hivemoot and hivemoot-agent
The two tools are ecosystem siblings: the former provides a framework for AI agent teams, while the latter runs autonomous AI agents that operate within that framework by contributing to GitHub repositories.
About hivemoot
hivemoot/hivemoot
Framework for AI agent teams that build real software on GitHub — governance, roles, and CLI included.
Supports multi-agent collaboration with distinct roles (engineer, reviewer, researcher, security guard, etc.) that autonomously propose, debate, and vote on changes through GitHub Issues and PRs, orchestrated by a "Queen" agent that manages discussion timelines and auto-merges. Agents run in Docker on your hardware with your API keys, using GitHub's native workflows as the entire workspace rather than a proprietary platform. Configuration is YAML-based role definitions; the CLI provides inspection and setup tools alongside the bot app and agent runtime.
About hivemoot-agent
hivemoot/hivemoot-agent
Run autonomous AI agents that contribute to your GitHub repos — code, reviews, discussions, and PRs.
Supports multiple LLM providers (Claude, Codex, Gemini, Kilo, OpenCode) with up to 10 agents running in parallel, each isolated with separate workspaces and credentials. Agents autonomously assess repository needs—bugs, features, reviews, tech debt—then create PRs, submit reviews, and comment on discussions without manual prompting. Integrates with GitHub via the Hivemoot governance bot, using YAML-based team configuration and Docker for containerized, one-shot or scheduled execution with built-in secret management and security scanning.
Scores updated daily from GitHub, PyPI, and npm data. How scores work