claude-mem

Search and retrieve past session observations with semantic relevance scoring.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/swat9013/dotfiles --skill claude-mem
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: claude-mem
Source: https://github.com/swat9013/dotfiles/tree/main/.claude-global/skills/claude-mem
Command: npx skills add https://github.com/swat9013/dotfiles --skill claude-mem

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides a structured workflow to locate, evaluate, and retrieve relevant past session observations so users can reuse prior debugging steps, configuration changes, and implementation patterns without re-searching or wasting tokens.

Core Features & Use Cases

  • Semantic search (search): Lightweight index queries to surface candidate observations with relevance scores.
  • Timeline inspection (timeline): View surrounding chronological context when the order of changes matters.
  • Batched retrieval (get_observations): Fetch full, detailed observations in bulk to minimize token cost and latency.
  • Privacy and save controls: Tag sensitive content with <private> and manually save important memories via save_memory.
  • Use Cases: Reapply a previous bug fix, reproduce a prior PR formatting, or inspect the sequence of changes for a configuration rollout.

Quick Start

Search the memory for a specific error or feature, pick the top one to three high-relevance results, and retrieve their full observations in a single batched request for immediate reuse.

Frequently Asked Questions about claude-mem

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I reuse past session memory for debugging without wasting tokens?

Session memory retrieval lets you search past observations, pick the top high-relevance results, and fetch their full details in a single batched request to minimize token cost and latency.

Can I search previous development sessions chronologically to review configuration history?

Yes, timeline inspection lets you view surrounding chronological context of past session observations, which is useful when the sequence of configuration changes or implementation patterns matters.

How does semantic search work for finding past implementation patterns and bug fixes?

Semantic search uses lightweight index queries to surface candidate observations with relevance scores, helping you quickly locate prior debugging steps, configuration changes, or implementation patterns for reuse.

What is the best way to protect sensitive data when saving session memories?

You can tag sensitive content with privacy tags and use manual save controls to protect sensitive data, ensuring only designated observations are stored and retrieved during semantic search workflows.

Does batched observation retrieval help reduce latency when reproducing prior PR formatting?

Batched retrieval fetches full, detailed observations in bulk to minimize token cost and latency, allowing you to efficiently reproduce prior PR formatting or reapply previous bug fixes without multiple requests.