claude-mem — What is it?

Claude-Mem is a Claude Code plugin that captures coding session data, compresses it with AI, and injects context into future sessions, enhancing continuity and knowledge retention.

⭐ 68,685 Stars 🍴 5,854 Forks TypeScript NOASSERTION Author: thedotmack
Source: Description per README View on GitHub →

Why it matters

Claude-Mem is gaining attention due to its innovative approach to preserving coding context across sessions, addressing the pain point of knowledge loss and continuity issues in coding workflows. Its use of AI for memory compression and context injection is a unique technical choice that stands out in the open-source landscape.

Source: Synthesis of README and project traits

Core Features

Persistent Memory

Automatically captures coding session data, compresses it with AI, and injects relevant context back into future sessions to maintain continuity of knowledge.

Source: Description per README
Progressive Disclosure

Retrieves context in a layered manner, showing only relevant information based on the user's current activity, with visibility into the cost of retrieving additional information.

Source: Description per README
Skill-Based Search

Enables querying of project history using a 'mem-search' skill, allowing users to search their project history with natural language.

Source: Description per README
Web Viewer UI

Provides a real-time memory stream through a web viewer UI accessible at http://localhost:37777.

Source: Description per README
Privacy Control

Supports the use of '' tags to exclude sensitive content from storage, enhancing privacy and security.

Source: Description per README

Architecture

The architecture of Claude-Mem involves lifecycle hooks for session management, a smart installer for dependency management, and a worker service for handling HTTP requests and providing a web viewer UI. The system uses a hybrid search architecture with a vector database for efficient search operations.

Source: Code tree + dependency files

Project Knowledge Graph

Knowledge graph: project (center) + core features (inner hexagons) + key dependencies (outer chips) Claude Agent SDKClaude Agent S… SQLite Bun Persistent Memory Progressive DisclosureProgressive Disclos… Skill-Based Search Web Viewer UI Privacy Control claude-mem Project Core feature Key dependency

Center: project; inner ring: core feature modules; outer ring: key dependencies. Auto-generated from core_features and tech_stack.key_deps.

Tech Stack

LanguageTypeScriptFrameworkNot enough information
Claude Agent SDKSQLiteBun
Not enough information
Source: Dependency files + code tree

Quick Start

Install with a single command: ```bash npx claude-mem install ```
Source: README Installation/Quick Start

Use Cases

Claude-Mem is suitable for developers using Claude Code who need to maintain continuity and knowledge retention across coding sessions. It is useful in scenarios where developers require quick access to past coding activities and context to enhance productivity and reduce errors.

Source: README

Strengths & Limitations

Strengths

  • Strength 1: Enhances coding continuity and knowledge retention.
  • Strength 2: Provides efficient context retrieval with privacy controls.

Limitations

  • Limitation 1: Limited information on infrastructure and deployment options.
  • Limitation 2: May require additional setup for certain IDEs or gateways.
Source: Synthesis of README, code structure and dependencies

Latest Release

v13.2.0 (2026-05-12): Added 'wowerpoint' skill for generating kawaii NotebookLM slide-deck PDFs, introduced server-beta event pipeline, and fixed bugs related to MCP server and Enviro.

Source: GitHub Releases

Verdict

Claude-Mem is a promising project for developers seeking to enhance coding continuity and knowledge retention. Its innovative approach to memory compression and context injection offers significant benefits for productivity and error reduction, particularly for those deeply engaged in Claude Code workflows.

Transparency Notice
This page is auto-generated by AI (a large language model) from the following public materials: GitHub README, code tree, dependency files and release notes. Analyzed at: 2026-05-24 23:35. Quality score: 85/100.

Data sources: README, GitHub API, dependency files