how-it-works
CommunityUnderstand how claude-mem stores and reuses context
Content & Communication#governance#local storage#observations#claude-mem#session context#memory injection#how it works
Authorenigmaicon-eng
Version1.0.0
Installs0
System Documentation
What problem does it solve?
It explains how claude-mem captures what you do with Claude, when it starts injecting stored observations into new prompts, and where that data is saved so you can trust what happens between sessions.
Core Features & Use Cases
- Observation capture: Turns every Read, Edit, and Bash action into compressed observations that are summarized at session end.
- Session-to-session injection: Auto-injects relevant stored observations into future prompts to reduce re-explaining prior work.
- Local storage transparency: Keeps SQLite, vector index, logs, and settings on your machine under ~/.claude-mem, with optional compression calls to your configured AI provider.
Quick Start
Ask: “How does claude-mem work, when does memory injection start, and where does it store my data?”
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: how-it-works Download link: https://github.com/enigmaicon-eng/AI-Enterprise-OS/archive/main.zip#how-it-works Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.