claude-memory CLAUDE.md

claude-memory CLAUDE.md is an instructions file for coding agents from NathanNorman/claude-memory. It costs 4,509 tokens per session, scanned A, original, MIT.

A repository instruction file for `claude-memory`, a persistent memory system for Claude Code. It documents the Python service, Node.js indexer, webhook pipeline, build commands, and tests.

In plain words
What is it for?
Use it to guide builds, type checks, tests, conversation indexing, and webhook-related development for `claude-memory`.
Why use it?
It gives an agent the project context and development commands needed to work in the repository consistently.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/nathannorman/claude-memory/claude-md
Clone the repo
git clone --depth 1 https://github.com/NathanNorman/claude-memory

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.

agentmods badge for claude-memory CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nathannorman/claude-memory/claude-md.svg)](https://agentmods.dev/instructions/nathannorman/claude-memory/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nathannorman/claude-memory/claude-md"><img src="https://agentmods.dev/badge/instructions/nathannorman/claude-memory/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,509 This file is loaded in full into every session.
When invoked 4,509 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04509 $0.04509
Opus 5 $0.02254 $0.02254
Sonnet 5 $0.00902 $0.00902
Haiku 4.5 $0.00451 $0.00451

Measured 5d ago against content hash 97b5537abbe7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

claude-memory 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 5d 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 · 295 lines

How it starts

The opening of the file, as written. The whole thing — 295 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.

What This Is

claude-memory is a persistent memory system for Claude Code, implemented as an MCP server. It has three main subsystems:

  1. Python MCP server (src/unified_memory_server.py) — The runtime that Claude Code connects to. Handles search, read, write, and status tools via stdio. This is what runs in production.
  2. Node.js indexer (src/indexer.ts and friends) — Batch indexer that scans conversation archives, chunks content, generates embeddings, and maintains the SQLite search index. Runs on-demand via reindex.
  3. Webhook pipeline (src/webhook_server.py, src/index_worker.py, src/mirror_manager.py) — FastAPI server that receives GitHub push webhooks and incrementally re-indexes changed files via bare git mirrors.

Build & Development Commands

# Node.js indexer
npm install          # Install dependencies
npm run build        # Build MCP server + doctor CLI (esbuild, single-file ESM bundles → dist/)
npm run build:doctor # Build doctor CLI only
npm run typecheck    # TypeScript type checking (tsc --noEmit)
npm test             # tsc compile + integration tests (node --test)

# Reindex (rebuild search index from memory files + conversation archives)
npx tsc && node dist/reindex-cli.js   # Backs up DB to ~/.claude-memory/backups/ before reindexing

# Python MCP server (uses venv at ~/.claude-memory/graphiti-venv/)
~/.claude-memory/graphiti-venv/bin/python3 src/unified_memory_server.py  # Run directly
python3 -c "import py_compile; py_compile.compile('src/unified_memory_server.py', doraise=True)"  # Syntax check

# Python tests (pytest-style, run individually)
~/.claude-memory/graphiti-venv/bin/python3 -m pytest scripts/test_conversation_parser.py -v
~/.claude-memory/graphiti-venv/bin/python3 -m pytest scripts/test_code_chunker.py -v
~/.claude-memory/graphiti-venv/bin/python3 -m pytest scripts/test_build_parser.py -v
~/.claude-memory/graphiti-venv/bin/python3 -m pytest scripts/test_cross_repo_deps.py -v
~/.claude-memory/graphiti-venv/bin/python3 -m pytest scripts/test_turboquant_backend.py -v
# Or run all Python tests at once:
~/.claude-memory/graphiti-venv/bin/python3 -m pytest scripts/test_*.py -v

# Database diagnostics
node dist/doctor-cli.js          # Diagnose (read-only)
node dist/doctor-cli.js --fix    # Diagnose and repair

# Retrieval benchmarks
~/.claude-memory/graphiti-venv/bin/python3 benchmarks/retrieval_bench.py

Read the full file on GitHub · 295 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.

  1. 5d ago First seen · 295 lines · 4,509 tokens per session scan A 97b5537abbe7

Subscribe to this mod's changes

claude-memory CLAUDE.md is an instructions file published in the GitHub repository NathanNorman/claude-memory (1 stars, last pushed 4mo ago), licensed MIT. It adds 4,509 tokens to every session, about $0.0225 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.