KeiaiLab

SwarmOps — Data skill for Claude Code

Data community

SwarmOps: a git replacement for coding-agent swarms.

How to install SwarmOps

This entry records only its repository, not the path inside it, so there is no exact command to give. Open KeiaiLab/SwarmOps and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What SwarmOps does

SwarmOps: a git replacement for coding-agent swarms. Many agents commit into one embedded store at once, every command answers in JSON, and the work moves back to git. Rust, no database or daemon, full-fsync durability. Pre-1.0. Linux today; macOS and Windows next.

Alternatives in Data

Agentsview — Local-first session intelligence and analytics for coding agents, supporting Claude Code, Codex, and 14 other 824 ★
AgriQuant AI — AI-powered weather intelligence for agricultural commodity futures 707 ★
Figma UI MCP — AI can draw UI directly on the Figma canvas via JavaScript, and read existing designs back as structured data 232 ★

README

SwarmOps

A git replacement for coding-agent swarms: many writers, one store, one JSON envelope per command.

Website · Why · SwarmOps and git · How it works · Quick start · MCP · Commands · Roadmap · Documentation

SwarmOps is a git replacement for coding-agent swarms: many agents commit into one embedded store at once, every command answers in JSON, and the work moves back to git. It is built for 10 to 50 Claude Code or LangGraph processes on one host, committing to one repository at once. It is written in Rust and fully embedded: one program, no external database, no daemon. It is pre-release, at milestone M8: usable by one agent, with a store that already takes commits from many processes at once; merging and landing, which a swarm needs, are built, but landing is not yet measured under a swarm's load ([roadmap](#roadmap)).