Loom

A self-hosted AI testing platform for trying out models and MCP servers, recording every request, and fronting your applications through the same OpenAI-compatible gateway.

Install

curl -fsSL https://raw.githubusercontent.com/HSPK/loom/main/install.sh | sh
# or
docker run -d -p 3000:3000 -v loom-data:/data ghcr.io/hspk/loom:latest

See Getting started for every install route, or Docker deployment for containers.

A look at it

One prompt, three providers, answers side by side.

• 

  Dashboard — volume, tokens, latency and error rate per model.

• 

  Request log — every call, with TTFT and total latency split out.

• 

  Trace detail — the full prompt and response, reassembled from the stream.

• 

  MCP servers — stdio or HTTP, with the tools Loom discovered on each.

Captured from a throwaway instance seeded by scripts/demo-screenshots.sh. The traffic is real — it went through the gateway and was logged by it — against a scripted local upstream, so no vendor was called and the numbers are reproducible.

What it does

Loom gives you, in a single process backed by one SQLite file, three things that usually live in three separate tools:

• A playground for exercising models and MCP tool flows
• A request log that captures the full prompt and full response of every call, with search, replay, and direct SQLite access
• An OpenAI-compatible gateway at /api/v1/* for your applications, with the same auth model and the same log table as the playground

The same auth applies across playground and gateway. The same MCP servers serve both. The same log table records both. There is no separate observability service to deploy.

Documentation map

• Getting started — install, init, first request
• Docker deployment — image tags, volumes, secrets, backups
• Configuration — config file, env vars, search order
• Providers — register upstreams, override model params
• MCP integration — connect MCP servers and use their tools
• Playground — chat, embedding, multi-model compare
• Request logs — search, replay, audit
• CLI reference — every flag for every subcommand
• API reference — /api/v1/* endpoints
• Environment variables — LOOM_* precedence rules
• Architecture — how the pieces fit together
• Development — local setup, conventions, contributing

Project status

Loom is under active development. The public surface (HTTP API, CLI flags, config file shape) is stabilising but may still change before 1.0. Pin a specific version in production until 1.0.0 ships.

License

MIT — © HSPK and contributors.