explaingit

thedotmack/claude-mem

🔥 Hot76,583TypeScriptAudience · developerComplexity · 3/5ActiveLicenseSetup · moderate

TLDR

A plugin that gives Claude Code persistent memory across sessions by recording your work, summarizing it with AI, and automatically surfacing relevant context in future sessions.

Mindmap

mindmap
  root((repo))
    What it does
      Persistent memory
      Auto-summarization
      Context injection
    How it works
      Hooks into Claude Code
      Vector database storage
      Semantic search
    Use cases
      Long-running projects
      Multi-project switching
      Avoid re-explaining
    Tech stack
      TypeScript
      Node.js
      ChromaDB
    Features
      Web interface
      Search skill
      Project-scoped

Things people build with this

USE CASE 1

Resume work on long-running projects without re-explaining project structure or past decisions to Claude.

USE CASE 2

Switch between multiple projects and have Claude automatically recall relevant context for each one.

USE CASE 3

Browse your entire work history and search past sessions through a local web interface.

Tech stack

TypeScriptNode.jsChromaDBClaude SDK

Getting it running

Difficulty · moderate Time to first run · 30min

Requires Claude API key and ChromaDB setup; plugin installation into Claude Code environment may need configuration.

Use freely for any purpose including commercial. Keep the notice and disclose changes to the patent grant.

In plain English

Claude-Mem is a plugin for Claude Code, Anthropic's AI coding assistant, that gives it a persistent memory across separate work sessions. Normally when you close a Claude Code session and start a new one, the AI has no memory of what you worked on before. Claude-Mem solves this by automatically recording what Claude does during each session, compressing those observations into concise summaries using AI, and then injecting the most relevant pieces of that history back into future sessions so Claude has context about your project without you needing to re-explain everything. The system works by hooking into Claude Code's plugin system. A background worker process monitors each session, captures tool usage and observations, and stores them in a local database using ChromaDB, which is a vector database that allows semantic search. When a new session starts, the plugin retrieves the most relevant past observations based on what you are currently working on and surfaces them at the top of the context. There is also a web interface running locally that lets you browse your memory stream in real time, and a search skill that lets you explicitly query past work. You would use this if you work on long-running projects with Claude Code and find yourself constantly re-explaining project structure, past decisions, or ongoing tasks at the start of each session. It is also useful when switching between multiple projects, since the memory is project-scoped. The plugin supports Claude Code, Gemini CLI, and OpenCode. The tech stack is TypeScript running on Node.js 18 or later, with ChromaDB for vector storage and Claude's own agent SDK used to perform the AI-powered compression and summarization of observations. Installation is a single npx command.

Copy-paste prompts

Prompt 1
Install claude-mem and set it up to track my Claude Code sessions, then show me how to view my memory stream in the web interface.
Prompt 2
How do I configure claude-mem to be project-scoped so it only surfaces memories relevant to my current project?
Prompt 3
Use the search skill in claude-mem to find all observations from my past sessions about database schema decisions.
Prompt 4
Show me how claude-mem compresses and summarizes my work observations using AI so I can understand what context it will inject into future sessions.
Open on GitHub → Explain another repo

Generated 2026-05-18 · Model: sonnet-4-6 · Verify against the repo before relying on details.