light-mem

Lightweight persistent memory for Claude Code and OpenCode.

Quick Start • How It Works • Search Tools • Documentation • Configuration • Troubleshooting • License

Light-Mem seamlessly preserves context across sessions by automatically capturing tool usage observations, generating semantic summaries, and making them available to future sessions. Works with Claude Code via lifecycle hooks and with OpenCode via a plugin installed into ~/.config/opencode/plugins — both editors POST to the same shared worker.

---

Quick Start

Install with a single command:

npx light-mem install

Or install from the plugin marketplace inside Claude Code:

/plugin marketplace add light-mem/light-mem

/plugin install light-mem

Restart Claude Code. Context from previous sessions will automatically appear in new sessions.

Note: Light-Mem is also published on npm, but npm install -g light-mem installs the SDK/library only — it does not register the plugin hooks or set up the worker service. Always install via npx light-mem install or the /plugin commands above.

Key Features:

• 🧠 Persistent Memory - Context survives across sessions
• 🖥️ Claude Code + OpenCode - Works with both editors; OpenCode support resurrected in this release
• 📊 Progressive Disclosure - Layered memory retrieval with token cost visibility
• 🔍 Skill-Based Search - Query your project history with mem-search skill
• 🌐 Web Viewer UI - Real-time memory stream on the worker port (run npx light-mem status to see the URL)
• 🔒 Privacy Control - Use <private> tags to exclude sensitive content from storage
• ⚙️ Context Configuration - Fine-grained control over what context gets injected
• 🤖 Automatic Operation - No manual intervention required
• 🔗 Citations - Reference past observations with IDs (access via /api/observation/{id} on the worker port, or view all in the web viewer)
• 🧪 Beta Channel - Try experimental features like Endless Mode via version switching

---

Documentation

📚 View Full Documentation - Browse on GitHub

Getting Started

• Installation Guide - Quick start & advanced installation
• Usage Guide - How Light-Mem works automatically
• Search Tools - Query your project history with natural language
• Beta Features - Try experimental features like Endless Mode

Best Practices

• Context Engineering - AI agent context optimization principles
• Progressive Disclosure - Philosophy behind Light-Mem's context priming strategy

Architecture