hyperloom-setup SKILL.md skillC

hyperloom-setup from amd-agi/hyperloom is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

mdr add amd-agi/hyperloom/hyperloom-setup@git:20261106.2f99e29

Pins git:20261106.2f99e29 in mdr.lock. Pin the fingerprint instead.

Audit grade

C, 15 of 17 checks passed

Kind

SKILL.md skill

Repository

amd-agi/hyperloom

Path

src/hyperloom/skills/hyperloom-setup/SKILL.md

Versions recorded

39

Latest version

git:20261106.2f99e29, committed Nov 6, 2026

First version recorded

Aug 14, 2026

Size

31,745 bytes

Repository stars

262

License

a license file GitHub does not identify

Configures Hyperloom after pip install --target . by collecting core LLM/runtime settings once, choosing direct baremetal or Docker execution, writing .env, deploying the workspace's local Experience KB service, and running the setup backend directly only in baremetal mode.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Hyperloom Setup

Use this skill after the user prepares a dedicated workspace, opens that
directory in the agent, and installs Hyperloom into the current directory:

```bash
pip install your_package.whl --target .
```

The Experience KB service ships inside Hyperloom. Setup deploys one local
service per workspace; every optimize run reads from and writes to it.

The current directory is the Hyperloom workspace and install target. It is normal
for this directory to contain many Python package folders; users do not need to
inspect them. Do not use an existing project directory unless the user accepts
that setup may create or update `.env` in that directory.

This skill should normally run once per workspace. It resolves a run mode into
`HYPERLOOM_RUN_MODE` (`baremetal` or `docker`) for this session. In `baremetal`
mode it runs the setup backend on the host; in `docker` mode it writes `.env`
only. It does **not** start any container.
Whether to generate or run a Docker container is decided later by the example
(workload) skill based on `HYPERLOOM_RUN_MODE`.

- `baremetal`: run directly in the current development environment, even if that
…

Read the whole file at its exact version.

How to install

mdr add amd-agi/hyperloom/hyperloom-setup@sha256:3bef3c4ca2e4cec7

[![mdr](https://markdownregistry.com/badge/art_mzkjqj4e6tsvwghv.svg)](https://markdownregistry.com/a/art_mzkjqj4e6tsvwghv)

Versions

The registry has recorded 39 versions of this file, between Aug 14, 2026 and Nov 6, 2026, about one every 2 days. Its first recorded version is graded B and its latest C.

Audit of the latest version

Source

API

GET https://markdownregistry.com/api/v1/artifacts/art_mzkjqj4e6tsvwghv
GET https://markdownregistry.com/api/v1/resolve?ref=amd-agi/hyperloom/hyperloom-setup
GET https://markdownregistry.com/api/v1/blob/3bef3c4ca2e4cec7f223de7a5b7e4af28168aa98e976f81ba408bdd66da8b542

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from amd-agi/hyperloom

Every file in amd-agi/hyperloom

Browse by kind, by grade C, or by owner.