Tier 3 · Agent memory Agent memory · fetched 2026-07-02

Elite Longterm Memory

An npm-published long-term memory system for AI agents promising 'never lose context again' - a representative of the packaged, drop-in memory layer approach.

View source on GitHub

Key takeaways

01
Drop-in npm memory layers trade control for convenience

From the archive

Verbatim excerpts mined from our local archive of this repository — the prompts, schemas, and patterns worth stealing.

Memory

Hot/warm/cold tiers: chat history is a buffer, not storage

HOT RAM: SESSION-STATE.md (survives compaction) -> WARM STORE: LanceDB vectors (semantic search) -> COLD STORE: Git-Notes knowledge graph (permanent decisions) -> all distilled into MEMORY.md + daily/ (curated, human-readable).

From the SESSION-STATE.md template:
"This file is the agent's 'RAM' - survives compaction, restarts, distractions.
Chat history is a BUFFER. This file is STORAGE."

Sections: Current Task / Key Context / Pending Actions / Recent Decisions.

The one-line mental model every agent-memory design needs: context windows are buffers; anything that must survive belongs in explicit storage tiers.

SKILL.md