claude-mem-persistent-memorylisted

# claude-mem — Persistent Memory for Claude Code Brain-multiplier skill. Compresses past sessions into structured context and re-injects only the relevant chunks into future sessions. The reported token savings: **~75% per session**. Effect on the Octopus: every arm's runtime budget multiplies, every long engagement gets cross-session memory automatically. ## When to use - A client engagement spans many sessions and context drift is hurting quality - Token spend is the bottleneck on a high-frequency arm - You want session-to-session continuity that survives `/clear`, compaction, and machine switches - You're evaluating whether to standardize cross-session memory across all arms ## When NOT to use - One-shot tasks (overhead not worth it) - Highly sensitive arms where AGPL copyleft creates IP issues with client deliverables — see "License caveat" below - Engagements where the brain's existing auto-memory at `~/.claude/projects/<arm>/memory/` already covers the need (it's lighter, no compression, no ChromaDB) ## Source of truth - Repository: `github.com/thedotmack/claude-mem` (76.5k+ stars at time of writing — verify current state) - License: **AGPL 3.0** ← read the License caveat section before adopting - Requires: Node >= 18, ChromaDB (vector store) running locally - Compatible agents per repo: Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode and more - Local viewer UI typically at `localhost:37777` ## What it does technically 1. Hooks into the agent's