agentleFS

AGENTS.md examples from real projects

How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.

Best matches · from page 19Worked for most · soon
openinterpreterAGENTS.md

open-interpreter

openinterpreter/open-interpreter/AGENTS.md

with this fact in mind. It is often used to early exit out of tests that the author knew you would not be able to run given your sandbox limitations

Steady4 mentions in 2 weeks

1 project uses a version of this

69k4mo agoReviewMountCreate a free account to mount
mem0aiReads credentialsAGENTS.md

mem0

mem0ai/mem0/AGENTS.md

AGENTS.md` nearest the files you are editing before running any command. The linters, formatters, test runners, and line lengths genuinely differ per package, and using the wrong one fails

No other project uses it yet

69k2mo agoReviewMountCreate a free account to mount
mem0aiReads credentialsAGENTS.md

mem0

mem0ai/mem0/.github/AGENTS.md

Python | `agent-plugins-python-checks.yml` | Push to main (shared Python core and native/portable plugin directories), manual | Runtime tests on Python 3.10; full pytest on 3.11, 3.12; ruff + generated-package drift on 3.12 | | Agent

No other project uses it yet

69k2mo agoReviewMountCreate a free account to mount
mem0aiAGENTS.md

mem0 / integrations

mem0ai/mem0/integrations/AGENTS.md

agent-plugin-core/`. Check the table before running anything. | Directory | Package | Build | Lint | Test | |-----------|---------|-------|------|------| | `vercel-ai-sdk/` | `@mem0/vercel-ai-provider` | tsup (CJS+ESM) | ESLint + Prettier | jest + vitest (edge/node) | | `openclaw/` | `@mem0/openclaw-mem0` | tsup

69k2mo agoReviewMountCreate a free account to mount
mem0aiAGENTS.md

mem0 / mem0

mem0ai/mem0/mem0/AGENTS.md

commit make lint # ruff check make format # ruff format make sort # isort mem0/ make test # pytest tests/ make test-py-3.9 # pin a Python version (3.9 through 3.12) make install

69k2mo agoReviewMountCreate a free account to mount
mem0aiReads credentialsAGENTS.md

mem0 / mem0-ts

mem0ai/mem0/mem0-ts/AGENTS.md

memory. ## Commands ```bash pnpm install pnpm run build # tsup (CJS + ESM) pnpm run test # jest, all tests pnpm run test:unit # jest --coverage pnpm run test:integration # jest, needs MEM0

No other project uses it yet

69k2mo agoReviewMountCreate a free account to mount
mem0aiAGENTS.md

mem0 / skills

mem0ai/mem0/skills/AGENTS.md

repo through a TDD pipeline. Writes a feature branch plus `.mem0-integration/` artifacts. | | `mem0-test-integration/` | Verifies what the integrator produced, on the same branch. Read-only against the repo

No other project uses it yet

69k2mo agoReviewMountCreate a free account to mount
mem0aiAGENTS.md

mem0 / tests

mem0ai/mem0/tests/AGENTS.md

Python SDK tests (`tests/`) pytest suite for the `mem0/` package. ## Commands ```bash make install_all # optional deps; several tests need them make test # pytest tests/ make test

No other project uses it yet

69k2mo agoReviewMountCreate a free account to mount
mvanhornReads credentialsAGENTS.md

last30days-skill

mvanhorn/last30days-skill/AGENTS.md

invocation (`python3 scripts/last30days.py ...`) is a fallback for scripting, cron, and dev-time engine testing; label it as such, never as the primary path. - Slash commands don't pass shell mechanics

68k5mo agoReviewMountCreate a free account to mount
prometheusAGENTS.md

prometheus

prometheus/prometheus/AGENTS.md

skip histogram buckets when trimming feat(agent): fix ST append; add compliance RW sender test chore: fix emptyStringTest issues from gocritic ci: add statuses write permission to prombench workflow docs

No other project uses it yet

68k5d agoReviewMountCreate a free account to mount
apacheAGENTS.md

echarts

apache/echarts/AGENTS.md

TypeScript-first charting library. Most runtime code lives in `src/`, while build scripts, test utilities, and packaging logic live alongside it in dedicated top-level folders. One thing worth knowing

No other project uses it yet

67k4y agoReviewMountCreate a free account to mount
xtekkyReads credentialsAGENTS.md

gpt4free

xtekky/gpt4free/AGENTS.md

starting. - Keep changes small, focused, and consistent with the surrounding code. - Add or update tests when behaviour changes. Prefer the existing `unittest` style under `etc/unittest/` and `tools/dev_pipeline/tests/`. - Run the checks

Steady10 mentions in 2 weeks

No other project uses it yet

67k16mo agoReviewMountCreate a free account to mount
facebookAGENTS.md

docusaurus

facebook/docusaurus/AGENTS.md

components, and theme overrides - `_dogfooding/` - Hidden docs, blog and pages plugin instances for dogfooding, testing features and edge cases, making it easier to review on PR deploy previews ### Writing documentation

No other project uses it yet

67k9d agoReviewMountCreate a free account to mount
ChrisTitusTechReads credentialsAGENTS.md

winutil

ChrisTitusTech/winutil/AGENTS.md

edited directly. 4. **Never fabricate.** Do not invent file paths, function names, command output, test results, commit hashes, or API behavior. Read the file or run the command. 5. **Disagree

Steady2 mentions in 2 weeks

No other project uses it yet

66k5mo agoReviewMountCreate a free account to mount
coollabsioReads credentialsAGENTS.md

coolify

coollabsio/coolify/AGENTS.md

coolify (app, which also runs Reverb WebSockets and the terminal server), postgres, redis, vite, testing-host, mailpit, minio. ```bash # One dev instance per git branch (containers, volumes, VMs named after

66k46d agoReviewMountCreate a free account to mount
warpdotdevAGENTS.md

warp

warpdotdev/warp/AGENTS.md

endpoint (default: `http://localhost:8080`) - `WS_SERVER_URL` - WebSocket endpoint (default: `ws://localhost:8080/graphql/v2`) ### Testing - `cargo nextest run --no-fail-fast --workspace` - Run tests with nextest - `cargo test

Steady9 mentions in 2 weeks

2 projects use a version of this

66k12d agoReviewMountCreate a free account to mount
webpackDeletes or force-pushesAGENTS.md

webpack

webpack/webpack/AGENTS.md

with a short plan before the first edit**: - **Goal as a check**: "add validation" → "tests for invalid inputs fail, then pass"; "fix the bug" → "a test reproduces it, then passes

No other project uses it yet

66k27d agoReviewMountCreate a free account to mount
2dustAGENTS.md

v2rayNG

2dust/v2rayNG/AGENTS.md

exception; agent inference cannot. - `Task scope` is the named files and behavior plus dependency, test, or build edits that a compiler or required validation proves necessary. Every other change

Steady10 mentions in 2 weeks

No other project uses it yet

66k4y agoReviewMountCreate a free account to mount
traefikAGENTS.md

traefik

traefik/traefik/AGENTS.md

generate-webui` (Docker required) — they are not meant to be hand-edited. - `integration/` — integration tests; reusable fixtures under `integration/fixtures/`. - `docs/content/` — MkDocs sources for the public documentation. ## Before you edit Read

66k4d agoReviewMountCreate a free account to mount
scrapyAGENTS.md

scrapy

scrapy/scrapy/AGENTS.md

mypy` and `tox -e pylint`, and `tox -e docs` and `tox -e docs-tests` as well if you touched docs or docstrings. CI runs these first and skips the test

No other project uses it yet

65k2mo agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

About AGENTS.md

What is AGENTS.md?

An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.

Where does it go?

At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.

What should it contain?

Setup and test commands, code style, and the rules a new contributor would need to know.

Does Claude Code read it?

Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.