thedotmack/claude-mem

Project overview

claude-mem preserves context for Claude Code across sessions by automatically capturing tool usage, generating semantic summaries, and injecting relevant context into future sessions. It addresses the loss of knowledge continuity when AI agent sessions end.

Project type: MCP · AI Agent
Use cases: Coding & Development · Automation
Deployment: Refer to project documentation
License: Apache-2.0

Best for

Developers using Claude Code who need an automated way to maintain and search agent context across multiple sessions.

Key capabilities

Compresses and generates semantic summaries from captured session data.
Makes relevant past summaries available and injects them into future sessions.

Limitations and risks

GPU requirements, cost dependencies, and telemetry policies are not documented in the available information.
While local execution is supported, the system features optional external cloud synchronization, which requires evaluation regarding data boundary requirements.

Getting started

Run the installer using a single command via npx and restart Claude Code to enable session capture and context injection.

Evidence and sources

README: Claude-Mem seamlessly preserves context across sessions by automatically capturing tool usage observations, generating semantic summaries, and making them available to future sess…
README: Persistent memory compression system built for <a href="https://claude.com/claude-code" target="_blank">Claude Code</a>.
README: Stable releases ship from `main` and are published to npm.
README: Mentioned in Awesome Claude Code
README: Persistent Memory** - Context survives across sessions

Reviewed at: 2026-07-17T04:37:27Z