💡 Summary
Claude Recall is a local memory engine that enables Claude Code to learn and adapt from user interactions over time.
🎯 Target Audience
🤖 AI Roast: “Powerful, but the setup might scare off the impatient.”
Risk: Low. Review: shell/CLI command execution; dependency pinning and supply-chain risk. Run with least privilege and audit before enabling in production.
Claude Recall
Persistent, local memory for Claude Code — powered by native Claude Skills.
Claude Recall is a local memory engine + MCP server that gives Claude Code something it's missing by default: the ability to learn from you over time.
Your preferences, project structure, workflows, corrections, and coding style are captured automatically and applied in future sessions — securely stored on your machine.
TL;DR Claude Recall stores and searches your past preferences and project knowledge. Install it → restart Claude Code → Claude knows when to search memory via native Skills integration.
🚀 Features
🌱 Continuous Learning (Local SQLite)
Claude learns your:
- coding patterns
- tool preferences
- corrections
- architectural decisions
- workflow habits
Everything stays local.
🎯 Native Claude Skills Integration
Claude Recall uses Claude Code's native Skills system for seamless memory guidance.
How it works
- No hooks required — Skills are built into Claude Code
- Non-blocking — Claude decides when to search/store based on skill guidance
- Self-directed — Claude understands when memory is relevant to the task
- Zero latency — No external processes or enforcement overhead
What the Skill teaches Claude
- Search memory before writing/editing code
- Apply learned conventions and avoid past mistakes
- Capture corrections when users fix mistakes
- Store learning cycles (fail → fix → success)
The skill is automatically installed to .claude/skills/memory-management/SKILL.md on package install.
📂 Project-Scoped Knowledge
Each project gets its own memory namespace:
- architecture
- tech stack
- conventions
- past decisions
- known pitfalls
- previous fixes
- preferences unique to that codebase
Switch projects → Claude switches memory.
🔌 Zero Cloud Storage
- All memory stored locally in SQLite
- No cloud sync
- No telemetry
- Entire system works offline
💻 Claude Code–Native Integration
Claude Recall integrates via:
- MCP server — search, store, retrieve memories
- Native Skills — guides Claude on when to use memory tools
- Automatic capture — extracts preferences from conversations
Claude knows to search memory before significant actions, with no enforcement overhead.
⚡ Quick Start
Requirements
| Component | Version | Notes | | --------- | ----------------------- | --------------------------- | | Node.js | 20+ | required for better-sqlite3 | | OS | macOS / Linux / Windows | WSL supported |
Install (per project)
cd your-project npm install claude-recall # Check installed version: npx claude-recall --version # Show activation instructions: npx claude-recall setup
Upgrade
npm uninstall claude-recall && npm install claude-recall
Activate
Register MCP server:
claude mcp add claude-recall -- npx -y claude-recall@latest mcp start
Then restart your terminal or Claude Code session.
Already registered? Remove first:
claude mcp remove claude-recall
Verify
In Claude Code, ask: "Search my memories"
Claude should call mcp__claude-recall__search. If it works → you're ready.
🧠 How It Works (High-Level)
Claude Recall consists of:
1. Local Memory Engine (SQLite)
Stores and evolves preferences, patterns, decisions, corrections.
2. MCP Server
Exposes memory tools to Claude Code:
mcp__claude-recall__search— find relevant memoriesmcp__claude-recall__store_memory— save new knowledgemcp__claude-recall__retrieve_memory— get specific memories
3. Native Claude Skill
Teaches Claude when and how to use memory:
- Search before writing/editing code
- Store corrections and learning cycles
- Apply preferences and patterns
🔐 Security & Privacy
Claude Recall is built for local-first workflows:
- SQLite memory never leaves your machine
- No external services required
- No prompts, code, or memory content is transmitted
- Full transparency via CLI (
list,inspect,export)
Full details in /docs/security.md.
📚 Full Documentation
All docs in /docs:
- Installation
- Quickstart
- Architecture
- Learning Loop
- Memory Types
- CLI Reference
- Skills Integration
- Project Scoping
- Troubleshooting
- Security
- FAQ
🛠 Development & Contributions
PRs welcome — Claude Recall is open to contributors.
📝 License
MIT.
Pros
- Local memory storage ensures privacy and security.
- Seamless integration with Claude Code enhances usability.
- Continuous learning improves coding efficiency over time.
Cons
- Limited to local storage, which may not suit all workflows.
- Dependency on Claude Code limits broader applicability.
- Initial setup may be complex for some users.
Related Skills
pytorch
S“It's the Swiss Army knife of deep learning, but good luck figuring out which of the 47 installation methods is the one that won't break your system.”
agno
S“It promises to be the Kubernetes for agents, but let's see if developers have the patience to learn yet another orchestration layer.”
nuxt-skills
S“It's essentially a well-organized cheat sheet that turns your AI assistant into a Nuxt framework parrot.”
Disclaimer: This content is sourced from GitHub open source projects for display and rating purposes only.
Copyright belongs to the original author raoulbia-ai.
