agentleFS
yantrikosyantrikos/yantrikdb-mcp/AGENTS.md

yantrikdb-mcp

AGENTS.md24 starsChanged 10 days agoMITView on GitHub

Guidance for AI coding agents working in this repository. An MCP server giving MCP-compatible AI agents (Claude Code, Cursor, Windsurf, and others) persistent, structured, queryable memory across sessions, backed by the YantrikDB Rust engine. MIT license; the engine dependency is Apache-2.0. Use Python 3.10 through 3.13 (the yantrikdb engine ships native wheels for those versions; 3.14 may not install yet). This installs the server, its runtime dependencies, and pytest. Only tests/ is collected by default (see pyproject.toml). test_v14.py at the…

  • Installs packages
  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repositoryOne other file it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use Python 3.10 through 3.13 (the yantrikdb engine ships native wheels for those versions.

    line 14
  2. Very specific:

    Only tests/ is collected by default (see pyproject.toml).

    line 32
  3. Very specific:

    If you add behavior, add or extend a test in tests/.

    line 48

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AGENTS.md

Guidance for AI coding agents working in this repository.

What this is

An MCP server giving MCP-compatible AI agents (Claude Code, Cursor, Windsurf, and others) persistent, structured, queryable memory across sessions, backed by the YantrikDB Rust engine. MIT license; the engine dependency is Apache-2.0.

Setup

Use Python 3.10 through 3.13 (the yantrikdb engine ships native wheels for those versions; 3.14 may not install yet).

python3.12 -m venv .venv
source .venv/bin/activate   # Windows: .venv\Scripts\activate
python -m pip install -U pip
pip install -e ".[dev]"

This installs the server, its runtime dependencies, and pytest.

Run tests

pytest

Only tests/ is collected by default (see pyproject.toml). test_v14.py at the repo root is a heavier integration check against the engine — run it explicitly with pip install -e ".[torch]" first.

Run the server locally

yantrikdb-mcp --help
yantrikdb-mcp --version

Stdio mode (the default, used by Cursor/Claude Code) needs no extra flags.

Before opening a PR

  1. Branch from main.
  2. If you add behavior, add or extend a test in tests/. Doc-only changes don't need one.
  3. Open the PR against yantrikos/yantrikdb-mcp with a short description of the change.

Full contributor guide: CONTRIBUTING.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.