Happy slice of mcp pizzaMCP.pizza
loom

loom

MCP.Pizza Chef: valkor-ai

When you ask Claude, Codex, or OpenCode to build a full feature or ship an app, the work often stalls halfway through — the assistant forgets what it agreed to build, skips checks, or loses track of what it already finished. Loom sits alongside the coding assistant you already use and keeps a running record of the plan, the test results, and what still needs doing, so a stopped session can pick back up right where it left off instead of starting over. It runs on your own computer and needs Docker installed if you want to preview or hand off the finished work.

Coding

Use This MCP client To

Keep my AI coding assistant on track through a big feature build Pick up a stalled coding session right where it left off Get a written report of what my AI assistant built and tested See a working preview of the app before it ships Track requirements and progress across multiple work sessions Catch problems in the code before I review it myself Hand off a finished project with proof that it actually works

README

Loom

Loop engineering for agentic software delivery.

An open delivery harness that helps Claude Code, Codex, OpenCode, and other coding agents finish larger software tasks without losing state.

Simplified Chinese · Technical Report · Godot · Use Cases · Quick Start · How to Use · Context Routing · FAQ

License: Apache-2.0 Discord Rust Python Status

⭐ If Loom is useful to you, give it a star and help more developers find it.

What Is Loom?

Coding agents are good at writing code. They are less reliable at finishing the whole job: they lose context, skip checks, and leave handoffs unclear.

Loom is an open-source harness that runs beside the agent you already use. It keeps the work moving through a simple loop: plan, build, test, fix, preview, and hand off.

Loom saves the important project state: requirements, task progress, test results, runtime facts, and repair notes. If a session stops, the next run can continue from where things left off.

Use Loom when a task is too big for a single prompt: feature work, deployment, review, repair, preview, or a handoff that needs evidence.

News

  • Upcoming: V-SEFM, a verifier model for software delivery, is in progress. Details later.
  • Jul 2026: Loom moved its MCP runtime from TypeScript to Rust to make the core smaller and faster.
  • Jul 2026: Loom now supports Godot projects through Godot MCP. Setup guide

loom FAQ

Can I use this to keep a long coding project from losing its own plan?
Yes — Loom saves your requirements, task progress, and test results as you go, so if a session stops partway through, the next one can pick up instead of starting over.
Can I use this to get a working preview of my app before I ship it?
Yes — Loom can build a local preview using Docker so you can look over the finished result and check it before handing it off.
Do I need to know how to code to use Loom?
Yes — Loom is built for people already using a coding assistant such as Claude Code, Codex, or OpenCode to write software, and it expects one of those to be installed and working first.
Which AI coding assistants does Loom work with?
Loom works alongside Claude Code, Codex, and OpenCode, adding a memory and progress-tracking layer on top of whichever one you're already using.
Do I need an account or a paid key to use Loom?
There's no separate Loom account required, but you do need a supported coding assistant, such as Claude Code, already set up, since Loom relies on it to actually write the code.
How hard is it to set up?
It takes real technical setup — you need a supported coding assistant installed locally, plus Docker if you want to preview or deploy your project, so this fits people already comfortable with developer tools.
Does Loom write the code on its own?
No — Loom doesn't replace your coding assistant. It manages the plan, the testing, and the handoff around the assistant's work, whether that assistant is Claude, Codex, or another supported agent.
Can Loom help me pick up work after stepping away for a few days?
Yes — because Loom keeps a saved record of the project's requirements and progress, you can close your laptop and come back later without losing the plan.