AGENTS.mdA

AGENTS.md from amd-agi/hyperloom is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add amd-agi/hyperloom/AGENTS.md@git:20261030.f418170

Pins git:20261030.f418170 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
amd-agi/hyperloom
Path
AGENTS.md
Versions recorded
18
Latest version
git:20261030.f418170, committed Oct 30, 2026
First version recorded
Sep 5, 2026
Size
13,757 bytes
Repository stars
262
License
a license file GitHub does not identify

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

<!--
SPDX-FileCopyrightText: 2026 Advanced Micro Devices, Inc.
SPDX-License-Identifier: MIT
-->

# AGENTS.md

The authoring contract for anyone (human or AI) changing this repo: **how to make a
change land cleanly.**

Hyperloom is an autonomous agentic system that optimizes end-to-end LLM inference on AMD
GPUs (host code and GPU kernels). A Python Coordinator drives an iterative
Think → Decide → Implement → Benchmark loop, delegating to LLM roles and programmatic
handlers and integrating external components.

## Where things are documented

| Topic | Source of truth |
|---|---|
| Optimization loop, phase chain, orchestration model | [`docs/conceptual/optimization-loop.md`](docs/conceptual/optimization-loop.md) |
| Profiling → TraceLens → kernel value chain | [`docs/reference/kernel-execution-path.md`](docs/reference/kernel-execution-path.md) |
| External components (Magpie, TraceLens, GEAK, IntelliKit, AgentKernelArena) | [`docs/components/`](docs/components/) |
| Agent instructions / runtime behavior | [`src/hyperloom/inference_optimizer/SKILL.md`](src/hyperloom/inference_optimizer/SKILL.md) |
| Workflow & PR process | [`CONTRIBUTING.md`](CONTRIBUTING.md) |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add amd-agi/hyperloom/AGENTS.md@sha256:fcd9baf0e5c9d2d4

The line at the top of this page pins the label git:20261030.f418170, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_akrsckubous6b2o2.svg)](https://markdownregistry.com/a/art_akrsckubous6b2o2)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 18 versions of this file, between Sep 5, 2026 and Oct 30, 2026, about one every 3 days.

versioncommittedcommitsizeaudit
git:20261030.f418170 latest2026-10-30 f418170 13,757 BA view · diff
git:20261028.42950782026-10-28 4295078 13,475 BA view · diff
git:20261027.67e8ca42026-10-27 67e8ca4 13,431 BA view · diff
git:20261023.8b399d42026-10-23 8b399d4 13,081 BA view · diff
git:20261020.96780022026-10-20 9678002 12,871 BA view · diff
git:20261020.fd56bc92026-10-20 fd56bc9 13,088 BA view · diff
git:20261012.ac6ae792026-10-12 ac6ae79 12,686 BA view · diff
git:20261012.8ae988c2026-10-12 8ae988c 11,306 BA view · diff
git:20261010.f7e7afe2026-10-10 f7e7afe 12,370 BA view · diff
git:20261010.e0ec7e22026-10-10 e0ec7e2 12,340 BA view · diff
git:20261010.b78114c2026-10-10 b78114c 11,308 BA view · diff
git:20261010.5d261362026-10-10 5d26136 10,990 BA view · diff
git:20260921.e27c6de2026-09-21 e27c6de 10,753 BA view · diff
git:20260921.dcebdcd2026-09-21 dcebdcd 10,629 BA view · diff
git:20260921.2d70a452026-09-21 2d70a45 6,520 BA view · diff
git:20260921.6b4b4132026-09-21 6b4b413 10,574 BA view · diff
git:20260916.a3612d82026-09-16 a3612d8 6,396 BA view · diff
git:20260905.807e1172026-09-05 807e117 5,806 BA view

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (13757 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

amd-agi/hyperloom · 262 stars · license a license file GitHub does not identify · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_akrsckubous6b2o2
GET https://markdownregistry.com/api/v1/resolve?ref=amd-agi/hyperloom/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/fcd9baf0e5c9d2d4a6cb144f996c5559aa21c06cbffff99ae34eac0d10bac51c

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: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from amd-agi/hyperloom

analyze-upstream-pr SKILL.md skill
amd-agi/hyperloom · .claude/skills/analyze-upstream-pr/SKILL.md · Analyze whether an upstream pull request applies to an AMD/ROCm deployment. Invoke with the PR's repository and number…
git:20261020.6cc6611 · audit A · 262 stars
check-prior-art SKILL.md skill
amd-agi/hyperloom · .claude/skills/check-prior-art/SKILL.md · Check whether a planned optimization already exists upstream before building it. Invoke with a one-sentence mechanism…
git:20261020.a160c20 · audit A · 262 stars
review-pr SKILL.md skill
amd-agi/hyperloom · .claude/skills/review-pr/SKILL.md · Review a Hyperloom pull request. Invoke with a PR number whenever asked to review, re-review or sanity-check a PR in…
git:20261029.8d68eef · audit A · 262 stars
CLAUDE.md CLAUDE.md file
amd-agi/hyperloom · CLAUDE.md
git:20260921.6b4b413 · audit B · 262 stars
hyperloom-remote-mn-qwen3-30b SKILL.md skill
amd-agi/hyperloom · docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30b/SKILL.md · Run a 4-hour multi-node Hyperloom Qwen3-30B-A3B optimization (Infera PD-disaggregated or RayJob aggregated) with…
git:20260827.1988620 · audit A · 262 stars
hyperloom-custom-advanced SKILL.md skill
amd-agi/hyperloom · examples/hyperloom-custom-advanced/SKILL.md · Run an advanced configurable Hyperloom optimization session with explicit model, framework, workload, objective, and…
git:20261106.2f99e29 · audit B · 262 stars
hyperloom-qwen3-14b-fp8-12h-forge SKILL.md skill
amd-agi/hyperloom · examples/hyperloom-qwen3-14b-fp8-12h-forge/SKILL.md · Run a 12-hour Hyperloom Qwen3-14B-FP8 optimization session on SGLang, vLLM or ATOM with the per-kernel KernelForge…
git:20261106.2f99e29 · audit B · 262 stars
hyperloom-qwen3-14b-fp8-12h SKILL.md skill
amd-agi/hyperloom · examples/hyperloom-qwen3-14b-fp8-12h/SKILL.md · Run a 12-hour Hyperloom Qwen3-14B-FP8 optimization session on SGLang, vLLM or ATOM. Use when the user wants a…
git:20261106.2f99e29 · audit B · 262 stars
hyperloom-qwen3-8b-3h SKILL.md skill
amd-agi/hyperloom · examples/hyperloom-qwen3-8b-3h/SKILL.md · Run a 3-hour Hyperloom Qwen3-8B FRAMEWORK_AGENT (OPTIMIZE) session without the Kernel Agent. Use when the user wants a…
git:20261106.2f99e29 · audit B · 262 stars
hyperloom-workload-optimizer SKILL.md skill
amd-agi/hyperloom · examples/skills/hyperloom-workload-optimizer/SKILL.md · Autonomously optimizes end-to-end LLM inference throughput on AMD Instinct GPUs and reports a validated gain, using the…
git:20260924.f2e2a9c · audit A · 262 stars
critic-agent SKILL.md skill
amd-agi/hyperloom · src/hyperloom/agents/critic/SKILL.md · Critic layer for the inference optimizer. Use when Conductor asks for a Critic Review verdict on Orchestration or…
git:20261023.0718479 · audit A · 262 stars
quantization-agent SKILL.md skill
amd-agi/hyperloom · src/hyperloom/agents/quantization/SKILL.md · Hyperloom sub-agent that drives the AMD Quark PTQ skill chain end-to-end from a natural-language prompt. Produces a…
git:20261029.20d8b20 · audit A · 262 stars

Every file in amd-agi/hyperloom

Other files named AGENTS.md

AGENTS.md AGENTS.md file
morluto/rea · AGENTS.md
git:20261102.920d634 · audit A · 433,876 stars
AGENTS.md AGENTS.md file
obra/superpowers · AGENTS.md
git:20261020.b739a8a · audit A · 314,583 stars
AGENTS.md AGENTS.md file
affaan-m/ecc · AGENTS.md
git:20261030.f29e332 · audit A · 299,696 stars
AGENTS.md AGENTS.md file
firecrawl/firecrawl · AGENTS.md
git:20261008.5a75dca · audit A · 199,595 stars
AGENTS.md AGENTS.md file
dietrichgebert/ponytail · AGENTS.md
git:20261008.2a1fe84 · audit A · 185,249 stars
AGENTS.md AGENTS.md file
graphify-labs/graphify · AGENTS.md
git:20260926.98d73fe · audit A · 144,492 stars
AGENTS.md AGENTS.md file
garrytan/gstack · AGENTS.md
git:20261107.ef99eb5 · audit A · 140,694 stars
AGENTS.md AGENTS.md file
juliusbrussee/caveman · AGENTS.md
git:20261106.e45976c · audit A · 118,366 stars

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