eidetic
SkillClaude Code memory system — auto context injection, drift detection, compounding, FTS5/vector search, Obsidian vault export. Zero core deps.
Install
git clone https://github.com/LARIkoz/eidetic.git ~/.claude/skills/eideticWhat is eidetic?
Claude Code memory system — auto context injection, drift detection, compounding, FTS5/vector search, Obsidian vault export. Zero core deps.
Trust
83/100 · Excellent2 factors scored below maximum
Documentation
README · ~16 min read🇬🇧 English · 🇷🇺 Русский
Eidetic
Long-term memory for AI coding agents — that knows when its memories go bad.
What is it? · Why · Install · How to use it · How it works · Features · Compare
What is it?
Eidetic gives an AI coding agent long-term memory that lives in plain Markdown files and is searched with hybrid FTS5 + vector search. One engine, two kinds of memory:
- Personal memory (PUSH) — your own decisions, rules, and project context. The agent writes its own memory: at every session end a small LLM pulls the decisions, rules, and lessons out of the transcript and files them as cards (
agent-extracted, 0.5× weight) — your memory grows from just working. It auto-injects into every Claude Code session (recallable on demand from any MCP agent too) and compounds — updating existing notes instead of piling up duplicates. - Topic bases (PULL) — an external corpus (API docs, a methodology, a book) you turn into an isolated base and attach only to the projects that need it.
Reviews
Log in to leave a review.
No reviews yet — be the first.
Explore related
Other things in this space — across every part of the ecosystem, not just skills.
Skillssimilar to this one
All skills →ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
235.3K stars
claude-mem
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
88.9K stars
mem0
Universal memory layer for AI Agents
62K stars
MCP Servers
All mcp servers →codebase-memory-mcp
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
36.7K stars
notion-mcp-server
Official Notion MCP Server
4.6K stars
linear-mcp-server
A server that integrates Linear's project management system with the Model Context Protocol (MCP) to allow LLMs to interact with Linear.
347 stars
Subagents
All subagents →ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
235.3K stars
patch-generator
Implements the fix for one finding inside a scratch workspace clone, staged for review and delivery as a patch file; dispatched by the fix job, not for direct invocation.
32.8K stars
patch-verifier
The single verifier per fix round — reviews the workspace's staged diff against the finding, runs the tests, and states the three confidence claims a patch file must earn; dispatched by the fix job, not for direct invocation.
32.8K stars
Commands
All commands →modernize-extract-rules
Mine business logic from legacy code into testable, human-readable rule specifications
32.8K stars
ars-format-convert
ARS academic-paper `format-convert` mode — convert to LaTeX / DOCX / PDF / Markdown
ars-revision-coach
ARS academic-paper `revision-coach` mode — Revision Roadmap + Response Letter Skeleton
Plugins
All plugins →claude-md-management
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
32.9K stars
hookify
Easily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or from explicit instructions. Define rules via simple markdown files.
32.9K stars
beads
Beads - A memory upgrade for your coding agent
25.7K stars