Report · marked 26 Aug 2026

commaai/openpilot

An agent can work here, but it will waste turns finding its footing.

Python · 63,497 stars · 1,170 files · branch master

58 /100 B-

Instructions 2/27Whether the repo tells an agent how to behave before it starts guessing. Losing marks on agent instruction file and instruction quality.Setup 14/14Whether an agent can install the project and get it running without a human. Full marks.Verification loop 15/25Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy. Losing marks on test command is discoverable and static type checking.Context economy 15/20Whether the repo fits in a context window, or fights it. Losing marks on 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

Agent instruction file

Add an AGENTS.md at the root: what the project is, how to install, how to run, how to test, and the two or three conventions a newcomer always gets wrong.

Instruction quality

Instructions earn their keep by naming exact commands. 'Run the tests with `pnpm test`' beats three paragraphs of philosophy.

Test command is discoverable

Add a `test` script or a `test` target that runs the whole suite with no arguments. The convention is the interface — an agent tries `npm test` and `make test` before it tries reading your CI config.

The full marking

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

Instructions 2/27 F

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

✗Agent instruction file 0/12

None found. Every agent that opens this repo starts from zero.

Add an AGENTS.md at the root: what the project is, how to install, how to run, how to test, and the two or three conventions a newcomer always gets wrong.

Looked for AGENTS.md, CLAUDE.md, .github/copilot-instructions.md, .cursorrules

✗Instruction quality 0/12

Nothing to judge, since there are no instructions.

Instructions earn their keep by naming exact commands. 'Run the tests with `pnpm test`' beats three paragraphs of philosophy.

✗README as an entry point 2/3

README exists but never explains how to get the thing running.

Give the README an Install and a Usage heading with real commands under each. Agents pattern-match on those headings.

Setup 14/14 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.

scripts/ directory

–Environment config n/a

Not applicable — this reads as a library, with no environment to configure.

✓Pinned runtime version 2/2

The language runtime version is pinned.

Found .python-version

–Reproducible environment n/a

Not applicable — a library doesn't need a container to be worked on.

Verification loop 15/25 B-

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

✓Tests exist 8/8

128 test files against 752 source files.

e.g. openpilot/cereal/messaging/tests/__init__.py, openpilot/cereal/messaging/tests/test_messaging.py, openpilot/cereal/messaging/tests/test_pub_sub_master.py

✗Test command is discoverable 0/7

There's no obvious way to run the tests. Even if tests exist, an agent won't reliably find the entry point.

✓Continuous integration 4/4

9 GitHub Actions workflows define what "passing" means.

✓Lint and format rules 3/3

pyproject.toml encodes the house style.

✗Static type checking 0/3

No static type checking.

A type checker gives an agent an error message instead of a runtime surprise. It's the second-fastest feedback loop after the compiler.

Context economy 15/20 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 84 patterns.

✓File sizes fit in context 6/6

No source file is large enough to crowd out a context window.

✗Repository weight 0/5

About 2490MB checked out. Large enough that cloning and searching are both slow.

Large binaries and vendored trees slow every operation an agent performs. Git LFS or a separate assets repo keeps the working tree navigable.

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 commaai/openpilot

# AGENTS.md

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.

## Setup

```
uv sync
```

## Commands

```
ruff check .   # lint
```

## Layout

- `openpilot/` 666 source files
- `tools/`     64 source files
- `scripts/`   18 source files
- `docs/`      1 source file

## Conventions

- Tests live alongside the code they cover, following `openpilot/cereal/messaging/tests/__init__.py`.
- CI defines what passing means. See `.github/workflows/auto_pr_review.yaml`, and keep it green.
- TODO: add the two or three conventions a newcomer always gets wrong here.

---

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/commaai/openpilot.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/commaai/openpilot.svg)](https://agentreadme.com/commaai/openpilot)

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