Report · marked 25 Aug 2026

headroomlabs-ai/headroom

Solid foundations, held back in a few specific places.

Python · 67,577 stars · 2,319 files · branch main

81 /100 A-

Instructions 15/27Whether the repo tells an agent how to behave before it starts guessing. Losing marks on agent instruction file and instruction quality.Setup 20/20Whether an agent can install the project and get it running without a human. Full marks.Verification loop 22/22Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy. Full marks.Context economy 13/20Whether the repo fits in a context window, or fights it. Losing marks on file sizes fit in context and repository weight.Navigability 10/10How quickly anything new can orient itself. Full marks.

Higher is better. Accent marks what is costing you most.

Fix these first

Instruction quality

Worth fixing: it never states a build, test, or run command; has no headings to structure it; has no code blocks.

File sizes fit in context

A single file that fills the context window forces an agent to work from fragments, and it will confidently edit code it never saw. Splitting the worst offenders pays for itself immediately.

Agent instruction file

Rename or symlink to AGENTS.md so tools other than one vendor's can read it. Keeping Copilot instructions alongside it costs nothing.

The full marking

Every deduction below names the file or setting it came from.

Instructions 15/27 B-

Whether the repo tells an agent how to behave before it starts guessing.

✗Agent instruction file 8/12

Copilot instructions is present, but not the vendor-neutral AGENTS.md.

Rename or symlink to AGENTS.md so tools other than one vendor's can read it. Keeping Copilot instructions alongside it costs nothing.

✗Instruction quality 4/12

Present but too thin to change an agent's behavior.

Worth fixing: it never states a build, test, or run command; has no headings to structure it; has no code blocks.

695 characters, a workable length

✓README as an entry point 3/3

README has a clear getting-started section.

Setup 20/20 A+

Whether an agent can install the project and get it running without a human.

✓Deterministic install 6/6

uv.lock pins the dependency tree.

Found uv.lock

✓Discoverable commands 6/6

Commands are declared where an agent will look for them.

Makefile

pyproject.toml scripts

scripts/ directory

✓Environment config 4/4

.env.example documents what the app needs to run.

✓Pinned runtime version 2/2

The language runtime version is pinned.

Found rust-toolchain.toml

✓Reproducible environment 2/2

.devcontainer/devcontainer.json gives a known-good environment.

Verification loop 22/22 A+

Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy.

✓Tests exist 8/8

1159 test files against 1783 source files.

e.g. crates/headroom-core/tests/auth_mode.rs, crates/headroom-core/tests/cache_control.rs, crates/headroom-core/tests/ccr_backends.rs

✓Test command is discoverable 7/7

An agent can find and run `make test`.

✓Continuous integration 4/4

23 GitHub Actions workflows define what "passing" means.

✓Lint and format rules 3/3

pyproject.toml encodes the house style.

–Static type checking n/a

Not applicable — the Rust compiler type checks every build.

Context economy 13/20 B

Whether the repo fits in a context window, or fights it.

✓No committed build output 6/6

No generated directories committed.

✓.gitignore hygiene 3/3

.gitignore covers 178 patterns.

✗File sizes fit in context 0/6

10 source files are over 100KB.

A single file that fills the context window forces an agent to work from fragments, and it will confidently edit code it never saw. Splitting the worst offenders pays for itself immediately.

headroom/proxy/handlers/openai.py — 488KB

headroom/providers/opencode/_dist/entry.opencode.js — 453KB

headroom/cli/wrap.py — 332KB

✗Repository weight 4/5

About 75.9MB checked out, which is comfortable.

Here is your AGENTS.md

Drafted from what is actually in this repository: the install command from your lockfile, the commands you already declare, your real directory layout. Anything marked TODO needs a person. Save it at the root as AGENTS.md.

AGENTS.md — drafted for headroomlabs-ai/headroom

# AGENTS.md

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

## Setup

```
uv sync
```

## Commands

```
make help
make test          # run the test suite, must pass before any commit
make test-parity
make bench
make build-proxy
make build-wheel
```

## Layout

- `tests/`    834 source files
- `headroom/` 530 source files
- `crates/`   198 source files
- `sdk/`      55 source files
- `plugins/`  35 source files
- `scripts/`  33 source files

## Conventions

- Tests live alongside the code they cover, following `crates/headroom-core/tests/auth_mode.rs`.
- CI defines what passing means. See `.github/workflows/changelog-guard.yml`, and keep it green.
- TODO: add the two or three conventions a newcomer always gets wrong here.

## Gotchas

- `headroom/proxy/handlers/openai.py` is 488KB. It will not fit comfortably in context, so read it in parts.
- Copy `.env.example` before running anything that needs configuration.

---

Drafted by agentreadme.com from what is in this repository. Everything marked TODO
needs a human. Check it in as AGENTS.md at the root.

Open the raw markdown or curl -o AGENTS.md agentreadme.com/draft/headroomlabs-ai/headroom.md

Show the mark

The badge re-checks daily, so it keeps up as the repository changes. Use mark again to force it now.

[![agent ready](https://agentreadme.com/badge/headroomlabs-ai/headroom.svg)](https://agentreadme.com/headroomlabs-ai/headroom)

Other Python repositories, marked

vinta/awesome-python 81 A- NousResearch/hermes-agent 84 A- TheAlgorithms/Python 66 B yt-dlp/yt-dlp 54 C+ Significant-Gravitas/AutoGPT 63 B microsoft/markitdown 46 C

All Python repositories

Think this mark is wrong?

Every deduction above names the file it came from, so this can be settled by looking. If a check missed something, that is a rule worth fixing.

Open an issue, already filled in