file-search
π―Skillfrom massgen/massgen
|Searches files across directories using specified search criteria, returning matching file paths and relevant details.
Part of
massgen/massgen(11 items)
Installation
pip install --upgrade massgenuv run massgen --config @examples/configs/providers/openai/codex/codex_local.yaml "Create a website about Bob Dylan"uv run massgen --config @examples/configs/providers/openai/codex/codex_docker.yaml "Create a website about Bob Dylan"npm install -g @openai/codexSkill Details
Overview
[](https://pypi.org/project/massgen/) [](https://docs.massgen.ai) [](https://github.com/Leezekun/MassGen) [](https://www.python.org/downloads/) [](LICENSE)
[](https://x.massgen.ai) [](https://www.linkedin.com/company/massgen-ai) [](https://discord.massgen.ai)
π MassGen: Multi-Agent Scaling System for GenAI
MassGen is a cutting-edge multi-agent system that leverages the power of collaborative AI to solve complex tasks.
Scaling AI with collaborative, continuously improving agents
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](https://docs.ag2.ai/latest/docs/blog/2025/04/16/Reasoning/), and extends the classic "multi-agent conversation" idea in [AG2](https://github.com/ag2ai/ag2). Here is a [video recording](https://www.youtube.com/watch?v=xM2Uguw1UsQ) of the background context introduction presented at the Berkeley Agentic AI Summit 2025.
π€ For LLM Agents: AI_USAGE.md - Complete automation guide to run MassGen inside an LLM
π For Contributors: See MassGen Contributor Handbook - Centralized policies and resources for development and research teams
---
π Table of Contents
β¨ Key Features
- [Cross-Model/Agent Synergy](#-key-features-1)
- [Parallel Processing](#-key-features-1)
- [Intelligence Sharing](#-key-features-1)
- [Consensus Building](#-key-features-1)
- [Live Visualization](#-key-features-1)
π Latest Features
- [v0.1.47 Features](#-latest-features-v0147)
ποΈ System Design
- [System Architecture](#%EF%B8%8F-system-design-1)
- [Parallel Processing](#%EF%B8%8F-system-design-1)
- [Real-time Collaboration](#%EF%B8%8F-system-design-1)
- [Convergence Detection](#%EF%B8%8F-system-design-1)
- [Adaptive Coordination](#%EF%B8%8F-system-design-1)
π Quick Start
- [π₯ Installation](#1--installation)
- [π API Configuration](#2--api-configuration)
- [𧩠Supported Models and Tools](#3--supported-models-and-tools)
- [Models](#models)
- [Tools](#tools)
- [π Run MassGen](#4--run-massgen)
- [CLI Configuration Parameters](#cli-configuration-parameters)
- [1. Single Agent (Easiest Start)](#1-single-agent-easiest-start)
- [2. Multi-Agent Collaboration (Recommended)](#2-multi-agent-collaboration-recommended)
- [3. Model Context Protocol (MCP)](#3-model-context-protocol-mcp)
- [4. File System Operations](#4-file-system-operations--workspace-management)
- [5. Project Integration (NEW in v0.0.21)](#5-project-integration--user-context-paths-new-in-v0021)
- [Backend Configuration Reference](#backend-configuration-reference)
- [Interactive Multi-Turn Mode](#interactive-multi-turn-mode)
- [π View Results](#5--view-results)
- [Real-time Display](#real-time-display)
- [Comprehensive Logging](#comprehensive-logging)
π€ Automation & LLM Integration
- [Automation Mode](#-automation--llm-integration)
- [BackgroundShellManager](#using-backgroundshellmanager)
- [Status File Reference](#statusjson-structure)
- [Full Automation Guide](https://docs.massgen.ai/en/latest/user_guide/automation.html)
π‘ Case Studies & Examples
- [Case Studies](#-case-studies)
πΊοΈ Roadmap
- [Recent Achievements (v0.1.47)](#recent-achievements-v0147)
- [Previous Achievements (v0.0.3 - v0.1.46)](#previous-achievements-v003---v0146)
- [Key Future Enhancements](#key-future-enhancements)
- Bug Fixes & Backend Improvements
- Advanced Agent Collaboration
- Expanded Model, Tool & Agent Integrations
- Improved Performance & Scalability
- Enhanced Developer Experience
- [v0.1.48 Roadmap](#v0148-roadmap)
π Additional Resources
- [π€ Contributing](#-contributing)
- [π License](#-license)
- [β Star History](#-star-history)
---
β¨ Key Features
| 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₯οΈ Live Visualization | Interactive Textual TUI with timeline, agent cards, and vote tracking (default). Also available: Web UI, Rich display. |
---
π Latest Features (v0.1.47)
π Released: February 4, 2026
What's New in v0.1.47:
- π Codex Backend - Run OpenAI Codex CLI as a MassGen backend with local and Docker execution
- π¨ TUI Theme System - Palette-based theming with dark and light variants
- π³οΈ Per-agent Voting Sensitivity - Set different voting standards (strict/balanced/lenient) for each agent
- π§ Claude Code Refactored - Shared
NativeToolMixinfor native tool handling across CLI-based backends - π Bug Fixes - Fixed final presentation display, improved MCP error handling, enhanced round tracking
Try v0.1.47 Features:
```bash
# Install or upgrade
pip install --upgrade massgen
# First install codex with npm install -g @openai/codex, then authenticate and run the below.
uv run massgen --config @examples/configs/providers/openai/codex/codex_local.yaml "Create a website about Bob Dylan"
uv run massgen --config @examples/configs/providers/openai/codex/codex_docker.yaml "Create a website about Bob Dylan"
```
β [See full release history and examples](massgen/configs/README.md#release-history--examples)
---
ποΈ System Design
MassGen operat
More from this repository10
serena skill from massgen/massgen
evolving-skill-creator skill from massgen/massgen
textual-ui-developer skill from massgen/massgen
Creates configuration files and templates for setting up and configuring MassGen multi-agent AI systems and their collaborative workflows.
Recursively develops and improves the MassGen multi-agent system by using its own collaborative AI agents to enhance and evolve the project's codebase and capabilities.
pr-checks skill from massgen/massgen
semtools skill from massgen/massgen
Manages and maintains a centralized registry of AI models, tracking their metadata, versions, performance metrics, and availability for multi-agent system deployment.
massgen-release-documenter skill from massgen/massgen
massgen-log-analyzer skill from massgen/massgen