---
name: "Preserve agent session context with Claude Mem"
slug: "preserve-agent-session-context-with-claude-mem"
description: "Capture coding-agent sessions, compress the useful decisions and context, and inject relevant memory into future runs so long-running repository work does not restart cold."
github_stars: 74480
verification: "security_reviewed"
source: "https://github.com/thedotmack/claude-mem"
author: "thedotmack"
publisher_type: "open_source"
category: "Library & API Reference"
framework: "Multi-Framework"
tool_ecosystem:
  github_repo: "thedotmack/claude-mem"
  github_stars: 74480
  npm_package: "claude-mem"
  npm_weekly_downloads: 16072
---

# Preserve agent session context with Claude Mem

Capture coding-agent sessions, compress the useful decisions and context, and inject relevant memory into future runs so long-running repository work does not restart cold.

## Prerequisites

Claude Mem; supported coding-agent runtime such as Claude Code, OpenClaw, Codex, Gemini, Copilot, OpenCode, or compatible agent workflow

## Installation

Requirements and caveats from upstream:
- <img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node">
- **Node.js**: 18.0.0 or higher
- **uv**: Python package manager for vector search (auto-installed if missing)

Basic usage or getting-started notes:
- <a href="#quick-start">Quick Start</a> •
- Claude-Mem seamlessly preserves context across sessions by automatically capturing tool usage observations, generating semantic summaries, and making them available to future sessions. This enables Claude to maintain...
- **[Installation Guide](https://docs.claude-mem.ai/installation)** - Quick start & advanced installation

- Source: https://github.com/thedotmack/claude-mem
- Extracted from upstream docs: https://raw.githubusercontent.com/thedotmack/claude-mem/HEAD/README.md

## Documentation

- https://claude-mem.ai

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/preserve-agent-session-context-with-claude-mem/)