{
  "listings": [
    {
      "slug": "lancedb",
      "name": "LanceDB",
      "company": "LanceDB Systems, Inc.",
      "grade": "B",
      "fit": "yes",
      "why": "The open-source library runs in-process on a local directory or object storage with metadata filters, updates and deletes, and needs no account. An account prefers it because the index never moves rows.",
      "source": "https://docs.lancedb.com/_llms/embedded/0-41-0/documentation.txt",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/lancedb"
    },
    {
      "slug": "milvus-zilliz",
      "name": "Milvus and Zilliz Cloud API + MCP",
      "company": "Zilliz Inc.",
      "grade": "B",
      "fit": "yes",
      "why": "Milvus Lite runs locally through the same MilvusClient API with insert, upsert, delete, metadata filters and hybrid search, and no account.",
      "source": "https://raw.githubusercontent.com/milvus-io/milvus-docs/v3.0.x/site/en/getstarted/milvus_lite.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/milvus-zilliz"
    },
    {
      "slug": "chroma",
      "name": "Chroma API + MCP",
      "company": "Chroma Inc.",
      "grade": "D",
      "fit": "caveat",
      "why": "Runs in-process (ephemeral or persistent) with metadata and updates and no account, but hybrid, GroupBy and the Search API are Cloud only, the use case's named blocker.",
      "source": "https://raw.githubusercontent.com/chroma-core/chroma-mcp/main/README.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/chroma"
    },
    {
      "slug": "elasticsearch",
      "name": "Elasticsearch",
      "company": "Elasticsearch B.V.",
      "grade": "C",
      "fit": "caveat",
      "why": "Self-managed Elasticsearch runs locally with the same API and no account, but as a server, not in-process or from a directory.",
      "source": "https://www.elastic.co/docs/solutions/vector-database",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/elasticsearch"
    },
    {
      "slug": "epsilla",
      "name": "Epsilla Vector Database",
      "company": "Epsilla, Inc.",
      "grade": "E",
      "fit": "caveat",
      "why": "The open-source database runs locally from a Docker image with the same pyepsilla client and no account, but as a server, not in-process.",
      "source": "https://epsilla-inc.gitbook.io/epsilladb/epsilla-vector-database/quick-start/quick-start.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/epsilla"
    },
    {
      "slug": "meilisearch",
      "name": "Meilisearch",
      "company": "Meili SAS",
      "grade": "A",
      "fit": "caveat",
      "why": "The MIT Community Edition runs locally from one binary with the same API and no account, but as a local server, not in-process.",
      "source": "https://www.meilisearch.com/docs/llms.txt",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/meilisearch"
    },
    {
      "slug": "opensearch",
      "name": "OpenSearch",
      "company": "OpenSearch Software Foundation, a project of The Linux Foundation",
      "grade": "BB",
      "fit": "caveat",
      "why": "Runs locally in Docker under Apache-2.0 with the same API and no account, but as a server, not in-process; the whole HNSW graph sits in memory per an account.",
      "source": "https://docs.opensearch.org/latest/vector-search/filter-search-knn/index/",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/opensearch"
    },
    {
      "slug": "pinecone",
      "name": "Pinecone API + MCP",
      "company": "Pinecone Systems Inc.",
      "grade": "A",
      "fit": "caveat",
      "why": "The open-source pg_pinecone extension runs Pinecone's engine inside a self-managed Postgres 17 or 18 with no Pinecone call, but through SQL, not the cloud API, and not in-process.",
      "source": "https://docs.pinecone.io/guides/pg-pinecone/overview.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/pinecone"
    },
    {
      "slug": "qdrant",
      "name": "Qdrant API + MCP",
      "company": "Qdrant Solutions GmbH",
      "grade": "BB",
      "fit": "caveat",
      "why": "Qdrant Edge runs in-process like SQLite with no account, and the MCP server takes QDRANT_LOCAL_PATH, but Edge has its own API pages and a separate comparison with the server, so feature parity is not shown.",
      "source": "https://qdrant.tech/documentation/edge.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/qdrant"
    },
    {
      "slug": "typesense",
      "name": "Typesense API + MCP",
      "company": "Typesense, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "Self-hosted Typesense runs locally with the same API and no account, but as a server process, not in-process or from a directory.",
      "source": "https://typesense.org/docs/llms.txt",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/typesense"
    },
    {
      "slug": "vespa",
      "name": "Vespa",
      "company": "Vespa.ai AS",
      "grade": "BB",
      "fit": "caveat",
      "why": "Runs locally in a Docker container with the same API and no account, but as a server that needs an application package deployed, not in-process.",
      "source": "https://docs.vespa.ai/en/basics/deploy-an-application-local.html.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/vespa"
    },
    {
      "slug": "weaviate",
      "name": "Weaviate API + MCP",
      "company": "Weaviate B.V.",
      "grade": "C",
      "fit": "caveat",
      "why": "Embedded Weaviate runs locally with the same client API but is labelled experimental, and local instances can't use Weaviate Embeddings, so a local vectorizer must be configured.",
      "source": "https://docs.weaviate.io/deploy/installation-guides/embedded.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/weaviate"
    },
    {
      "slug": "cloudflare-ai-search",
      "name": "Cloudflare AI Search",
      "company": "Cloudflare, Inc.",
      "grade": "BB",
      "fit": "no",
      "why": "Managed Cloudflare service only; no local or embedded mode.",
      "source": "https://developers.cloudflare.com/ai-search/concepts/how-ai-search-works/index.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/cloudflare-ai-search"
    },
    {
      "slug": "upstash-vector",
      "name": "Upstash Vector API + MCP",
      "company": "Upstash, Inc.",
      "grade": "B",
      "fit": "no",
      "why": "Hosted service only; no self-hosted or embedded build.",
      "source": "https://upstash.com/docs/vector/overall/getstarted.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/upstash-vector"
    }
  ],
  "marks": "yes: the docs show it does the job as the success test says. caveat: it does the job with a limit an agent should know. no: it doesn't do this job. unchecked: we couldn't read it.",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "useCase": {
    "accounts": 2,
    "after": [
      "vector-search.rag-over-docs"
    ],
    "area": "developer",
    "asks": [
      "keep the index local",
      "search my files offline",
      "no external service"
    ],
    "before": [
      "embeddings.local-model"
    ],
    "blockers": [
      "local mode lacks functions of the server (filters, hybrid)",
      "telemetry on by default in a self-hosted build"
    ],
    "capabilities": [
      "db.vector",
      "db.embedded"
    ],
    "category": "vector-search",
    "categoryName": "Retrieval \u0026 vector search",
    "checked": "2026-11-15",
    "companies": {
      "fit": 2,
      "fitWithLimit": 10,
      "tagged": 17
    },
    "competition": "few",
    "fits": [
      "lancedb",
      "milvus-zilliz"
    ],
    "fitsWithLimit": [
      "chroma",
      "elasticsearch",
      "epsilla",
      "meilisearch",
      "opensearch",
      "pinecone",
      "qdrant",
      "typesense",
      "vespa",
      "weaviate"
    ],
    "id": "vector-search.local-embedded",
    "listings": {
      "caveat": 10,
      "no": 2,
      "notRead": 0,
      "tagged": 17,
      "unchecked": 0,
      "yes": 2
    },
    "name": "Run retrieval on the machine, in-process or air-gapped",
    "status": "draft",
    "success": "The index runs in-process or from a local directory with the same API as the server, holds metadata and supports updates, and needs no account or network call. Measured: a 1M-chunk index opens and answers a query in under 2 seconds on a laptop.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/vector-search.local-embedded.json",
    "weight": 6,
    "weightBasis": "2 of 37 accounts (air-gapped Qdrant embedded, LanceDB); kept small because most accounts were hosted or self-hosted servers"
  }
}
