One file. All your AI memory.
Ship a single.mv2 file that holds your data, indexes, and crash recovery. Copy it, sync it, commit it to git. No embeddings required. No servers. No infrastructure. Just one file.
- CLI
- Node.js
- Python
Why Memvid?
Single File Storage
Everything in one portable
.mv2 file. No databases, no Docker, no cloud dependencies.Hybrid Search
Combines BM25 lexical search with vector similarity. Best of both worlds.
O(1) Entity Lookups
Ask “What’s Alice’s job?” and get instant answers via Memory Cards (SPO triplets).
Time-Travel Debugging
Record sessions, replay with different parameters, debug retrieval quality.
Memvid vs Alternatives
| Capability | Memvid | Pinecone | ChromaDB | Weaviate |
|---|---|---|---|---|
| Single file | .mv2 | Cloud only | SQLite + files | Docker |
| Offline | Yes | No | Limited | No |
| Hybrid search | BM25 + vectors | Vectors only | Vectors only | BM25 + vectors |
| Entity lookups | O(1) via SlotIndex | No | No | No |
| Time-travel | Built-in | No | No | No |
| Crash safety | Embedded WAL | Cloud | Manual | Cloud |
Quick Start
Ready to build? Start with the 5-Minute Quickstart for a complete walkthrough.
Core Capabilities
Hybrid Search
Combine keyword matching with semantic understanding:Memory Cards (Entity Extraction)
Extract structured facts and query them instantly:LLM-Powered Q&A
Ask natural language questions with sourced answers:Time-Travel Debugging
Record and replay sessions to debug retrieval:Framework Integrations
Use Memvid with your favorite AI frameworks:LangChain
Vector store adapter
LlamaIndex
Index and retriever
Vercel AI
RAG pipeline
OpenAI
Function calling
Start Exploring
5-Minute Quickstart
Build your first AI memory with search and Q&A
CLI Reference
Complete command reference for all 38+ commands
Node.js SDK
Full API reference with TypeScript types
Python SDK
Complete Python API with examples
Core Concepts
Deep dive into .mv2 format, indexes, and architecture
Embedding Providers
OpenAI, Gemini, Mistral, Cohere, and local models