elite-longterm-memory — Claude Code skill: what it does
A skill that stacks six memory layers for an AI agent: session state, vector search, a git knowledge graph, daily logs and cloud backup. Useful when context dies after compaction.
npx skills add NextFrontierBuilds/elite-longterm-memory --skill elite-longterm-memory -a claude-codeWhat elite-longterm-memory does
The skill splits agent memory into layers. Hot memory is SESSION-STATE.md: you write to it before answering, so it survives compaction and restarts. Warm memory is LanceDB vector search, with auto-recall pulling relevant context through memory_recall. Cold memory is git notes shaped as a knowledge graph of decisions, branch-aware.
Above that sit a curated MEMORY.md archive with a memory/ folder for daily logs, an optional SuperMemory cloud copy, and fact extraction on Mem0. Setup steps are spelled out: create SESSION-STATE.md, turn on LanceDB in ~/.clawdbot/clawdbot.json, initialise git notes with python3 skills/git-notes-memory/memory.py -p . sync --start.
LanceDB needs OPENAI_API_KEY and the memory-lancedb plugin. No key means the vector layer stays idle, and without the plugin you are left with plain files and git notes. Mem0 installs separately with npm install mem0ai and wants MEM0_API_KEY.
What it helps with
- keep task context alive across session compaction
- find an earlier decision by meaning instead of exact wording
- record a tech choice in the decision graph tied to a branch
- merge daily logs and a distilled summary into one readable file
- sync memory across devices
Example prompts for the agent
- write to SESSION-STATE.md that we're moving to React, then continue
- search memory for what we decided about the database schema
- store this as a decision in git-notes
How to install elite-longterm-memory
1Skills CLI (Vercel)
npx skills add NextFrontierBuilds/elite-longterm-memory --skill elite-longterm-memory -a claude-code2Manually: put the files in place
~/.claude/skills/elite-longterm-memory/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/elite-longterm-memory/
1Skills CLI (Vercel)
npx skills add NextFrontierBuilds/elite-longterm-memory --skill elite-longterm-memory -a codex2Manually: put the files in place
.agents/skills/elite-longterm-memory/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add NextFrontierBuilds/elite-longterm-memory --skill elite-longterm-memory -a cursor2Manually: put the files in place
.cursor/skills/elite-longterm-memory/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install NextFrontierBuilds/elite-longterm-memory elite-longterm-memory2Manually: put the files in place
.github/skills/elite-longterm-memory/SKILL.md1Skills CLI (Vercel)
npx skills add NextFrontierBuilds/elite-longterm-memory --skill elite-longterm-memory -a gemini-cli2Platform CLI
gemini skills install https://github.com/NextFrontierBuilds/elite-longterm-memoryManually: put the files in place
.devin/skills/elite-longterm-memory/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add NextFrontierBuilds/elite-longterm-memory --skill elite-longterm-memory -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about elite-longterm-memory
How do I install elite-longterm-memory in Claude?
Run npx skills add NextFrontierBuilds/elite-longterm-memory --skill elite-longterm-memory -a claude-code. The skill file then lands at ~/.claude/skills/elite-longterm-memory/SKILL.md.
What does elite-longterm-memory do?
It lays out six agent memory layers and how to use them: session state, vector search, a git decision graph, an archive with daily logs, cloud backup and automatic fact extraction.
What does the vector layer need to work?
The OPENAI_API_KEY environment variable and the memory-lancedb plugin enabled. Search settings live in ~/.clawdbot/clawdbot.json.
