Claude Mem
ActiveDescription
A Claude Code plugin that automatically captures coding session context, compresses it with AI, and injects relevant context back into future sessions for persistent memory.
Key Features
- Cross-session persistent memory - Automatically captures tool observations and generates semantic summaries, injecting relevant context into new sessions
- Progressive disclosure - Layered memory retrieval with token cost visibility for precise control over injected context volume
- Skill-based search - Query project history via mem-search skill with semantic project context retrieval
- Privacy control tags - Use <private> tags to exclude sensitive content from being stored in memory
- Web viewer UI - Real-time memory stream interface at localhost:37777 with ID-based citation of past observations
- Multi-IDE compatibility - Supports Claude Code, Gemini CLI, OpenCode, and OpenClaw Gateway coding environments
Use Cases
💡 Maintain context continuity in long-term projects, remembering architecture decisions and progress across sessions
💡 Share project memory in team collaboration, helping new members quickly understand development history and key decisions
💡 Track issue context in complex debugging scenarios, automatically recording investigation processes and root cause analysis
💡 Enhance coding agents by providing cross-session learning capabilities for tools like Claude Code
💡 Project knowledge accumulation, automatically archiving insights from daily coding sessions into a searchable knowledge base
Strengths & Limitations
✅ Strengths
- • Actively maintained, recent updates
- • High community interest (93.0k stars)
- • Permissive open-source license (Apache-2.0)
- • Responsive to issues, low backlog
Tags
Categories
Quick Start
# Install claude-mem (for Claude Code)
npx claude-mem install
# Or install for Gemini CLI
npx claude-mem install --ide gemini-cli
# Or install for OpenCode
npx claude-mem install --ide opencode
# Restart Claude Code or the target IDE
# Memory persists automatically across sessions, no manual intervention needed
# Visit http://localhost:37777 to view real-time memory stream