MassGen
A terminal system where several models and agents collaborate on one task
Medium risk
We rate an entry medium when the tool runs code, makes network calls or reads project files. Check what exactly it does before installing.
Why this level
- Sends requests to external models with keys
- Runs tools and code as the agents work
Install
In your terminal, with SkillFoxx CLI
npx skillfoxx add cli/massgenDetects the agents on your machine, checks the risk and pins the version.
Other ways to install
Install the tool
pipx install massgenWithout pipx, pip install massgen works too.
Install MassGen with pip install massgen (or uv pip install massgen), then run uv run massgen --quickstart to set up. The user provides the model API keys themselves.
Other ways from the author
pip install massgenThen uv run massgen --quickstart to set up; you can also use uv pip install massgen.
This is third-party code. Review the repository files before installing.
What it does
MassGen runs several models and agents that work on a task in parallel, share reasoning and converge on a common answer. The tool works in the terminal and orchestrates different providers and agents, calling tools along the way. It has built-in skills such as image and audio generation, file search, log analysis and config creation. It installs via pip or uv, with a quickstart command for a fast start. The skill set can also be wired into other agents through the skills installer.
Who it is for. For developers and researchers who want to compare and combine answers from several models.
Good fit when
- You want an answer from several models merged together
- You need terminal orchestration of agents on one task
- You want to compare how different models solve a task
Not a fit when
- One model is enough and orchestration is overkill
- You have no access to the required model APIs
Example request
Run the task across three models and merge their answers into one solutionLimitations
It needs model API keys, and some providers are not reachable from Russia without VPN. Running several models at once increases token usage. It requires Python and environment setup.
How to disable. Remove the package with pip uninstall massgen and uninstall any wired-in skills from the agent directories.
Security check
- Sends requests to external models with keys
- Runs tools and code as the agents work
README in short
The README describes MassGen as an open-source system that runs several models and agents in the terminal to collaborate on a task and merge answers. Installation is via pip or uv, with a quickstart command for fast setup. It also offers using the skill set in other agents through the skills installer, and the built-in skills cover media generation, file search and log analysis. There is a web UI and detailed docs.
FAQ
Can it be used as a skill?
Yes, the skill set installs into agents with npx skills add massgen/skills --all.
Do I need keys for several models?
Collaboration across several models needs keys for the respective providers.
Related
Open-source personal AI assistant on your own machine: answers in Telegram, Slack, Discord and WhatsApp, extended with skills and plugins
A self-improving agent from Nous Research with a TUI, messaging gateway, cron jobs and skills it writes itself
An open source coding agent for the terminal and desktop with build and plan modes
Open prompt library with a Claude Code plugin, MCP server and CLI: search, fetch and improve prompts and skills from an agent