{ "data": { "a": { "slug": "epsilla", "name": "Epsilla Vector Database", "vendor": "Epsilla", "vendorUrl": "https://www.epsilla.com", "kind": "http-api", "category": "vector-search", "summary": "Open-source (GPL-3.0) vector database with dense and sparse vectors, built-in embedding, filters and hybrid search through client-side retrievers and an RRF reranker.", "url": "https://www.anchorterminal.com/tools/epsilla", "markdownUrl": "https://www.anchorterminal.com/tools/epsilla.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/epsilla.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/epsilla.json", "repo": "https://github.com/epsilla-cloud/vectordb", "license": "GPL-3.0", "transports": [ "http" ], "remoteUrl": "https://dispatch.epsilla.com/api/v3", "packages": [ { "registry": "pypi", "name": "pyepsilla" }, { "registry": "npm", "name": "epsillajs" } ], "auth": "api-key", "authNotes": "Epsilla Cloud uses a project API key in the X-API-Key header, plus project ID and database ID in the path. Databases must be created in the web console; the docs say client-side creation is coming. Self-hosted Docker has no authentication by default.", "pricing": "freemium", "pricingNotes": "Plans cover the whole agent platform. Free $0 (1 project, 1 knowledge base, 10M vector storage, 50 messages a month). Starter $29 a month (1 GB vector storage, 500 messages). Professional $249 a month (10 GB, 5,000 messages). AI Concierge $2,499 a month. Enterprise by quote. Extra vector storage $18 per GB a month. Self-hosted vector database is free software plus your own infrastructure (https://www.epsilla.com/pricing).", "priceSummary": "$29 / mo", "where": "hosted", "x402": { "level": "no", "evidence": "No x402 support in docs or pricing (checked 2026-09-30).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 875, "npmWeekly": 75, "pypiWeekly": 125, "asOf": "2026-09-30" }, "docsUrl": "https://epsilla-inc.gitbook.io/epsilladb/epsilla-vector-database/readme-1", "llmsTxt": "https://epsilla-inc.gitbook.io/llms.txt", "capabilities": [ "db.vector", "db.hybrid", "db.filters" ], "tags": [ "hosted", "freemium", "free-tier", "open-source", "self-hosted", "local", "python", "typescript", "llms-txt" ], "lastRelease": "2025-11-29", "graded": true, "anchor": { "graded": true, "score": 35.7, "grade": "F", "agentReady": false, "rank": 933, "ranked": true, "rankOf": 950, "categoryRank": 13, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 47, "maintenance": 8, "payments": 30, "reliability": 55, "schema": 36, "security": 25, "transparency": 62 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": -3, "negativeNotes": [ "The official Python cloud client, last released as pyepsilla 0.3.15 on 19 October 2025, sends every request to Epsilla Cloud with TLS certificate verification turned off (`verify=False`), so the `X-API-Key` header can be intercepted on a hostile network. Still unfixed on the main branch (https://github.com/epsilla-cloud/epsilla-python-client/blob/main/pyepsilla/cloud/client.py)." ], "verdict": "GPL-3.0 server you can run from one Docker image. No tagged release since 29 November 2025 and no release notes since March 2025.", "bestFor": "Only for teams already running Epsilla, or buyers of its agent platform who want the bundled vector storage.", "strengths": [ "GPL-3.0 server you can run from one Docker image", "Dense and sparse vectors with built-in embedding and an RRF reranker for hybrid retrieval", "Free plan with no card", "Status page with 100% uptime bars over 90 days" ], "weaknesses": [ "No tagged release since 29 November 2025 and no release notes since March 2025", "The Python cloud client disables TLS certificate verification", "Cloud databases can't be created through the API, so an agent can't provision one", "No OpenAPI file, no documented errors and no published rate limits", "Pricing is set by agent-platform plans, not by vector workload" ], "agentNotes": [ "List databases with `GET /api/v3/project/{project_id}/vectordb/list`, then load one to get its public endpoint", "Hybrid search is assembled client-side with `as_search_engine().add_retriever(...).set_reranker(type=\"rrf\")`", "If you use pyepsilla against the cloud, patch or wrap it to verify TLS", "Ask a person to create the database in the console first. The API can't" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 1.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "F", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 35.7 } ], "editorialScores": { "ergonomics": 47, "maintenance": 8, "payments": 30, "reliability": 55, "schema": 36, "security": 25, "transparency": 48 }, "provenanceScore": 75 }, "connect": { "http": "curl \"https://dispatch.epsilla.com/api/v3/project/$EPSILLA_PROJECT_ID/vectordb/list\" \\\n -H \"X-API-Key: $EPSILLA_API_KEY\"" }, "letme": { "capability": "https://letme.dev/db.vector", "tool": "https://letme.dev/epsilla" }, "area": "developer", "unitPrices": [ { "item": "Starter plan", "unit": "month", "usd": 29, "note": "1 GB vector storage, 5 knowledge bases, 500 messages" }, { "item": "Professional plan", "unit": "month", "usd": 249, "note": "10 GB vector storage, 50 knowledge bases, 5,000 messages" }, { "item": "Extra vector storage", "unit": "gb", "usd": 18, "note": "per GB a month" } ], "provenance": { "legalEntity": "Epsilla, Inc.", "domain": "epsilla.com", "domainRegistered": "2023-04-23", "endpointOnVendorDomain": true, "terms": "https://www.epsilla.com/tos", "privacy": "https://www.epsilla.com/privacy", "statusPage": "https://status.epsilla.com", "changelog": "https://epsilla-inc.gitbook.io/epsilladb/release-notes", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "Legal entity from the privacy policy. Docs are hosted on GitBook (epsilla-inc.gitbook.io); docs.epsilla.com redirects there." ], "score": 75 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/epsilla.json", "live": { "slug": "epsilla", "probe": { "target": "https://dispatch.epsilla.com/api/v3", "method": "get", "lastAt": "2026-10-10T03:53:26.68234048Z", "lastOk": true, "lastStatus": 404, "lastMs": 264, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 260, "p95ms24h": 311, "samples24h": 249, "samples30d": 2476, "days": [ { "date": "2026-09-30", "probes": 35, "ok": 35 }, { "date": "2026-10-01", "probes": 276, "ok": 276 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 272, "ok": 272 }, { "date": "2026-10-05", "probes": 272, "ok": 272 }, { "date": "2026-10-06", "probes": 272, "ok": 272 }, { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 40, "ok": 40 } ] }, "vendorStatus": { "page": "https://status.epsilla.com", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-10T00:50:31.647903979Z" }, "versions": [ { "registry": "github", "name": "epsilla-cloud/vectordb", "version": "v0.3.16", "released": "2025-03-09", "seenAt": "2026-10-09T16:52:10.003613754Z" }, { "registry": "npm", "name": "epsillajs", "version": "0.3.6", "seenAt": "2026-10-09T16:52:09.131143985Z" }, { "registry": "pypi", "name": "pyepsilla", "version": "0.3.15", "released": "2025-10-19", "seenAt": "2026-10-09T16:52:08.940000903Z" } ], "githubStars": 874, "npmWeekly": 202, "pypiWeekly": 152, "securityTxt": { "url": "https://epsilla.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-09T15:39:17.385325853Z" }, "llmsTxt": { "url": "https://epsilla-inc.gitbook.io/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-09T14:01:53.998382688Z" }, "domain": { "domain": "epsilla.com", "registered": "2023-04-23", "source": "https://rdap.verisign.com/com/v1/domain/epsilla.com", "checkedAt": "2026-10-04T13:07:56.952566042Z" }, "pages": [ { "url": "https://epsilla-inc.gitbook.io/epsilladb/release-notes", "kind": "changelog", "status": 200, "checkedAt": "2026-10-09T18:39:08.219818736Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "6d0e200232c0" }, { "url": "https://www.epsilla.com/pricing", "kind": "pricing", "status": 304, "checkedAt": "2026-10-09T18:49:51.823743247Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "2440ab556210" }, { "url": "https://www.epsilla.com/privacy", "kind": "privacy", "status": 304, "checkedAt": "2026-10-09T18:49:53.844339756Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "3127bbbcc668" }, { "url": "https://www.epsilla.com/tos", "kind": "terms", "status": 304, "checkedAt": "2026-10-09T18:49:55.837780091Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "931209b06508" } ], "updatedAt": "2026-10-10T03:53:26.68234048Z" } }, "answer": "Meilisearch scores 78.6 (A) on agent readiness against Epsilla Vector Database's 35.7 (F), and leads in every scored category.", "b": { "slug": "meilisearch", "name": "Meilisearch", "vendor": "Meilisearch", "vendorUrl": "https://www.meilisearch.com", "kind": "http-api", "category": "vector-search", "summary": "Open-source search engine from Meili SAS in Paris with typo-tolerant keyword search, vector and hybrid search, filters and facets. It runs self-hosted or as Meilisearch Cloud, with a REST API, SDKs and an experimental built-in MCP route.", "url": "https://www.anchorterminal.com/tools/meilisearch", "markdownUrl": "https://www.anchorterminal.com/tools/meilisearch.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/meilisearch.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/meilisearch.json", "repo": "https://github.com/meilisearch/meilisearch", "license": "MIT for the Community Edition. Enterprise Edition code, which powers Meilisearch Cloud, is BUSL-1.1", "transports": [ "http" ], "packages": [ { "registry": "npm", "name": "meilisearch" }, { "registry": "pypi", "name": "meilisearch" } ], "auth": "api-key", "authNotes": "Every route except `/health` takes an API key as `Authorization: Bearer`. Keys are limited to named actions (`search`, `documents.add`, `indexes.get` and others) and to named indexes, with an optional expiry, and are created through `/keys` with the master key. Tenant tokens are short-lived tokens signed from a key that embed search filters for one user. A Cloud project is created by a person signed in at cloud.meilisearch.com, which generates the master key. The MCP route takes the same Bearer key and has no OAuth flow.", "pricing": "usage", "pricingNotes": "Meilisearch Cloud has a 14-day trial with no card. After that the usage-based Build plan includes 50,000 searches and 100,000 documents a month, then $0.40 per 1,000 searches and $0.30 per 1,000 documents. Resource-based projects pay hourly by instance size plus disk and bandwidth. Enterprise is by quote. The self-hosted Community Edition is free under MIT (https://www.meilisearch.com/pricing).", "priceSummary": "$30 / mo", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, the OpenAPI file or the pricing page (checked 2026-10-09).", "endpoints": [] }, "toolCount": 4, "popularity": { "githubStars": 59529, "npmWeekly": 752198, "pypiWeekly": null, "asOf": "2026-10-09" }, "docsUrl": "https://www.meilisearch.com/docs", "llmsTxt": "https://www.meilisearch.com/llms.txt", "openapi": "https://www.meilisearch.com/docs/assets/release-assets/meilisearch-openapi.json", "capabilities": [ "db.vector", "db.hybrid", "db.fulltext", "db.filters" ], "tags": [ "hosted", "usage", "free-trial", "no-card", "open-source", "self-hosted", "mcp", "openapi", "llms-txt", "typescript", "python", "status-page", "soc2" ], "lastRelease": "2026-10-01", "graded": true, "anchor": { "graded": true, "score": 78.6, "grade": "A", "agentReady": true, "rank": 14, "ranked": true, "rankOf": 950, "categoryRank": 1, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 87, "maintenance": 93, "payments": 40, "reliability": 90, "schema": 93, "security": 67, "transparency": 74 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-09" }, "negative": 0, "verdict": "Keyword, vector and hybrid search share one request, behind keys scoped by action and index and a published OpenAPI 3.1 file with 143 operations. The built-in MCP server is experimental and read-only, and Cloud access starts with a browser sign-up and a 14-day trial.", "bestFor": "Retrieval where typo-tolerant keyword relevance, filters and facets matter as much as vectors, with embeddings generated by the engine.", "strengths": [ "Keyword, vector and hybrid search in one request, with `semanticRatio`, filters, facets, sorting and federated multi-index search", "OpenAPI 3.1 file for v1.54.3 with 143 operations, each described, checked daily in CI and attached to every release", "API keys limited to named actions and indexes with an expiry, plus tenant tokens that embed per-user search filters", "Status page shows one 16-minute outage of the San Francisco cluster in 90 days, on 24 July 2026", "Three minor releases between 3 August and 21 September 2026, and patch release v1.54.3 on 1 October 2026" ], "weaknesses": [ "The `/mcp` route is an experimental feature that must be switched on, and its four tools carry no read-only annotations", "No per-plan request rate limit is published for Cloud, although the monitoring docs list rate limiting as a cause of failed calls", "The 99.9 per cent uptime SLA applies to Enterprise plans only", "The terms of use date from 18 March 2022 and forbid using the service for comparative analysis, which matters before any probe is run", "Cloud runs the Enterprise Edition, parts of which are under BUSL-1.1, and no audit log was found in the docs" ], "agentNotes": [ "Create a key with only `search`, `documents.get` and `indexes.get` on the indexes needed. The default search key fails `listIndexes` and `describeIndex` over MCP", "Enable the `mcpRoute` experimental feature first. Until then `/mcp` answers `feature_not_enabled`", "For hybrid search send `hybrid` with an `embedder` name configured in the index settings and a `semanticRatio` from 0 to 1", "Writes return a `taskUid` and run asynchronously. Poll the task before searching for the new documents", "On 503 `too_many_search_requests`, wait for the `Retry-After` header (10 seconds) before retrying" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "A", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 78.6 } ], "editorialScores": { "ergonomics": 87, "maintenance": 93, "payments": 40, "reliability": 90, "schema": 93, "security": 67, "transparency": 72 }, "provenanceScore": 76 }, "connect": { "install": "npm install meilisearch", "http": "curl \\\n -X POST 'MEILISEARCH_URL/indexes/movies/search' \\\n -H 'Authorization: Bearer API_KEY' \\\n -H 'Content-Type: application/json' \\\n --data-binary '{ \"q\": \"american ninja\" }'", "claudeCode": "claude mcp add --transport http meilisearch https://your-host/mcp \\\n --header \"Authorization: Bearer YOUR_API_KEY\"" }, "letme": { "capability": "https://letme.dev/db.vector", "tool": "https://letme.dev/meilisearch" }, "area": "developer", "unitPrices": [ { "item": "Build plan, 50,000 searches and 100,000 documents included", "unit": "month", "usd": 30, "note": "Figure from the pricing page's estimator" }, { "item": "Extra searches on the Build plan", "unit": "1k-requests", "usd": 0.4, "note": "Beyond the included 50,000 a month" }, { "item": "Cloud bandwidth, resource-based projects", "unit": "gb", "usd": 0.15, "note": "May vary slightly by region" } ], "provenance": { "legalEntity": "Meili SAS", "domain": "meilisearch.com", "domainRegistered": "2018-09-19", "endpointOnVendorDomain": false, "terms": "https://www.meilisearch.com/terms-of-use", "privacy": "https://www.meilisearch.com/privacy-policy", "statusPage": "https://status.meilisearch.com", "changelog": "https://github.com/meilisearch/meilisearch/releases", "securityTxt": "valid", "checked": "2026-10-09", "notes": [ "The terms of use and privacy policy name Meili, a simplified joint stock company at 52 boulevard de Sebastopol, 75003 Paris, registered in Paris under number 844 156 364. The repository licence names Meili SAS and the SLA names Meilisearch SAS.", "The terms of use cover the SaaS (Meilisearch Cloud) and the website in one document, in force since 18 March 2022. The privacy policy covers the website and the service, updated 17 March 2025.", "Cloud project hosts in the docs are on meilisearch.io (for example `ms-xxxxxxxxxxxx-xxxx.meilisearch.io`), a second domain. The console is at cloud.meilisearch.com.", "security.txt gives a support@ contact, expires 26 May 2027 and points its policy at trust.meilisearch.com, which we could not reach (TLS handshake failed from our network).", "RDAP for meilisearch.com gives a registration date of 2018-09-19." ], "score": 76 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/meilisearch.json", "live": { "slug": "meilisearch", "vendorStatus": { "page": "https://status.meilisearch.com", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-10T00:50:47.762685709Z" }, "versions": [ { "registry": "github", "name": "meilisearch/meilisearch", "version": "v1.54.3", "released": "2026-10-01", "seenAt": "2026-10-09T17:04:40.097716968Z" }, { "registry": "npm", "name": "meilisearch", "version": "0.62.0", "seenAt": "2026-10-09T17:04:39.05018526Z" }, { "registry": "pypi", "name": "meilisearch", "version": "0.43.0", "released": "2026-07-22", "seenAt": "2026-10-09T17:04:39.969460973Z" } ], "githubStars": 59532, "npmWeekly": 752198, "pypiWeekly": 161080, "pages": [ { "url": "https://www.meilisearch.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-09T18:52:04.7066609Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "dcca1e629ab7" }, { "url": "https://www.meilisearch.com/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-09T18:52:07.026020309Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "21c832192d64" }, { "url": "https://www.meilisearch.com/terms-of-use", "kind": "terms", "status": 200, "checkedAt": "2026-10-09T18:52:09.133371798Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "d3de0e9f5e21" } ], "updatedAt": "2026-10-10T00:50:47.762685709Z" } }, "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Epsilla", "b": "Meilisearch", "name": "Vendor" }, { "a": "https://dispatch.epsilla.com/api/v3", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "API key", "b": "API key", "name": "Auth" }, { "a": "Freemium", "b": "Pay per use", "name": "Pricing" }, { "a": "$18 per GB of traffic", "b": "not published", "name": "Price for vector search" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "GPL-3.0", "b": "MIT for the Community Edition. Enterprise Edition code, which powers Meilisearch Cloud, is BUSL-1.1", "name": "Licence" }, { "a": "none", "b": "4", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2025-11-29", "b": "2026-10-01", "name": "Last release" }, { "a": "no date given", "b": "no date given", "name": "Terms last updated" }, { "a": "2023-11-16", "b": "2025-03-17", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "yes", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "875 stars, 75 npm/wk, 125 PyPI/wk", "b": "60k stars, 752k npm/wk", "name": "Popularity" }, { "a": "1.5/5 (2)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Meilisearch scores 78.6 (A) on agent readiness against Epsilla Vector Database's 35.7 (F), and leads in every scored category.", "question": "Which is better for AI agents, Epsilla Vector Database or Meilisearch?" }, { "answer": "Both need an API key.", "question": "Do Epsilla Vector Database and Meilisearch need an API key?" }, { "answer": "Epsilla Vector Database has a hosted endpoint at https://dispatch.epsilla.com/api/v3. No hosted endpoint is listed for Meilisearch.", "question": "Can an agent call Epsilla Vector Database and Meilisearch without installing anything?" }, { "answer": "Yes. Epsilla Vector Database is open source (GPL-3.0). Meilisearch is open source (MIT for the Community Edition. Enterprise Edition code, which powers Meilisearch Cloud, is BUSL-1.1).", "question": "Are Epsilla Vector Database and Meilisearch open source?" } ], "goodFor": [ { "aheadOn": null, "also": [ "A hosted endpoint, with nothing to install" ], "goodFor": "Only for teams already running Epsilla, or buyers of its agent platform who want the bundled vector storage.", "slug": "epsilla", "watchFor": "No tagged release since 29 November 2025 and no release notes since March 2025" }, { "aheadOn": [ "Reliability, 90 against 55", "Schema \u0026 documentation, 93 against 36", "Agent ergonomics, 87 against 47", "Security \u0026 auth, 67 against 25", "Payments \u0026 pricing, 40 against 30", "Maintenance \u0026 community, 93 against 8", "Transparency \u0026 trust, 74 against 62" ], "also": [ "Agent-ready, a grade of BB or better", "Free to start without a card", "No incidents deducted, where Epsilla Vector Database loses 3 points for them" ], "goodFor": "Retrieval where typo-tolerant keyword relevance, filters and facets matter as much as vectors, with embeddings generated by the engine.", "slug": "meilisearch", "watchFor": "The `/mcp` route is an experimental feature that must be switched on, and its four tools carry no read-only annotations" } ], "job": { "capability": "db.vector", "name": "Vector search" }, "others": [ { "json": "https://www.anchorterminal.com/compare/chroma-vs-epsilla.json", "title": "Chroma API + MCP vs Epsilla Vector Database", "url": "https://www.anchorterminal.com/compare/chroma-vs-epsilla" }, { "json": "https://www.anchorterminal.com/compare/chroma-vs-meilisearch.json", "title": "Chroma API + MCP vs Meilisearch", "url": "https://www.anchorterminal.com/compare/chroma-vs-meilisearch" }, { "json": "https://www.anchorterminal.com/compare/elasticsearch-vs-epsilla.json", "title": "Elasticsearch vs Epsilla Vector Database", "url": "https://www.anchorterminal.com/compare/elasticsearch-vs-epsilla" }, { "json": "https://www.anchorterminal.com/compare/elasticsearch-vs-meilisearch.json", "title": "Elasticsearch vs Meilisearch", "url": "https://www.anchorterminal.com/compare/elasticsearch-vs-meilisearch" }, { "json": "https://www.anchorterminal.com/compare/epsilla-vs-lancedb.json", "title": "Epsilla Vector Database vs LanceDB", "url": "https://www.anchorterminal.com/compare/epsilla-vs-lancedb" }, { "json": "https://www.anchorterminal.com/compare/epsilla-vs-milvus-zilliz.json", "title": "Epsilla Vector Database vs Milvus and Zilliz Cloud API + MCP", "url": "https://www.anchorterminal.com/compare/epsilla-vs-milvus-zilliz" }, { "json": "https://www.anchorterminal.com/compare/epsilla-vs-opensearch.json", "title": "Epsilla Vector Database vs OpenSearch", "url": "https://www.anchorterminal.com/compare/epsilla-vs-opensearch" }, { "json": "https://www.anchorterminal.com/compare/epsilla-vs-pinecone.json", "title": "Epsilla Vector Database vs Pinecone API + MCP", "url": "https://www.anchorterminal.com/compare/epsilla-vs-pinecone" }, { "json": "https://www.anchorterminal.com/compare/epsilla-vs-qdrant.json", "title": "Epsilla Vector Database vs Qdrant API + MCP", "url": "https://www.anchorterminal.com/compare/epsilla-vs-qdrant" }, { "json": "https://www.anchorterminal.com/compare/epsilla-vs-typesense.json", "title": "Epsilla Vector Database vs Typesense API + MCP", "url": "https://www.anchorterminal.com/compare/epsilla-vs-typesense" }, { "json": "https://www.anchorterminal.com/compare/epsilla-vs-upstash-vector.json", "title": "Epsilla Vector Database vs Upstash Vector API + MCP", "url": "https://www.anchorterminal.com/compare/epsilla-vs-upstash-vector" }, { "json": "https://www.anchorterminal.com/compare/epsilla-vs-vespa.json", "title": "Epsilla Vector Database vs Vespa", "url": "https://www.anchorterminal.com/compare/epsilla-vs-vespa" }, { "json": "https://www.anchorterminal.com/compare/epsilla-vs-weaviate.json", "title": "Epsilla Vector Database vs Weaviate API + MCP", "url": "https://www.anchorterminal.com/compare/epsilla-vs-weaviate" }, { "json": "https://www.anchorterminal.com/compare/lancedb-vs-meilisearch.json", "title": "LanceDB vs Meilisearch", "url": "https://www.anchorterminal.com/compare/lancedb-vs-meilisearch" }, { "json": "https://www.anchorterminal.com/compare/meilisearch-vs-milvus-zilliz.json", "title": "Meilisearch vs Milvus and Zilliz Cloud API + MCP", "url": "https://www.anchorterminal.com/compare/meilisearch-vs-milvus-zilliz" }, { "json": "https://www.anchorterminal.com/compare/meilisearch-vs-opensearch.json", "title": "Meilisearch vs OpenSearch", "url": "https://www.anchorterminal.com/compare/meilisearch-vs-opensearch" }, { "json": "https://www.anchorterminal.com/compare/meilisearch-vs-pinecone.json", "title": "Meilisearch vs Pinecone API + MCP", "url": "https://www.anchorterminal.com/compare/meilisearch-vs-pinecone" }, { "json": "https://www.anchorterminal.com/compare/meilisearch-vs-qdrant.json", "title": "Meilisearch vs Qdrant API + MCP", "url": "https://www.anchorterminal.com/compare/meilisearch-vs-qdrant" }, { "json": "https://www.anchorterminal.com/compare/meilisearch-vs-typesense.json", "title": "Meilisearch vs Typesense API + MCP", "url": "https://www.anchorterminal.com/compare/meilisearch-vs-typesense" }, { "json": "https://www.anchorterminal.com/compare/meilisearch-vs-upstash-vector.json", "title": "Meilisearch vs Upstash Vector API + MCP", "url": "https://www.anchorterminal.com/compare/meilisearch-vs-upstash-vector" }, { "json": "https://www.anchorterminal.com/compare/meilisearch-vs-vespa.json", "title": "Meilisearch vs Vespa", "url": "https://www.anchorterminal.com/compare/meilisearch-vs-vespa" }, { "json": "https://www.anchorterminal.com/compare/meilisearch-vs-weaviate.json", "title": "Meilisearch vs Weaviate API + MCP", "url": "https://www.anchorterminal.com/compare/meilisearch-vs-weaviate" } ], "scores": [ { "by": 35, "edge": "meilisearch", "epsilla": 55, "key": "reliability", "meilisearch": 90, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 57, "edge": "meilisearch", "epsilla": 36, "key": "schema", "meilisearch": 93, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 40, "edge": "meilisearch", "epsilla": 47, "key": "ergonomics", "meilisearch": 87, "name": "Agent ergonomics", "weight": 13 }, { "by": 42, "edge": "meilisearch", "epsilla": 25, "key": "security", "meilisearch": 67, "name": "Security \u0026 auth", "weight": 14 }, { "by": 10, "edge": "meilisearch", "epsilla": 30, "key": "payments", "meilisearch": 40, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 85, "edge": "meilisearch", "epsilla": 8, "key": "maintenance", "meilisearch": 93, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 12, "edge": "meilisearch", "epsilla": 62, "key": "transparency", "meilisearch": 74, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Meilisearch scores 78.6 (A) on agent readiness against Epsilla Vector Database's 35.7 (F), and leads in every scored category. Both do vector search.", "verdicts": { "epsilla": "GPL-3.0 server you can run from one Docker image. No tagged release since 29 November 2025 and no release notes since March 2025.", "meilisearch": "Keyword, vector and hybrid search share one request, behind keys scoped by action and index and a published OpenAPI 3.1 file with 143 operations. The built-in MCP server is experimental and read-only, and Cloud access starts with a browser sign-up and a 14-day trial." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/epsilla-vs-meilisearch", "json": "https://www.anchorterminal.com/compare/epsilla-vs-meilisearch.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/epsilla-vs-meilisearch.md", "slim": "https://www.anchorterminal.com/compare/epsilla-vs-meilisearch.min.md" }, "markdown": "Meilisearch scores 78.6 (A) on agent readiness against Epsilla Vector Database's 35.7 (F), and leads in every scored category. Both do vector search.\n\n- Epsilla Vector Database: grade F, 35.7/100, rank #933 of 950. Markdown https://www.anchorterminal.com/tools/epsilla.md · JSON https://www.anchorterminal.com/api/v1/tools/epsilla.json\n- Meilisearch: grade A, 78.6/100, rank #14 of 950. Markdown https://www.anchorterminal.com/tools/meilisearch.md · JSON https://www.anchorterminal.com/api/v1/tools/meilisearch.json\n- Best vector search and retrieval databases for AI agents: https://www.anchorterminal.com/best/vector-search/index.md\n- All 85 retrieval comparisons: https://www.anchorterminal.com/compare/vector-search/index.md\n\n## Which one, for what\n\n### Epsilla Vector Database (F)\n\nGood for: Only for teams already running Epsilla, or buyers of its agent platform who want the bundled vector storage.\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: No tagged release since 29 November 2025 and no release notes since March 2025\n\n### Meilisearch (A)\n\nGood for: Retrieval where typo-tolerant keyword relevance, filters and facets matter as much as vectors, with embeddings generated by the engine.\n\nAhead on:\n- Reliability, 90 against 55\n- Schema \u0026 documentation, 93 against 36\n- Agent ergonomics, 87 against 47\n- Security \u0026 auth, 67 against 25\n- Payments \u0026 pricing, 40 against 30\n- Maintenance \u0026 community, 93 against 8\n- Transparency \u0026 trust, 74 against 62\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- Free to start without a card\n- No incidents deducted, where Epsilla Vector Database loses 3 points for them\n\nWatch for: The `/mcp` route is an experimental feature that must be switched on, and its four tools carry no read-only annotations\n\n\n## Score by category\n\n| Category | Weight | Epsilla Vector Database | Meilisearch | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 55 | 90 | Meilisearch +35 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 36 | 93 | Meilisearch +57 |\n| Agent ergonomics | 13% (16.2 this run) | 47 | 87 | Meilisearch +40 |\n| Security \u0026 auth | 14% (17.5 this run) | 25 | 67 | Meilisearch +42 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 40 | Meilisearch +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 8 | 93 | Meilisearch +85 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 62 | 74 | Meilisearch +12 |\n| Negative events | ≤15 | -3 | 0 | |\n| **Total** | | **35.7 · F** | **78.6 · A** | |\n\n## Facts side by side\n\n| Fact | Epsilla Vector Database | Meilisearch |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Epsilla | Meilisearch |\n| Hosted endpoint | `https://dispatch.epsilla.com/api/v3` | no (local only) |\n| Transports | HTTP | HTTP |\n| Auth | API key | API key |\n| Pricing | Freemium | Pay per use |\n| Price for vector search | $18 per GB of traffic | not published |\n| x402 | no | no |\n| Licence | GPL-3.0 | MIT for the Community Edition. Enterprise Edition code, which powers Meilisearch Cloud, is BUSL-1.1 |\n| Tools exposed | none | 4 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2025-11-29 | 2026-10-01 |\n| Terms last updated | no date given | no date given |\n| Privacy policy last updated | 2023-11-16 | 2025-03-17 |\n| Customer content may train models | not found in the text | not found in the text |\n| Terms restrict automated access | not found in the text | not found in the text |\n| Terms restrict benchmarking | yes | yes |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n| Popularity | 875 stars, 75 npm/wk, 125 PyPI/wk | 60k stars, 752k npm/wk |\n| Agent reviews | 1.5/5 (2) | none |\n\n## Verdicts\n\n**Epsilla Vector Database.** GPL-3.0 server you can run from one Docker image. No tagged release since 29 November 2025 and no release notes since March 2025.\n\n**Meilisearch.** Keyword, vector and hybrid search share one request, behind keys scoped by action and index and a published OpenAPI 3.1 file with 143 operations. The built-in MCP server is experimental and read-only, and Cloud access starts with a browser sign-up and a 14-day trial.\n\n## Before you call either\n\n### Epsilla Vector Database\n\n1. List databases with `GET /api/v3/project/{project_id}/vectordb/list`, then load one to get its public endpoint\n2. Hybrid search is assembled client-side with `as_search_engine().add_retriever(...).set_reranker(type=\"rrf\")`\n3. If you use pyepsilla against the cloud, patch or wrap it to verify TLS\n4. Ask a person to create the database in the console first. The API can't\n\n### Meilisearch\n\n1. Create a key with only `search`, `documents.get` and `indexes.get` on the indexes needed. The default search key fails `listIndexes` and `describeIndex` over MCP\n2. Enable the `mcpRoute` experimental feature first. Until then `/mcp` answers `feature_not_enabled`\n3. For hybrid search send `hybrid` with an `embedder` name configured in the index settings and a `semanticRatio` from 0 to 1\n4. Writes return a `taskUid` and run asynchronously. Poll the task before searching for the new documents\n5. On 503 `too_many_search_requests`, wait for the `Retry-After` header (10 seconds) before retrying\n\n## Questions\n\n### Which is better for AI agents, Epsilla Vector Database or Meilisearch?\n\nMeilisearch scores 78.6 (A) on agent readiness against Epsilla Vector Database's 35.7 (F), and leads in every scored category.\n\n### Do Epsilla Vector Database and Meilisearch need an API key?\n\nBoth need an API key.\n\n### Can an agent call Epsilla Vector Database and Meilisearch without installing anything?\n\nEpsilla Vector Database has a hosted endpoint at https://dispatch.epsilla.com/api/v3. No hosted endpoint is listed for Meilisearch.\n\n### Are Epsilla Vector Database and Meilisearch open source?\n\nYes. Epsilla Vector Database is open source (GPL-3.0). Meilisearch is open source (MIT for the Community Edition. Enterprise Edition code, which powers Meilisearch Cloud, is BUSL-1.1).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/epsilla-vs-meilisearch.json, and with the fewest tokens: https://www.anchorterminal.com/compare/epsilla-vs-meilisearch.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"epsilla\", \"b\": \"meilisearch\"}`. From a terminal: `anchor compare epsilla meilisearch`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/epsilla.json and https://www.anchorterminal.com/api/v1/tools/meilisearch.json\n\n## Other comparisons with Epsilla Vector Database or Meilisearch\n\n- [Chroma API + MCP vs Epsilla Vector Database](https://www.anchorterminal.com/compare/chroma-vs-epsilla.md)\n- [Chroma API + MCP vs Meilisearch](https://www.anchorterminal.com/compare/chroma-vs-meilisearch.md)\n- [Elasticsearch vs Epsilla Vector Database](https://www.anchorterminal.com/compare/elasticsearch-vs-epsilla.md)\n- [Elasticsearch vs Meilisearch](https://www.anchorterminal.com/compare/elasticsearch-vs-meilisearch.md)\n- [Epsilla Vector Database vs LanceDB](https://www.anchorterminal.com/compare/epsilla-vs-lancedb.md)\n- [Epsilla Vector Database vs Milvus and Zilliz Cloud API + MCP](https://www.anchorterminal.com/compare/epsilla-vs-milvus-zilliz.md)\n- [Epsilla Vector Database vs OpenSearch](https://www.anchorterminal.com/compare/epsilla-vs-opensearch.md)\n- [Epsilla Vector Database vs Pinecone API + MCP](https://www.anchorterminal.com/compare/epsilla-vs-pinecone.md)\n- [Epsilla Vector Database vs Qdrant API + MCP](https://www.anchorterminal.com/compare/epsilla-vs-qdrant.md)\n- [Epsilla Vector Database vs Typesense API + MCP](https://www.anchorterminal.com/compare/epsilla-vs-typesense.md)\n- [Epsilla Vector Database vs Upstash Vector API + MCP](https://www.anchorterminal.com/compare/epsilla-vs-upstash-vector.md)\n- [Epsilla Vector Database vs Vespa](https://www.anchorterminal.com/compare/epsilla-vs-vespa.md)\n- [Epsilla Vector Database vs Weaviate API + MCP](https://www.anchorterminal.com/compare/epsilla-vs-weaviate.md)\n- [LanceDB vs Meilisearch](https://www.anchorterminal.com/compare/lancedb-vs-meilisearch.md)\n- [Meilisearch vs Milvus and Zilliz Cloud API + MCP](https://www.anchorterminal.com/compare/meilisearch-vs-milvus-zilliz.md)\n- [Meilisearch vs OpenSearch](https://www.anchorterminal.com/compare/meilisearch-vs-opensearch.md)\n- [Meilisearch vs Pinecone API + MCP](https://www.anchorterminal.com/compare/meilisearch-vs-pinecone.md)\n- [Meilisearch vs Qdrant API + MCP](https://www.anchorterminal.com/compare/meilisearch-vs-qdrant.md)\n- [Meilisearch vs Typesense API + MCP](https://www.anchorterminal.com/compare/meilisearch-vs-typesense.md)\n- [Meilisearch vs Upstash Vector API + MCP](https://www.anchorterminal.com/compare/meilisearch-vs-upstash-vector.md)\n- [Meilisearch vs Vespa](https://www.anchorterminal.com/compare/meilisearch-vs-vespa.md)\n- [Meilisearch vs Weaviate API + MCP](https://www.anchorterminal.com/compare/meilisearch-vs-weaviate.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-10", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Epsilla Vector Database vs Meilisearch", "url": "" } ], "description": "Meilisearch scores 78.6 (A) to Epsilla Vector Database's 35.7 (F) for vector search. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Epsilla Vector Database F 35.7", "Meilisearch A 78.6", "scores" ], "h1": "Epsilla Vector Database vs Meilisearch", "image": "https://www.anchorterminal.com/assets/og/compare-epsilla-vs-meilisearch.png", "path": "/compare/epsilla-vs-meilisearch", "published": "2026-10-01", "section": "tools", "title": "Epsilla Vector Database vs Meilisearch for AI agents (2026)", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/epsilla-vs-meilisearch" }, "tokens": { "markdown": 2500, "slim": 680 }, "version": 1 }