# memvid/memvid

Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.

Repository: https://github.com/memvid/memvid
Canonical: https://ross.abutalabs.com/products/memvid
Homepage: https://www.memvid.com
Language: Rust
License: Apache-2.0
License Family: permissive
Topics: ai, context, embedded, faiss, knowledge-base, knowledge-graph, llm, machine-learning, memory, nlp, offline-first, opencv, python, rag, retrieval-augmented-generation, semantic-search, vector-database, video-processing, memvid, mv2
Last push: 2026-07-14T14:39:07+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 92, release rhythm 86, longevity 33
- inputs: {"age_days": 463, "days_push": 50, "days_rel": 98, "gap_med": 9, "n_releases_24m": 12}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 16449, forks 1412 (observed 2026-08-28T04:11:16.487993+00:00)

## What it is
Memvid is a single-file memory layer for AI agents that packages data, embeddings, and search indexes into one portable .mv2 file. It replaces RAG pipelines and server-based vector databases with fast hybrid (BM25 + vector) retrieval, entity state tracking, and offline-first operation.

## Use cases
- give my AI agent long-term memory without running a vector database
- replace complex RAG pipelines with a single portable file
- add semantic search to my agent's knowledge base offline
- store embeddings and indexes in one file I can commit to git
- run on-prem or air-gapped retrieval for sensitive data
- query entity state and facts extracted from documents
- connect agent memory via MCP or SDK

## When to choose
- you want portable, serverless memory with no database infrastructure
- you need offline or air-gapped retrieval with low latency
- you want hybrid BM25 + vector search and temporal queries in one file
- you need crash-safe, versioned memory files you can copy or sync

## When to avoid
- you need multi-user concurrent writes at scale
- you require a managed distributed vector database with horizontal scaling
- your team depends on heavy existing RAG infrastructure integrations

## Facets
- artifact type: library
- maturity: active
- function: rag, vector-database, search-engine, nlp, llm-inference, mcp
- domain: artificial-intelligence, large-language-models, databases
- platform: cross-platform, cli, python, rust, self-hosted
- tags: single-file-memory, hybrid-search, bm25, embeddings, offline-first, portable-memory, mv2, agent-memory, ai-agents, retrieval-augmented-generation, search, nodejs

## Member repositories
- memvid/memvid (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:16.487993+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:05:05.759554+00:00, confidence not recorded.
  - readme: https://github.com/memvid/memvid (fetched 2026-08-28T04:11:16.487993+00:00, sha 44708a91989b)
  - homepage: https://www.memvid.com (fetched 2026-08-29T08:02:37.227826+00:00, sha 90b44345a880)
  - site_page: https://memvid.com/about (fetched 2026-08-29T08:02:37.231677+00:00, sha d1b0de81445b)
  - site_page: https://docs.memvid.com (fetched 2026-08-29T08:02:37.233697+00:00, sha f0b51b572c8e)
  - site_page: https://docs.memvid.com/quickstart/five-minute-guide (fetched 2026-08-29T08:02:37.235616+00:00, sha 0586996818ce)
- Data as of 2026-08-30T08:39:29.467469+00:00.