thedotmack/claude-mem

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

What it solves

Claude-Mem provides persistent memory for Claude Code, allowing the AI to maintain continuity of knowledge across different sessions. It prevents the loss of project context when sessions end or reconnect, ensuring that observations and tool usage from previous interactions are preserved.

How it works

The system uses a combination of lifecycle hooks (SessionStart, UserPromptSubmit, PostToolUse, Stop, and SessionEnd) to capture observations and generate semantic summaries. These are stored in a SQLite database and a Chroma vector database for hybrid semantic and keyword search. A local worker service manages an HTTP API and a web viewer UI, while a specialized "mem-search" skill allows Claude to query project history using a token-efficient 3-layer workflow (search, timeline, and get_observations).

Who it’s for

Developers using Claude Code, OpenCode, or Antigravity CLI who want their AI assistant to remember project-specific details, bugs, and decisions across multiple sessions.

Highlights

  • Persistent Memory: Context survives across sessions automatically.
  • Progressive Disclosure: A layered retrieval system that saves tokens by filtering results before fetching full details.
  • Hybrid Search: Combines full-text and vector search via SQLite and Chroma.
  • Web Viewer UI: Provides a real-time stream of the AI's memory.
  • Privacy Control: Supports <private> tags to exclude sensitive content from storage.
  • MCP Tool Integration: Provides four Model Context Protocol tools for intelligent memory retrieval.

Related

  • Project
    supermemoryai/claude-supermemory

    A Claude Code plugin that gives AI agents persistent memory across sessions and projects using Supermemory, allowing them to remember previous work and shared team knowledge.

  • Project
    JamesShi96/project-butler

    A persistent memory system for AI coding assistants that uses a structured Markdown-based memory stack to maintain project context, rules, and progress across sessions.

  • Project
    obra/private-journal-mcp

    An MCP server that gives Claude private, local-first journaling and semantic search capabilities to maintain persistent memory across conversations.

  • Project
    JuliusBrussee/cavemem

    A cross-agent persistent memory system for coding assistants that uses compressed local storage and MCP to allow AI agents to remember information across sessions.

  • Project
    Lyellr88/marm-memory

    A persistent local memory server for AI agents using the Model Context Protocol (MCP), providing shared context, code graphs, and concept graphs across sessions.