MemoriLabs/Memori

for project: multi-site-livechat · https://github.com/MemoriLabs/Memori

# MemoriLabs/Memori

**URL:** https://github.com/MemoriLabs/Memori
**One-liner:** Memori is an LLM-agnostic memory layer that persists agent execution and conversation state, with both TypeScript and Python SDKs.
**Relevance to multi-site-livechat:** high (85/100)
**Integration:** cherry-pick

## Summary
Agent-native memory infrastructure that persists conversation and execution state across sessions.

## Why it's useful here
The livechat system currently lacks persistent memory between conversations; Memori can automatically store and recall chat history, entity preferences, and agent context across reconnections and sessions.

## Suggested use
Import `@memorilabs/memori` and register it with the chat agent's LLM client to automatically persist conversations and enable recall on subsequent messages.

## Novelty / why now
Strong LoCoMo benchmark results (81.95% accuracy at 5% of full-context tokens) and both cloud and BYODB options.

## Risks
License is Apache 2.0 (low risk), active repo, but depends on Memori Cloud for default backend (vendor lock-in). BYODB option exists but requires extra setup. Single maintainer? Not sure, but 34 contributors.

## Safety scan
- Risk level: **low**
- Stars: 14416 (age 293d, 49.20 stars/day)
- Last push: 0 days ago
- Contributors: 34
- License: NOASSERTION
- Postinstall hooks: none
- Suspicious patterns: none
- Notes: (none)

### Reviewer safety notes
License is Apache 2.0, no postinstall hooks, no secrets, low risk. However, default usage depends on Memori Cloud (SaaS) which may raise data privacy concerns. BYODB mitigates this.