claude-persistent-memory CLAUDE.md

claude-persistent-memory CLAUDE.md is an instructions file for coding agents from MIMI180306/claude-persistent-memory. It costs 867 tokens per session, scanned A, original, MIT.

Project instructions for a persistent memory system for Claude Code. It stores information across conversations using keyword and meaning-based search, with services that organise and cluster saved memories.

In plain words
What is it for?
Use them when running or maintaining the memory system, including its embedding service, language-model service, MCP server, vector rebuilds, and Claude Code hooks.
Why use it?
They explain the separate services and automatic hooks needed for Claude Code to save, retrieve, validate, and inject useful past context.

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/mimi180306/claude-persistent-memory/claude-md
Clone the repo
git clone --depth 1 https://github.com/MIMI180306/claude-persistent-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-persistent-memory CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mimi180306/claude-persistent-memory/claude-md.svg)](https://agentmods.dev/instructions/mimi180306/claude-persistent-memory/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mimi180306/claude-persistent-memory/claude-md"><img src="https://agentmods.dev/badge/instructions/mimi180306/claude-persistent-memory/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 867 This file is loaded in full into every session.
When invoked 867 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 $0.00867 $0.00867
Opus 5 $0.00434 $0.00434
Sonnet 5 $0.00173 $0.00173
Haiku 4.5 $0.00087 $0.00087

Measured 5d ago against content hash 0cc6fde0f1af, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-persistent-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 · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 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

A persistent memory system for Claude Code — hybrid BM25 + vector semantic search with LLM-driven structuring and automatic clustering. It gives Claude Code sessions long-term memory that persists across conversations.

Commands

npm run embedding-server   # Start embedding service (TCP :23811, loads bge-m3 ~2GB RAM)
npm run llm-server         # Start LLM proxy service (TCP :23812, requires Azure OpenAI)
npm run mcp-server         # Start MCP server (stdio, used by Claude Code)
npm run rebuild-vectors    # Rebuild all embeddings (after model change)

Both TCP servers must be running for full functionality. The MCP server is configured in .mcp.json and launched by Claude Code automatically. Hooks are configured in .claude/settings.json.

Architecture

The system has two retrieval channels:

Pull channel — MCP server (services/memory-mcp-server.js) exposes 4 tools (memory_search, memory_save, memory_validate, memory_stats) that Claude invokes on demand via stdio.

Push channel — 5 hooks auto-inject memory context into Claude's conversation:

  • UserPromptSubmit → embeds user query, searches, prepends results to prompt via stdout
  • PreToolUse → searches on Edit/Write/Bash tool context, injects via additionalContext
  • PostToolUse → searches on tool context + result, injects via additionalContext
  • PreCompact → spawns compact-analyzer.js in background (non-blocking), which sends full transcript to LLM for memory extraction
  • SessionEnd → incremental transcript analysis + auto-clustering + mature cluster merging

Internal service communication

Hooks and MCP server communicate with the two TCP servers via lib/embedding-client.js and lib/llm-client.js. Both clients use raw TCP sockets with newline-delimited JSON protocol.

Data layer

lib/memory-db.js is the core module — manages SQLite database with three virtual tables:

  • memories — main table with structured content, confidence scores, cluster assignments
  • memories_fts — FTS5 full-text search (BM25 ranking, synced via triggers)
  • memories_vec — sqlite-vec cosine similarity (1024-dim bge-m3 embeddings)

Read the full file on GitHub · 66 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 · 66 lines · 867 tokens per session scan A 0cc6fde0f1af

Subscribe to this mod's changes

claude-persistent-memory CLAUDE.md is an instructions file published in the GitHub repository MIMI180306/claude-persistent-memory (8 stars, last pushed 6mo ago), licensed MIT. It adds 867 tokens to every session, about $0.0043 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.

Related

Other instructions, from other repositories