \
"Navigate to https://news.ycombinator.com, extract the top 10 stories, and create a summary report"
β See detailed case studies with real session logs and outcomes
Multi-Turn Conversations:
# Start interactive chat (no initial question)
uv run python -m massgen.cli \
--config massgen/configs/basic/multi/three_agents_default.yaml
# Debug mode for troubleshooting
uv run python -m massgen.cli \
--config massgen/configs/basic/multi/three_agents_default.yaml \
--debug "Your question"
MassGen configurations are organized by features and use cases. See the Configuration Guide for detailed organization and examples.
Quick navigation:
- Basic setups: Single agent | Multi-agent
- Tool integrations: MCP servers | Web search | Filesystem
- Provider examples: OpenAI | Claude | Gemini
- Specialized teams: Creative | Research | Development
See MCP server setup guides: Discord MCP | Twitter MCP
For detailed configuration of all supported backends (OpenAI, Claude, Gemini, Grok, etc.), see:
β Backend Configuration Guide
MassGen supports an interactive mode where you can have ongoing conversations with the system:
# Start interactive mode with a single agent (no tool enabled by default)
uv run python -m massgen.cli --model gpt-5-mini
# Start interactive mode with configuration file
uv run python -m massgen.cli \
--config massgen/configs/basic/multi/three_agents_default.yaml
Interactive Mode Features:
- Multi-turn conversations: Multiple agents collaborate to chat with you in an ongoing conversation
- Real-time coordination tracking: Live visualization of agent interactions, votes, and decision-making processes
-
Interactive coordination table: Press
r
to view complete history of agent coordination events and state transitions - Real-time feedback: Displays real-time agent and system status with enhanced coordination visualization
-
Clear conversation history: Type
/clear
to reset the conversation and start fresh -
Easy exit: Type
/quit
,/exit
,/q
, or pressCtrl+C
to stop
Watch the recorded demo:
The system provides multiple ways to view and analyze results:
- Live Collaboration View: See agents working in parallel through a multi-region terminal display
- Status Updates: Real-time phase transitions, voting progress, and consensus building
- Streaming Output: Watch agents' reasoning and responses as they develop
Watch an example here:
All sessions are automatically logged with detailed information. The file can be viewed throught the interaction with UI.
Logging storage are organized in the following directory hierarchy:
massgen_logs/
βββ log_{timestamp}/
βββ agent_outputs/
β βββ agent_id.txt
β βββ final_presentation_agent_id.txt
β βββ system_status.txt
βββ agent_id/
β βββ {answer_generation_timestamp}/
β βββ files_included_in_generated_answer
βββ final_workspace/
β βββ agent_id/
β βββ {answer_generation_timestamp}/
β βββ files_included_in_generated_answer
βββ massgen.log / massgen_debug.log
-
log_{timestamp}
: Main log directory identified by session timestamp -
agent_outputs/
: Contains text outputs from each agent-
agent_id.txt
: Raw output from each agent -
final_presentation_agent_id.txt
: Final presentation for the selected agent -
system_status.txt
: System status information
-
-
agent_id/
: Directory for each agent containing answer versions-
{answer_generation_timestamp}/
: Timestamp directory for each answer version-
files_included_in_generated_answer
: All relevant files in that version
-
-
-
final_workspace/
: Final presentation for selected agents-
agent_id/
: Selected agent id-
{answer_generation_timestamp}/
: Timestamp directory for final presentation-
files_included_in_generated_answer
: All relevant files in final presentation
-
-
-
-
massgen.log
ormassgen_debug.log
: Main log file,massgen.log
for general logging,massgen_debug.log
for verbose debugging information.
The final presentation continues to be stored in each Claude Code Agent's workspace as before. After generating the final presentation, the relevant files will be copied to the final_workspace/
directory.
To see how MassGen works in practice, check out these detailed case studies based on real session logs:
MassGen is currently in its foundational stage, with a focus on parallel, asynchronous multi-agent collaboration and orchestration. Our roadmap is centered on transforming this foundation into a highly robust, intelligent, and user-friendly system, while enabling frontier research and exploration. An earlier version of MassGen can be found here.
π Released: September 24, 2025
Version 0.0.23 introduces Backend Architecture Refactoring and Formatter Module, establishing cleaner, more maintainable codebase:
-
Major Code Consolidation: New
base_with_mcp.py
base class consolidating common MCP functionality (488 lines) - Massive Line Reduction: Reduced ~1,932 lines across core backend files through deduplication
- Standardized MCP Integration: Unified MCP client initialization and error handling across all backends
- Improved Maintainability: Extracted shared MCP logic from individual backends into unified base class
-
Dedicated Formatting Logic: New
massgen/formatter/
module with specialized formatters -
Message Formatting:
message_formatter.py
handles message formatting across backends -
Tool Formatting:
tool_formatter.py
andmcp_tool_formatter.py
manage tool call formatting - Better Code Organization: Separated formatting concerns from core backend logic
- Coordination Table: Fixed escape key handling on macOS with updated display components
- FastMCP Integration: Added fastmcp to dependencies for workspace copy MCP support
- Path Handling: Improved relative path handling for better portability
β
Backend Architecture Refactoring (v0.0.23): Major code consolidation with new base_with_mcp.py
class reducing ~1,932 lines across backends, extracted formatter module for better code organization, and improved maintainability through unified MCP integration
β Workspace Copy Tools via MCP (v0.0.22): Seamless file copying capabilities between workspaces, configuration organization with hierarchical structure, and enhanced file operations for large-scale collaboration
β Grok MCP Integration (v0.0.21): Unified backend architecture with full MCP server support, filesystem capabilities through MCP servers, and enhanced configuration files
β Claude Backend MCP Support (v0.0.20): Extended MCP integration to Claude backend, full MCP protocol and filesystem support, robust error handling, and comprehensive documentation
β Comprehensive Coordination Tracking (v0.0.19): Complete coordination tracking and visualization system with event-based tracking, interactive coordination table display, and advanced debugging capabilities for multi-agent collaboration patterns
β Comprehensive MCP Integration (v0.0.18): Extended MCP to all Chat Completions backends (Cerebras AI, Together AI, Fireworks AI, Groq, Nebius AI Studio, OpenRouter), cross-provider function calling compatibility, 9 new MCP configuration examples
β OpenAI MCP Integration (v0.0.17): Extended MCP (Model Context Protocol) support to OpenAI backend with full tool discovery and execution capabilities for GPT models, unified MCP architecture across multiple backends, and enhanced debugging
β
Unified Filesystem Support with MCP Integration (v0.0.16): Complete FilesystemManager
class providing unified filesystem access for Gemini and Claude Code backends, with MCP-based operations for file manipulation and cross-agent collaboration
β MCP Integration Framework (v0.0.15): Complete MCP implementation for Gemini backend with multi-server support, circuit breaker patterns, and comprehensive security framework
β Enhanced Logging (v0.0.14): Improved logging system for better agents' answer debugging, new final answer directory structure, and detailed architecture documentation
β Unified Logging System (v0.0.13): Centralized logging infrastructure with debug mode and enhanced terminal display formatting
β Windows Platform Support (v0.0.13): Windows platform compatibility with improved path handling and process management
β Enhanced Claude Code Agent Context Sharing (v0.0.12): Claude Code agents now share workspace context by maintaining snapshots and temporary workspace in orchestrator's side
β Documentation Improvement (v0.0.12): Updated README with current features and improved setup instructions
β Custom System Messages (v0.0.11): Enhanced system message configuration and preservation with backend-specific system prompt customization
β Claude Code Backend Enhancements (v0.0.11): Improved integration with better system message handling, JSON response parsing, and coordination action descriptions
β Azure OpenAI Support (v0.0.10): Integration with Azure OpenAI services including GPT-4.1 and GPT-5-chat models with async streaming
β MCP (Model Context Protocol) Support (v0.0.9): Integration with MCP for advanced tool capabilities in Claude Code Agent, including Discord and Twitter integration
β Timeout Management System (v0.0.8): Orchestrator-level timeout with graceful fallback and enhanced error messages
β Local Model Support (v0.0.7): Complete LM Studio integration for running open-weight models locally with automatic server management
β GPT-5 Series Integration (v0.0.6): Support for OpenAI's GPT-5, GPT-5-mini, GPT-5-nano with advanced reasoning parameters
β Claude Code Integration (v0.0.5): Native Claude Code backend with streaming capabilities and tool support
β GLM-4.5 Model Support (v0.0.4): Integration with ZhipuAI's GLM-4.5 model family
β Foundation Architecture (v0.0.3): Complete multi-agent orchestration system with async streaming, builtin tools, and multi-backend support
β Extended Provider Ecosystem: Support for 15+ providers including Cerebras AI, Together AI, Fireworks AI, Groq, Nebius AI Studio, and OpenRouter
- Advanced Agent Collaboration: Exploring improved communication patterns and consensus-building protocols to improve agent synergy
- Expanded Model Integration: Adding support for more frontier models and local inference engines
- Improved Performance & Scalability: Optimizing the streaming and logging mechanisms for better performance and resource management
- Enhanced Developer Experience: Introducing a more modular agent design and a comprehensive benchmarking framework for easier extension and evaluation
- Web Interface: Developing a web-based UI for better visualization and interaction with the agent ecosystem
We welcome community contributions to achieve these goals.
Version 0.0.24 builds upon the solid backend refactoring of v0.0.23 by focusing on local model support, orchestrator improvements, and enhanced agent communication. Key priorities include:
- VLLM Local Model Support: Add support for VLLM backends with local models for better performance and cost efficiency
- Agent System Prompt Fixes: Fix the problem where the final agent expects human feedback through system prompt changes
- Refactor Orchestrator: Streamline orchestrator code for better maintainability and performance
- MCP Marketplace Integration: Integrate MCP Marketplace support for expanded tool ecosystem
Key technical approach:
- Local Model Infrastructure: Enable high-performance local model inference through VLLM with OpenAI-compatible API
- Autonomous Agent Behavior: Ensure final agents complete tasks without expecting human feedback
- Code Maintainability: Streamline orchestrator code for improved performance and maintainability
- Tool Ecosystem: Expand capabilities through MCP Marketplace discovery and installation
For detailed milestones and technical specifications, see the full v0.0.24 roadmap.
We welcome contributions! Please see our Contributing Guidelines for details.
This project is licensed under the Apache License 2.0 - see the LICENSE file for details.
β Star this repo if you find it useful! β
Made with β€οΈ by the MassGen team
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for MassGen
Similar Open Source Tools

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. The system operates through an architecture designed for seamless multi-agent collaboration, with key features including cross-model/agent synergy, parallel processing, intelligence sharing, consensus building, and live visualization. Users can install the system, configure API settings, and run MassGen for various tasks such as question answering, creative writing, research, development & coding tasks, and web automation & browser tasks. The roadmap includes plans for advanced agent collaboration, expanded model, tool & agent integration, improved performance & scalability, enhanced developer experience, and a web interface.

tunacode
TunaCode CLI is an AI-powered coding assistant that provides a command-line interface for developers to enhance their coding experience. It offers features like model selection, parallel execution for faster file operations, and various commands for code management. The tool aims to improve coding efficiency and provide a seamless coding environment for developers.

llm-context.py
LLM Context is a tool designed to assist developers in quickly injecting relevant content from code/text projects into Large Language Model chat interfaces. It leverages `.gitignore` patterns for smart file selection and offers a streamlined clipboard workflow using the command line. The tool also provides direct integration with Large Language Models through the Model Context Protocol (MCP). LLM Context is optimized for code repositories and collections of text/markdown/html documents, making it suitable for developers working on projects that fit within an LLM's context window. The tool is under active development and aims to enhance AI-assisted development workflows by harnessing the power of Large Language Models.

llm4s
LLM4S provides a simple, robust, and scalable framework for building Large Language Models (LLM) applications in Scala. It aims to leverage Scala's type safety, functional programming, JVM ecosystem, concurrency, and performance advantages to create reliable and maintainable AI-powered applications. The framework supports multi-provider integration, execution environments, error handling, Model Context Protocol (MCP) support, agent frameworks, multimodal generation, and Retrieval-Augmented Generation (RAG) workflows. It also offers observability features like detailed trace logging, monitoring, and analytics for debugging and performance insights.

zotero-mcp
Zotero MCP is an open-source project that integrates AI capabilities with Zotero using the Model Context Protocol. It consists of a Zotero plugin and an MCP server, enabling AI assistants to search, retrieve, and cite references from Zotero library. The project features a unified architecture with an integrated MCP server, eliminating the need for a separate server process. It provides features like intelligent search, detailed reference information, filtering by tags and identifiers, aiding in academic tasks such as literature reviews and citation management.

dive
Dive is an AI toolkit for Go that enables the creation of specialized teams of AI agents and seamless integration with leading LLMs. It offers a CLI and APIs for easy integration, with features like creating specialized agents, hierarchical agent systems, declarative configuration, multiple LLM support, extended reasoning, model context protocol, advanced model settings, tools for agent capabilities, tool annotations, streaming, CLI functionalities, thread management, confirmation system, deep research, and semantic diff. Dive also provides semantic diff analysis, unified interface for LLM providers, tool system with annotations, custom tool creation, and support for various verified models. The toolkit is designed for developers to build AI-powered applications with rich agent capabilities and tool integrations.

R2R
R2R (RAG to Riches) is a fast and efficient framework for serving high-quality Retrieval-Augmented Generation (RAG) to end users. The framework is designed with customizable pipelines and a feature-rich FastAPI implementation, enabling developers to quickly deploy and scale RAG-based applications. R2R was conceived to bridge the gap between local LLM experimentation and scalable production solutions. **R2R is to LangChain/LlamaIndex what NextJS is to React**. A JavaScript client for R2R deployments can be found here. ### Key Features * **π Deploy** : Instantly launch production-ready RAG pipelines with streaming capabilities. * **π§© Customize** : Tailor your pipeline with intuitive configuration files. * **π Extend** : Enhance your pipeline with custom code integrations. * **βοΈ Autoscale** : Scale your pipeline effortlessly in the cloud using SciPhi. * **π€ OSS** : Benefit from a framework developed by the open-source community, designed to simplify RAG deployment.

quantalogic
QuantaLogic is a ReAct framework for building advanced AI agents that seamlessly integrates large language models with a robust tool system. It aims to bridge the gap between advanced AI models and practical implementation in business processes by enabling agents to understand, reason about, and execute complex tasks through natural language interaction. The framework includes features such as ReAct Framework, Universal LLM Support, Secure Tool System, Real-time Monitoring, Memory Management, and Enterprise Ready components.

paelladoc
PAELLADOC is an intelligent documentation system that uses AI to analyze code repositories and generate comprehensive technical documentation. It offers a modular architecture with MECE principles, interactive documentation process, key features like Orchestrator and Commands, and a focus on context for successful AI programming. The tool aims to streamline documentation creation, code generation, and product management tasks for software development teams, providing a definitive standard for AI-assisted development documentation.

zcf
ZCF (Zero-Config Claude-Code Flow) is a tool that provides zero-configuration, one-click setup for Claude Code with bilingual support, intelligent agent system, and personalized AI assistant. It offers an interactive menu for easy operations and direct commands for quick execution. The tool supports bilingual operation with automatic language switching and customizable AI output styles. ZCF also includes features like BMad Workflow for enterprise-grade workflow system, Spec Workflow for structured feature development, CCR (Claude Code Router) support for proxy routing, and CCometixLine for real-time usage tracking. It provides smart installation, complete configuration management, and core features like professional agents, command system, and smart configuration. ZCF is cross-platform compatible, supports Windows and Termux environments, and includes security features like dangerous operation confirmation mechanism.

klavis
Klavis AI is a production-ready solution for managing Multiple Communication Protocol (MCP) servers. It offers self-hosted solutions and a hosted service with enterprise OAuth support. With Klavis AI, users can easily deploy and manage over 50 MCP servers for various services like GitHub, Gmail, Google Sheets, YouTube, Slack, and more. The tool provides instant access to MCP servers, seamless authentication, and integration with AI frameworks, making it ideal for individuals and businesses looking to streamline their communication and data management workflows.

mcp-apache-spark-history-server
The MCP Server for Apache Spark History Server is a tool that connects AI agents to Apache Spark History Server for intelligent job analysis and performance monitoring. It enables AI agents to analyze job performance, identify bottlenecks, and provide insights from Spark History Server data. The server bridges AI agents with existing Apache Spark infrastructure, allowing users to query job details, analyze performance metrics, compare multiple jobs, investigate failures, and generate insights from historical execution data.

simba
Simba is an open source, portable Knowledge Management System (KMS) designed to seamlessly integrate with any Retrieval-Augmented Generation (RAG) system. It features a modern UI and modular architecture, allowing developers to focus on building advanced AI solutions without the complexities of knowledge management. Simba offers a user-friendly interface to visualize and modify document chunks, supports various vector stores and embedding models, and simplifies knowledge management for developers. It is community-driven, extensible, and aims to enhance AI functionality by providing a seamless integration with RAG-based systems.

pilottai
PilottAI is a Python framework for building autonomous multi-agent systems with advanced orchestration capabilities. It provides enterprise-ready features for building scalable AI applications. The framework includes hierarchical agent systems, production-ready features like asynchronous processing and fault tolerance, advanced memory management with semantic storage, and integrations with multiple LLM providers and custom tools. PilottAI offers specialized agents for various tasks such as customer service, document processing, email handling, knowledge acquisition, marketing, research analysis, sales, social media, and web search. The framework also provides documentation, example use cases, and advanced features like memory management, load balancing, and fault tolerance.

auto-engineer
Auto Engineer is a tool designed to automate the Software Development Life Cycle (SDLC) by building production-grade applications with a combination of human and AI agents. It offers a plugin-based architecture that allows users to install only the necessary functionality for their projects. The tool guides users through key stages including Flow Modeling, IA Generation, Deterministic Scaffolding, AI Coding & Testing Loop, and Comprehensive Quality Checks. Auto Engineer follows a command/event-driven architecture and provides a modular plugin system for specific functionalities. It supports TypeScript with strict typing throughout and includes a built-in message bus server with a web dashboard for monitoring commands and events.
For similar tasks

LLMStack
LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

ai-guide
This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.

onnxruntime-genai
ONNX Runtime Generative AI is a library that provides the generative AI loop for ONNX models, including inference with ONNX Runtime, logits processing, search and sampling, and KV cache management. Users can call a high level `generate()` method, or run each iteration of the model in a loop. It supports greedy/beam search and TopP, TopK sampling to generate token sequences, has built in logits processing like repetition penalties, and allows for easy custom scoring.

jupyter-ai
Jupyter AI connects generative AI with Jupyter notebooks. It provides a user-friendly and powerful way to explore generative AI models in notebooks and improve your productivity in JupyterLab and the Jupyter Notebook. Specifically, Jupyter AI offers: * An `%%ai` magic that turns the Jupyter notebook into a reproducible generative AI playground. This works anywhere the IPython kernel runs (JupyterLab, Jupyter Notebook, Google Colab, Kaggle, VSCode, etc.). * A native chat UI in JupyterLab that enables you to work with generative AI as a conversational assistant. * Support for a wide range of generative model providers, including AI21, Anthropic, AWS, Cohere, Gemini, Hugging Face, NVIDIA, and OpenAI. * Local model support through GPT4All, enabling use of generative AI models on consumer grade machines with ease and privacy.

khoj
Khoj is an open-source, personal AI assistant that extends your capabilities by creating always-available AI agents. You can share your notes and documents to extend your digital brain, and your AI agents have access to the internet, allowing you to incorporate real-time information. Khoj is accessible on Desktop, Emacs, Obsidian, Web, and Whatsapp, and you can share PDF, markdown, org-mode, notion files, and GitHub repositories. You'll get fast, accurate semantic search on top of your docs, and your agents can create deeply personal images and understand your speech. Khoj is self-hostable and always will be.

langchain_dart
LangChain.dart is a Dart port of the popular LangChain Python framework created by Harrison Chase. LangChain provides a set of ready-to-use components for working with language models and a standard interface for chaining them together to formulate more advanced use cases (e.g. chatbots, Q&A with RAG, agents, summarization, extraction, etc.). The components can be grouped into a few core modules: * **Model I/O:** LangChain offers a unified API for interacting with various LLM providers (e.g. OpenAI, Google, Mistral, Ollama, etc.), allowing developers to switch between them with ease. Additionally, it provides tools for managing model inputs (prompt templates and example selectors) and parsing the resulting model outputs (output parsers). * **Retrieval:** assists in loading user data (via document loaders), transforming it (with text splitters), extracting its meaning (using embedding models), storing (in vector stores) and retrieving it (through retrievers) so that it can be used to ground the model's responses (i.e. Retrieval-Augmented Generation or RAG). * **Agents:** "bots" that leverage LLMs to make informed decisions about which available tools (such as web search, calculators, database lookup, etc.) to use to accomplish the designated task. The different components can be composed together using the LangChain Expression Language (LCEL).

danswer
Danswer is an open-source Gen-AI Chat and Unified Search tool that connects to your company's docs, apps, and people. It provides a Chat interface and plugs into any LLM of your choice. Danswer can be deployed anywhere and for any scale - on a laptop, on-premise, or to cloud. Since you own the deployment, your user data and chats are fully in your own control. Danswer is MIT licensed and designed to be modular and easily extensible. The system also comes fully ready for production usage with user authentication, role management (admin/basic users), chat persistence, and a UI for configuring Personas (AI Assistants) and their Prompts. Danswer also serves as a Unified Search across all common workplace tools such as Slack, Google Drive, Confluence, etc. By combining LLMs and team specific knowledge, Danswer becomes a subject matter expert for the team. Imagine ChatGPT if it had access to your team's unique knowledge! It enables questions such as "A customer wants feature X, is this already supported?" or "Where's the pull request for feature Y?"

infinity
Infinity is an AI-native database designed for LLM applications, providing incredibly fast full-text and vector search capabilities. It supports a wide range of data types, including vectors, full-text, and structured data, and offers a fused search feature that combines multiple embeddings and full text. Infinity is easy to use, with an intuitive Python API and a single-binary architecture that simplifies deployment. It achieves high performance, with 0.1 milliseconds query latency on million-scale vector datasets and up to 15K QPS.
For similar jobs

weave
Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

LLMStack
LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

VisionCraft
The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

kaito
Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

PyRIT
PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

tabby
Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

spear
SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

Magick
Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.