Quilt

Quilt is a command-line tool that tracks which agent wrote which lines in a shared Git checkout, so multiple AI coding agents can work in one repo at once and each commits only its own changes.

It captures every edit at the tool boundary, keeps a per-line record of who wrote what, and reconstructs each agent's own changes at commit time. Git stays the source of truth. Quilt never calls an LLM or spawns agents, and its state lives in a .quilt/ sidecar you can delete without touching your repo.

npm install -g @quilt-dev/cli
quilt setup     # wire Quilt into your repo (Claude Code, Cursor, or plain git)

The problem

You can run about three coding agents on one repo before they start clobbering each other. Two edit the same file and one silently overwrites the other. Their commits tangle into one blob you can't attribute. The usual advice is "run fewer," or "give each agent its own worktree."

Quilt lifts that ceiling. The agents share one checkout, and Quilt keeps attribution clean, prevents collisions, and gives each agent its own clean commit. And it holds as you add agents. Here are seven fanning out on one repo, run head to head:

That is ./examples/fleet.sh. It uses the quilt system, and you can also run it yourself.

What it does

• One shared checkout. Model humans, agents, and bots as actors editing one working tree, no worktree per agent.
• Line-level attribution. commit --mine commits only your lines, even when they share a hunk with another actor's.
• Symbol-level claims. Reserve utils.js#formatPrice, not the whole file, so agents editing different functions never contend. Ten languages via tree-sitter; whole-file claims for the rest.
• Collision prevention. A write into code another agent has claimed is denied, with the holder's stated intent, before any bytes change.
• Push-awareness. Claim a symbol that depends on a function another actor is changing, and Quilt warns you at claim time.
• Detect and preserve. If one actor overwrites another's uncommitted lines, Quilt snapshots the victim's version so nothing is silently lost.

Every commit Quilt produces is an ordinary Git commit. It trusts Git and never rewrites it, and all state lives locally under .quilt/. No account, no daemon.

Quickstart

quilt setup      # wire Quilt into the repo (MCP server, hooks, coordination)
quilt doctor     # confirm it's wired and capture is flowing

That's it. Agents are named automatically: each Claude Code session or MCP connection gets its own id, so parallel agents are told apart with no setup. Set an explicit id when you want one that is stable across sessions:

QUILT_ACTOR=auth-agent claude    # this agent's edits are attributed to auth-agent

Then each agent commits only its own lines:

quilt status                     # who owns what
quilt preview --mine             # exact patch that would be committed
quilt commit --mine -m "fix auth redir

... [View full README on GitHub](https://github.com/wkoverfield/quilt#readme)