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 servers. No infrastructure. Just one file.

CLI
Node.js
Python

npm install -g memvid-cli

memvid create knowledge.mv2
echo "Alice works at Anthropic as a Senior Engineer." | memvid put knowledge.mv2
memvid find knowledge.mv2 --query "who works at AI companies"
memvid state knowledge.mv2 "Alice"
# { employer: 'Anthropic', role: 'Senior Engineer' }

import { create, use } from '@memvid/sdk';
import { existsSync } from 'fs';

// create() for NEW files, use() for EXISTING files
const mem = existsSync('knowledge.mv2')
  ? await use('basic', 'knowledge.mv2')
  : await create('knowledge.mv2', 'basic');

await mem.put({ title: 'Team Info', label: 'notes', text: 'Alice works at Anthropic...' });
const results = await mem.find('who works at AI companies', { k: 5, mode: 'lex' });
const alice = await mem.state('Alice');
// { slots: { employer: 'Anthropic', role: 'Senior Engineer' } }

from memvid_sdk import create, use
import os

# create() for NEW files, use() for EXISTING files
path = 'knowledge.mv2'
mem = use('basic', path) if os.path.exists(path) else create(path)

mem.put(title='Team', label='info', metadata={}, text='Alice works at Anthropic...')
results = mem.find('who works at AI companies', k=5, mode='lex')
alice = mem.state('Alice')
# {'slots': {'employer': 'Anthropic', 'role': 'Senior Engineer'}}

create() will OVERWRITE existing files! Note the different parameter order:

create(path, kind) — path first, creates NEW file (deletes existing data)
use(kind, path) — kind first, opens EXISTING file (preserves data)

Always check if the file exists first. See examples above.

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
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
Works Offline	Yes	No	Limited	No

Quick Start

CLI

npm install -g memvid-cli

Node.js

npm install @memvid/sdk

Python

pip install memvid-sdk

Ready to build? Start with the 5-Minute Quickstart for a complete walkthrough.

Core Capabilities

Hybrid Search

Combine keyword matching with semantic understanding:

# Lexical search (fast, exact matching)
memvid find knowledge.mv2 --query "budget" --mode lex

# Semantic search (meaning-based)
memvid find knowledge.mv2 --query "financial outlook" --mode sem

# Hybrid search (combines both - default)
memvid find knowledge.mv2 --query "Q4 projections"

Memory Cards (Entity Extraction)

Extract structured facts and query them instantly:

# Extract facts from documents
memvid enrich knowledge.mv2 --engine rules

# Query entity state (O(1) lookup)
memvid state knowledge.mv2 "Alice"
# employer: Anthropic
# role: Senior Engineer
# location: San Francisco

LLM-Powered Q&A

Ask natural language questions with sourced answers:

export OPENAI_API_KEY=sk-...
memvid ask knowledge.mv2 --question "What is Alice's role?" --use-model openai
# Answer: Alice is a Senior Engineer at Anthropic in San Francisco.
# Sources: [Meeting Notes, Team Directory]

Time-Travel Debugging

Record and replay sessions to debug retrieval:

memvid session start knowledge.mv2 --name "qa-test"
memvid find knowledge.mv2 --query "test query"
memvid session end knowledge.mv2

# Replay with different parameters
memvid session replay knowledge.mv2 --session abc123 --top-k 10

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

​One file. All your AI memory.

​Why Memvid?

Single File Storage

Hybrid Search

O(1) Entity Lookups

Time-Travel Debugging

​Memvid vs Alternatives

​Quick Start

CLI

Node.js

Python

​Core Capabilities

​Hybrid Search

​Memory Cards (Entity Extraction)

​LLM-Powered Q&A

​Time-Travel Debugging

​Framework Integrations

LangChain

LlamaIndex

Vercel AI

OpenAI

​Start Exploring

5-Minute Quickstart

CLI Reference

Node.js SDK

Python SDK

Core Concepts

Embedding Providers

One file. All your AI memory.

Why Memvid?

Memvid vs Alternatives

Quick Start

Core Capabilities

Hybrid Search

Memory Cards (Entity Extraction)

LLM-Powered Q&A

Time-Travel Debugging

Framework Integrations

Start Exploring