skills.rest
gaoqiongxie
gaoqiongxieCOMMUNITY
Explore all skills by this author →
GitHub

claude-mem

Capture session key points and search historical project context.

1|1|Updated Apr 9, 2026
Search Tags:#semantic search#persistent memory#bug tracking#project history#decision recall#cross-session context#ai assistant memory
One-click install
npx skills add https://github.com/gaoqiongxie/skills-ai --skill claude-mem-gaoqiongxie
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: claude-mem
Source: https://github.com/gaoqiongxie/skills-ai/tree/main/claude-mem
Command: npx skills add https://github.com/gaoqiongxie/skills-ai --skill claude-mem-gaoqiongxie

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI assistants typically lose all context from previous work sessions, forcing users to repeatedly explain project history, past decisions, and earlier bug fixes every time they start a new conversation. This Skill eliminates that friction by automatically capturing and storing key session information for easy retrieval later.

Core Features & Use Cases

  • Automatic Context Capture: No manual logging required, the system automatically saves key decisions, bug fixes, and project milestones from every work session.
  • Dual Search Capability: Combines semantic vector search and full-text keyword search to quickly find specific historical information, from architectural decisions to past bug fixes.
  • Privacy Controls: Built-in support for marking sensitive information as private so it is never stored in the memory system.
  • Use Case: If you join an ongoing software project, you can ask the AI to pull up all past technical decisions and bug fixes from previous sessions to get up to speed in minutes instead of asking multiple teammates.

Quick Start

Ask the AI to retrieve all past decisions and bug fixes related to your current project's user authentication module to avoid repeating earlier work.

Frequently Asked Questions about claude-mem

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

FAQPage Schema
How do I maintain AI assistant memory for project history across multiple sessions?▼

To maintain AI assistant memory across sessions, you need a persistent memory system that automatically captures key decisions and bug fixes. This skill implements automatic session capture and semantic compression to store historical context for later retrieval.

What is the best way to retrieve past architectural decisions and bug fixes from previous AI work sessions?▼

Retrieving past architectural decisions and bug fixes requires dual search capability combining semantic vector search and full-text keyword search. This approach quickly finds specific historical information without forcing you to manually log previous project sessions.

How does semantic compression reduce token usage when injecting cross-session context?▼

Semantic compression reduces token usage by automatically extracting key points from work sessions and applying progressive context injection. This preserves relevant historical data while minimizing the tokens consumed during AI assistant interactions.

Can I prevent sensitive project information from being stored in AI memory?▼

Yes, you can prevent sensitive project information from being stored using built-in privacy controls. The system supports marking specific data as private so it is never captured by the automatic session memory storage.

Does this persistent memory tool work for tracking ongoing software development workflows?▼

Persistent memory tracking works directly for software development workflows requiring historical context of feature implementations and architectural decisions. It automatically captures project milestones across multiple work sessions without manual logging.

Why does my AI assistant lose project context and force me to repeat historical work information?▼

AI assistants lose project context because they lack cross-session persistent memory by default. This skill solves that friction by automatically capturing session key points and applying AI-powered semantic compression for future retrieval.

Related Skills

Explore More Software Engineering Skills→
RepairYourTechRepairYourTech
6

lancedb

Implement LanceDB vector databases for RAG pipelines and semantic search.

Community
Advanced
Geralt1983Geralt1983
1

byterover

Query and curate project knowledge via a persistent context tree.

Community
Intermediate
sanity-labssanity-labs
1

create-agent-with-sanity-context

Build AI agents with schema-aware access to Sanity content via Agent Context.

Official
Advanced
coderhzycoderhzy

session-auto

Manage development session lifecycles with automatic logging of metadata and decisions.

Community
Intermediate