memesh-llm-memory
Reduces hallucination and context loss in LLM applications by persisting conversation state locally without cloud dependency, eliminating vendor lock-in and …
The lightest universal AI memory layer. One SQLite file, any LLM, zero cloud. MCP + HTTP + CLI. Smart Recall, Knowledge Evolution, Auto-Capture, Interactive Dashboard.
- Multi-turn customer support agents retaining conversation history without re-prompting
- Research assistants building and refining knowledge bases across sessions
- Internal chatbots learning domain context from repeated user interactions
Reduces hallucination and context loss in LLM applications by persisting conversation state locally without cloud dependency, eliminating vendor lock-in and latency overhead for teams running private deployments.
Engineering teams building LLM-powered internal tools requiring persistent memory without external infrastructure costs.
https://github.com/PCIRCLE-AI/memesh-llm-memory
By PCIRCLE-AI
How to Get It
claude plugins install PCIRCLE-AI/memesh-llm-memory
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
After installing, paste this into Claude:
Help me multi-turn customer support agents retaining conversation history without re-prompting
Trust Signals Auto-scanned
Community Pulse New
No community discussions found yet. This doesn't mean the tool isn't good — it may be new or serve a niche use case.
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Auto-assessment from April sweep — baseline scores pending hands-on review.
2026-04-18: Approved in April sweep: New and small but has a clear description and recent commits — worth tracking.
Things to check
- SQLite single-file design limits concurrent writes and scales poorly beyond small-to-medium deployments; requires manual schema versioning for memory structure changes. Dashboard and smart recall quality depend heavily on prompt engineering and indexing strategy.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.