MemPalace/mempalace

Health v2 · maintenance only

Adoption not part of the score

59621 stars · 7563 forks observed · 2026-10-18

What it is AI-extracted, prompt v1, taxonomy v1, 2026-09-21, confidence 0.97

MemPalace is a local‑first AI memory system that stores conversation and project data verbatim and makes it searchable via semantic search. It provides a pluggable backend (defaulting to ChromaDB) and a CLI for initializing, mining, and retrieving memories without any external API calls.

Use cases

• store and retrieve full conversation histories for LLM assistants
• index project code and documentation for quick semantic lookup
• enable long‑term memory in chatbots without external services
• search across personal notes, chats, and code bases using natural language
• create a private, offline knowledge base for AI agents

When to choose

• you need a fully offline, privacy‑preserving memory store for LLMs
• you want a simple CLI to mine files and chats into a searchable vector store
• you prefer a pluggable backend and can work with ChromaDB out of the box
• you are building AI agents that require verbatim recall rather than summarization

When to avoid

• you require a managed cloud service with built‑in scaling
• you need real‑time streaming ingestion or massive distributed storage
• your workflow depends on non‑Python environments without a CLI wrapper

Facets

cli-tool · maturity active

vector-database search-engine rag llm-inference cli artificial-intelligence large-language-models chatbots python windows cli local-first ai-memory mcp chromadb verbatim-storage semantic-search retrieval-augmented-generation linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="MemPalace/mempalace")