Plugin · Claude Code · LLM Integration

Tm42 Mnemograph

tm42-mnemograph is a Claude Code plugin for the Build phase that adds a graph-based persistent memory MCP so sessions retain structured knowledge across restarts.

by tm42 · github.com/tm42/mnemograph

Install when you want Claude Code to remember project knowledge in a graph MCP across sessions without manually reloading context every time.

3
GitHub stars
0
Installs
0
Community votes
One vote per signed-in builder - it helps surface the tools the community actually relies on.
Install

Add it to Claude Code

Install the plugin in Claude Code. One command, paste-ready.

Install the plugin
/plugin install tm42-mnemograph@tm42/mnemograph
Add to ClaudeUse the Agent APISkillselion is itself an MCP server - your agent can fetch this config directly.
Agent API

Built to be called by your agent

Skillselion is itself an MCP server. Your agent can pull this entry and a paste-ready install config straight from the API - no copy-paste.

Retrieve this entry with skillselion.get_details("plugin:tm42/mnemograph") and the paste-ready config with skillselion.get_install_config("plugin:tm42/mnemograph").

About

What it does

tm42-mnemograph is a Claude Code plugin that exposes mnemograph, a graph-based persistent yet lightweight memory MCP for coding agents. Indie builders tire of re-stating architecture, naming conventions, and past decisions at the start of every session; this bundle gives you a dedicated memory layer keyed to graph relationships instead of one long markdown file. The listing emphasizes persistent sessions, knowledge, and Claude integration—appropriate for agent-heavy workflows where continuity matters more than a single codegen task. Complexity sits at intermediate: you need MCP registration and comfort trusting an external memory graph. Use it journey-wide after the initial Build hookup whenever you iterate, support users, or prototype, because memory is not phase-locked. It complements skills and commands rather than replacing them: skills teach procedure, mnemograph remembers what already happened.

Highlights

  • Graph-based persistent memory MCP tailored for Claude Code sessions
  • Lightweight knowledge store across sessions without bloating the main repo
  • Category-tagged as memory with keywords: graph, persistent, sessions, knowledge
  • Single-plugin bundle (plugin count: 1) focused on mnemograph semantics
  • Fits builders who want structured recall rather than flat note dumps in CLAUDE.md

Why builders use it

Long agent threads forget prior decisions and you waste tokens re-uploading context that should survive between Claude Code sessions.

After you register the MCP, your agent can read and write lightweight graph memory so project knowledge persists across sessions without repeating the full brief.

At a glance

  • Type - Plugin in LLM Integration.
  • Adoption - 0 installs, 3 stars, 0 votes.

FAQ

Who is tm42-mnemograph for?

It is for Claude Code users who need cross-session memory—graph-linked facts and relationships—for ongoing product work.

When should I use tm42-mnemograph?

Use it when you start a new session and would otherwise paste long context, or when decisions and entities should accumulate over weeks of agent-assisted building.

How do I add tm42-mnemograph to my agent?

Install the plugin from tm42/mnemograph, enable the mnemograph MCP server in Claude Code settings, and verify the agent can query and update graph memory in a test session.

Discussion

Comments

Share how you use tm42-mnemograph, gotchas, or tips for other indie builders.

No comments yet - be the first to share how you use it.

This week for builders

Five minutes, every Monday — the tools, releases and tactics for shipping solo.

unsubscribe anytime.