What is supermem CLAUDE.md?

A set of Claude Code instructions for working on the supermem project. It documents the project, its build and setup commands, its supported memory paths, and important limitations.

It is for guiding Claude Code when developing or operating supermem, including installation, setup, chat, model-server, and MCP commands. It also explains that the supported memory surface uses local SQLite-based retrieval with optional vectors.

It gives an agent project-specific rules and commands instead of making it guess how to install, run, or modify the code. It also warns that some memory and executor features are restricted or disabled.

How lamenting-hawthorn/supermem configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lamenting-hawthorn/supermem. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/lamenting-hawthorn/supermem/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/lamenting-hawthorn/supermem

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/lamenting-hawthorn/supermem/claude-md/github.svg)](https://agentmods.dev/instructions/lamenting-hawthorn/supermem/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/lamenting-hawthorn/supermem/claude-md"><img src="https://agentmods.dev/badge/instructions/lamenting-hawthorn/supermem/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/lamenting-hawthorn/supermem/claude-md"><img src="https://agentmods.dev/badge/instructions/lamenting-hawthorn/supermem/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,952 This file is loaded in full into every session.

When invoked 1,952 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01952	$0.01952
Opus 5	$0.00976	$0.00976
Sonnet 5	$0.00390	$0.00390
Haiku 4.5	$0.00195	$0.00195

Measured 8d ago against content hash 99e046be7eb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

supermem CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

supermem — persistent AI memory without RAG. The supported MCP memory surface uses lifecycle-aware SQLite FTS, graph, and optional vector retrieval (tiers 1–3). Raw-vault Agent navigation (Tier 4) is disabled pending a source-aware lifecycle broker, so direct Agent.chat fails closed before model, tool, or executor use. The retained restricted executor is not a hostile-code sandbox and is not a supported MCP memory path.

Build & Run Commands

All commands use uv (not pip) and are orchestrated via Makefile.

# Install
make install              # deps + LM Studio (macOS)
make install-api          # deps only (API mode / CI)

# Setup
make setup-cli            # choose memory directory (CLI)
make setup                # choose memory directory (GUI)

# Run
make chat-cli             # interactive terminal REPL
make run-agent            # start local model server (MLX on macOS, vLLM on Linux)
make serve-mcp            # MCP server (stdio, for Claude Desktop)
make serve-mcp-http       # Loopback MCP HTTP; SUPERMEM_API_KEY required
make generate-mcp-json    # generate mcp.json config for Claude Desktop

# Quick start
make quickstart           # API mode (OpenRouter, no GPU)
make quickstart-local     # local model (Apple Silicon / CUDA GPU)

# Data import
make memory-wizard        # interactive import wizard
make connect-memory CONNECTOR=chatgpt SOURCE=/path/to/export.zip

# Privacy
make add-filters          # add privacy filter rules
make reset-filters        # clear filters

Testing

uv run pytest tests/ -v                                    # run all tests
uv run pytest tests/test_engine.py -v                      # run single test file
uv run pytest tests/ --cov=agent --cov-report=term-missing # with coverage

CI runs pytest + black formatting checks (.github/workflows/ci.yml).

Architecture

Workspace Structure

Read the full file on GitHub · 182 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 182 lines · 1,952 tokens per session scan A 99e046be7eb8

Subscribe to this mod's changes

supermem CLAUDE.md is an instructions file published in the GitHub repository lamenting-hawthorn/supermem (1 stars, last pushed 18d ago), licensed Apache-2.0. It adds 1,952 tokens to every session, about $0.0098 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

supermem: Instructions file for Claude Code