Claude Mem
Persistent context system for AI agents across sessions.
0 members list Claude Mem, unchanged over the last 12 weeks, data as of 21 November 2026
Members who list Claude Mem in their Stack, by week.
Members who list Claude Mem
Be the first to add Claude Mem
Nobody on Stackness runs Claude Mem yet. Add it to your stack and you're the first member running it.
About Claude Mem
Claude Mem is a persistent context system that captures what AI agents do during work sessions and makes that information available to the same agents in future sessions. The tool compresses session data with AI and injects relevant context back when needed, enabling agents to avoid repeating work and decisions. It works with Claude Code, Cursor, Codex, Gemini, and other AI agents and clients through an MCP server interface. The system stores observations in a structured, temporal database and uses vector search to recall information by meaning rather than exact matching.
Claude Mem is developed by thedotmack and is distributed under the Apache 2.0 license. The tool is written in TypeScript and includes both open-source and cloud-hosted components. It supports team collaboration through shared memory with per-project scopes and role-based access controls, allowing different team members to view and interact with memory at appropriate permission levels. The system can sync across devices and works offline-first with cloud synchronization.
Checked 16 November 2026.
Nobody on Stackness runs Claude Mem yet.
Sign up and add itPosts about Claude Mem
- Agent session portability: txcript, ACP and what a moved session loses
Agent session portability rewrites one agent's saved conversation into another's format. txcript does it for 11 agents; hooks, MCP and subagents stay behind.
- Agent memory vs documentation: which slot a memory plugin fills, and which one the repo does
Memory is what an agent noted and a plugin replays. Documentation is what you wrote, reviewed and committed. How each loads, and what to write down.