AGENTS.md@benchmarksA

AGENTS.md@benchmarks from basicmachines-co/basic-memory is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add basicmachines-co/basic-memory/benchmarks/AGENTS.md@git:20261024.3d433fd

Pins git:20261024.3d433fd in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
basicmachines-co/basic-memory
Path
benchmarks/AGENTS.md
Versions recorded
6
Latest version
git:20261024.3d433fd, committed Oct 24, 2026
First version recorded
Jun 25, 2026
Size
5,823 bytes
Repository stars
4,440
License
AGPL-3.0

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

# AGENTS.md - Basic Memory benchmarks guide

## Project Overview

`basic-memory-benchmarks` is the benchmark harness within Core's `/benchmarks`
directory for comparing Basic Memory against other memory systems.

Primary goals:
- Deterministic retrieval benchmarks
- End-to-end QA scoring with fixed answerer and judge models
- Public, reproducible artifact publication (including provenance metadata)

The benchmark package keeps its own `pyproject.toml` and lockfile so benchmark
dependencies do not pollute the Core product environment.

## Build / Test Commands

- Install: `uv sync --group dev`
- Run tests: `uv run pytest -q`
- Lint: `uv run ruff check .`
- Type check: `uv run pyright`

Recommended local gate before pushing:
1. `uv run pytest -q`
2. `uv run ruff check .`
3. `uv run pyright`

## Benchmark Commands

CLI entrypoint: `uv run bm-bench ...`

Dataset and conversion:
- `uv run bm-bench datasets fetch --dataset locomo`
- `uv run bm-bench convert locomo --dataset-path benchmarks/datasets/locomo/locomo10.json --output-dir benchmarks/generated/locomo`
- `bash benchmarks/datasets/beam/download.sh` (BEAM data is never vendored; sparse clone)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add basicmachines-co/basic-memory/benchmarks/AGENTS.md@sha256:9255b9280ebd4b2a

The line at the top of this page pins the label git:20261024.3d433fd, 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_hj6ese3vyfxdbb47.svg)](https://markdownregistry.com/a/art_hj6ese3vyfxdbb47)

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

Versions

The registry has recorded 6 versions of this file, between Jun 25, 2026 and Oct 24, 2026, about one every 24 days.

versioncommittedcommitsizeaudit
git:20261024.3d433fd latest2026-10-24 3d433fd 5,823 BA view · diff
git:20260831.54088a12026-08-31 54088a1 5,550 BA view · diff
git:20260831.e4cc1fa2026-08-31 e4cc1fa 5,837 BA view · diff
git:20260824.f84ea722026-08-24 f84ea72 5,097 BA view · diff
git:20260823.a9f4e082026-08-23 a9f4e08 5,074 BA view · diff
git:20260625.cb6bc322026-06-25 cb6bc32 4,914 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 (5823 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

basicmachines-co/basic-memory · 4,440 stars · license AGPL-3.0 · pushed 2026-11-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_hj6ese3vyfxdbb47
GET https://markdownregistry.com/api/v1/resolve?ref=basicmachines-co/basic-memory/benchmarks/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/9255b9280ebd4b2a5d62e1950621d464b70810aa2bf5bab1db253c2e0fd70e1c

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 basicmachines-co/basic-memory

adversarial-review SKILL.md skill
basicmachines-co/basic-memory · .agents/skills/adversarial-review/SKILL.md · Cross-vendor adversarial code review of the current branch. Two different model families (Claude + Codex/GPT) review…
git:20260530.4ea03d2 · audit A · 4,440 stars
cmux-markdown SKILL.md skill
basicmachines-co/basic-memory · .agents/skills/cmux-markdown/SKILL.md · Open markdown files in a formatted viewer panel with live reload. Use when you need to display plans, documentation, or…
git:20260823.9007836 · audit A · 4,440 stars
cmux-settings SKILL.md skill
basicmachines-co/basic-memory · .agents/skills/cmux-settings/SKILL.md · View and edit cmux settings in ~/.config/cmux/cmux.json. Use when the user wants to change cmux preferences…
git:20260823.9007836 · audit A · 4,440 stars
cmux-workspace SKILL.md skill
basicmachines-co/basic-memory · .agents/skills/cmux-workspace/SKILL.md · Work inside the current cmux workspace and terminal. Use for cmux workspace, current workspace, caller surface, panes…
git:20260823.9007836 · audit B · 4,440 stars
cmux SKILL.md skill
basicmachines-co/basic-memory · .agents/skills/cmux/SKILL.md · End-user control of cmux topology and routing (windows, workspaces, panes/surfaces, focus, moves, reorder, identify…
git:20260823.9007836 · audit A · 4,440 stars
code-review SKILL.md skill
basicmachines-co/basic-memory · .agents/skills/code-review/SKILL.md · Use when reviewing Basic Machines code for house style, architecture risk, pre-merge hardening, or whether a change…
git:20260609.03ba268 · audit A · 4,440 stars
fix-pr-issues SKILL.md skill
basicmachines-co/basic-memory · .agents/skills/fix-pr-issues/SKILL.md · Use when addressing Basic Memory pull request feedback, failed checks, or Codex review blockers, then re-running the…
git:20260718.85ce762 · audit A · 4,440 stars
infographics SKILL.md skill
basicmachines-co/basic-memory · .agents/skills/infographics/SKILL.md · Use when generating Basic Memory PR, changelog, release, or weekly images from Codex.
git:20260610.93494b8 · audit A · 4,440 stars
instrumentation SKILL.md skill
basicmachines-co/basic-memory · .agents/skills/instrumentation/SKILL.md · Add Pydantic Logfire observability to applications. Use this skill whenever the user asks to "add logfire", "instrument…
git:20260408.d7f3f6a · audit A · 4,440 stars
pr-create SKILL.md skill
basicmachines-co/basic-memory · .agents/skills/pr-create/SKILL.md · Use when explicitly creating or updating a Basic Memory pull request. This compatibility entry point delegates the full…
git:20260718.85ce762 · audit A · 4,440 stars
pr-description SKILL.md skill
basicmachines-co/basic-memory · .agents/skills/pr-description/SKILL.md · Use when opening or updating a GitHub PR - writes a detailed PR description that explains what changed, why it changed…
git:20260718.85ce762 · audit A · 4,440 stars
pr-review-loop SKILL.md skill
basicmachines-co/basic-memory · .agents/skills/pr-review-loop/SKILL.md · Enforce the Basic Machines GitHub PR review loop before merging. Use whenever Codex is preparing to merge…
git:20260718.85ce762 · audit A · 4,440 stars

Every file in basicmachines-co/basic-memory

Other files named AGENTS.md@benchmarks

AGENTS.md@benchmarks AGENTS.md file
jasonxudeveloper/nino · benchmarks/AGENTS.md
git:20261030.e7612a4 · audit A · 652 stars
AGENTS.md@benchmarks AGENTS.md file
borda/ai-rig · benchmarks/AGENTS.md
git:20260814.b9c6b5a · audit A · 30 stars

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