{ "data": { "a": { "slug": "elasticsearch", "name": "Elasticsearch", "vendor": "Elastic", "vendorUrl": "https://www.elastic.co", "kind": "http-api", "category": "vector-search", "summary": "Elasticsearch is Elastic's search engine and vector database, with keyword, vector and hybrid search over a REST API. Agents reach it through that API or the Agent Builder MCP server on Elastic Cloud and Elastic Stack 9.2 or later.", "url": "https://www.anchorterminal.com/tools/elasticsearch", "markdownUrl": "https://www.anchorterminal.com/tools/elasticsearch.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/elasticsearch.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/elasticsearch.json", "repo": "https://github.com/elastic/elasticsearch", "license": "AGPL-3.0, SSPL-1.0 or Elastic Licence 2.0 at the user's choice for most source. The `x-pack` folder is under Elastic Licence 2.0 only. Elastic Cloud is a proprietary service under Elastic's terms", "transports": [ "http" ], "packages": [ { "registry": "npm", "name": "@elastic/elasticsearch" }, { "registry": "pypi", "name": "elasticsearch" } ], "auth": "mixed", "authNotes": "Self-serve. The REST API takes `Authorization: ApiKey \u003ckey\u003e`, with keys created in Kibana or by `POST /_security/api_key` and limited by role descriptors and an expiry. The Agent Builder MCP server takes the same kind of key, which needs the `feature_agentBuilder.read` Kibana privilege, or OAuth 2.1 on Serverless projects, where a registered client and a browser consent give each user a revocable connection.", "pricing": "usage", "pricingNotes": "Serverless bills by use, with search from $0.09 a VCU-hour, ingest from $0.14, storage from $0.047 a GB a month and egress from $0.05 a GB. Agent Builder has 1,000 free executions a month, then from $0.025 each. A 14-day Elastic Cloud trial needs no credit card. Self-managed Elasticsearch is free to run under its source licences (https://www.elastic.co/pricing/serverless-search, checked 2026-10-08).", "priceSummary": "$0.09 / unit", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs index, the Serverless OpenAPI file or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 3136798, "pypiWeekly": 7755257, "asOf": "2026-10-08" }, "docsUrl": "https://www.elastic.co/docs/solutions/search", "llmsTxt": "https://www.elastic.co/docs/llms.txt", "openapi": "https://www.elastic.co/docs/api/doc/elasticsearch-serverless.json", "capabilities": [ "db.vector", "db.hybrid", "db.fulltext", "db.filters", "db.serverless" ], "tags": [ "hosted", "usage", "free-trial", "no-card", "open-source", "self-hosted", "mcp", "oauth", "openapi", "llms-txt", "typescript", "python", "status-page", "bug-bounty", "soc2", "sla" ], "lastRelease": "2026-10-06", "graded": true, "anchor": { "graded": true, "score": 67.7, "grade": "B", "agentReady": false, "rank": 242, "ranked": true, "rankOf": 950, "categoryRank": 8, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 77, "maintenance": 83, "payments": 35, "reliability": 62, "schema": 88, "security": 72, "transparency": 71 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": -2, "negativeNotes": [ "Sixteen Elasticsearch security advisories were posted between 25 September and 6 October 2026. The one we read, ESA-2026-199 (CVE-2026-103009, CVSS 7.1), is an authorisation bypass in cross-cluster search on self-managed clusters, fixed in 8.19.23, 9.4.8 and 9.5.5, and Elastic says Serverless is not affected. Fixed and disclosed, so a small deduction (https://discuss.elastic.co/c/announcements/security-announcements/31)." ], "verdict": "Keyword, dense and sparse vector, and hybrid search with rank fusion sit behind one OpenAPI-described REST API, with API keys scoped to indices and privileges. The status page lists more than 20 incidents marked major since July 2026, and Elasticsearch 9.5.0 returned incorrect results for some queries without raising an error.", "bestFor": "Retrieval that needs keyword relevance, filters and vectors in one query, and teams already running Elastic for logs or security.", "strengths": [ "OpenAPI 3.0.3 file for the Serverless API with 311 operations, plus llms.txt and a Markdown twin of every docs page", "API keys take role descriptors that limit indices and privileges, with an expiry, and the MCP server accepts OAuth 2.1 on Serverless", "Agent Builder MCP server is generally available on Serverless and on Elastic Stack 9.3 and later", "14-day Elastic Cloud trial with no credit card, and unit prices published for Serverless", "Public bug bounty on HackerOne, CVE Numbering Authority status and dated security advisories" ], "weaknesses": [ "More than 20 status notices marked major between 10 July and 8 October 2026, three of them regional service incidents", "Elasticsearch 9.5.0 (29 July 2026) returned incorrect results for some `must_not` queries with no error, fixed in 9.5.1 and 9.5.2", "No request rate limit with numbers was found in the reviewed documentation", "The 99.95 per cent Serverless SLA applies only at Platinum or Enterprise subscription level", "The monthly terms forbid use of the cloud service for benchmarking, competitive or comparative purposes", "Search compute on Serverless does not scale to zero, so an idle project is still billed a baseline" ], "agentNotes": [ "Send `Authorization: ApiKey \u003ckey\u003e` to the project's Elasticsearch URL. The MCP server is on the Kibana URL at `/api/agent_builder/mcp`", "Create the MCP key with `feature_agentBuilder.read` and only the index patterns needed, or the endpoint answers 403", "On 429, wait and retry with exponential backoff. Do not set short client timeouts, because a retried request joins the back of the queue", "Page past 10,000 hits with `search_after`, not `from` and `size`", "Tool calls made directly through the Tools API skip Agent Builder's confirmation prompts, so restrict the key instead" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 67.7 } ], "editorialScores": { "ergonomics": 77, "maintenance": 83, "payments": 35, "reliability": 62, "schema": 88, "security": 72, "transparency": 70 }, "provenanceScore": 71 }, "connect": { "install": "npm install @elastic/elasticsearch", "http": "curl -X GET \"${ES_URL}/_cat/indices?v=true\" \\\n -H \"Authorization: ApiKey ${API_KEY}\"", "config": { "mcpServers": { "elastic-agent-builder": { "args": [ "mcp-remote", "${KIBANA_URL}/api/agent_builder/mcp", "--header", "Authorization:${AUTH_HEADER}" ], "command": "npx", "env": { "AUTH_HEADER": "ApiKey ${API_KEY}", "KIBANA_URL": "${KIBANA_URL}" } } } } }, "letme": { "capability": "https://letme.dev/db.vector", "tool": "https://letme.dev/elasticsearch" }, "area": "developer", "unitPrices": [ { "item": "Serverless search compute, VCU-hour", "unit": "compute-unit", "usd": 0.09, "note": "Quoted as a floor on the pricing page" }, { "item": "Serverless ingest compute, VCU-hour", "unit": "compute-unit", "usd": 0.14, "note": "Quoted as a floor on the pricing page" }, { "item": "Serverless storage", "unit": "gb-month", "usd": 0.047, "note": "Quoted as a floor on the pricing page" }, { "item": "Serverless egress", "unit": "gb", "usd": 0.05, "note": "Quoted as a floor on the pricing page" }, { "item": "Agent Builder execution", "unit": "call", "usd": 0.025, "note": "After 1,000 free executions a month, quoted as a floor" } ], "provenance": { "legalEntity": "Elasticsearch B.V.", "domain": "elastic.co", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://www.elastic.co/agreements/cloud-monthly", "privacy": "https://www.elastic.co/legal/product-privacy-statement", "statusPage": "https://status.elastic.co", "changelog": "https://www.elastic.co/docs/release-notes/elasticsearch", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The Cloud Monthly Terms of Service (effective 12 September 2025) name the contracting entity by customer location, Elasticsearch, Inc. for the United States and Elasticsearch B.V. or Elastic International B.V. elsewhere. The page is a cover that links the PDF.", "Customers with an order form are under the Elastic Cloud Service Subscription Agreement of 5 March 2026 at https://www.elastic.co/agreements/global/cloud-services.", "The Product Privacy Statement (7 September 2026) is issued by Elastic N.V. and its subsidiaries and covers Elastic Cloud Hosted, Serverless and self-managed software. The General Privacy Statement covers only websites and events.", "www.elastic.co/.well-known/security.txt returned 404. Reports go to HackerOne or security@elastic.co.", "No RDAP service answered for elastic.co, so the registration date is not recorded.", "Project endpoints are on Elastic Cloud hostnames that we did not call. `endpointOnVendorDomain` rests on the docs, not on a request." ], "score": 71 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/elasticsearch.json", "live": { "slug": "elasticsearch", "vendorStatus": { "page": "https://status.elastic.co", "indicator": "major", "summary": "Partial System Outage", "checkedAt": "2026-10-10T02:05:56.44505885Z" }, "versions": [ { "registry": "github", "name": "elastic/elasticsearch", "version": "v9.5.5", "released": "2026-10-06", "seenAt": "2026-10-09T16:51:28.060716552Z" }, { "registry": "npm", "name": "@elastic/elasticsearch", "version": "9.5.1", "seenAt": "2026-10-09T16:51:25.742667029Z" }, { "registry": "pypi", "name": "elasticsearch", "version": "9.5.1", "released": "2026-09-09", "seenAt": "2026-10-09T16:51:27.922910454Z" } ], "githubStars": 78225, "npmWeekly": 2585602, "pypiWeekly": 7817826, "securityTxt": { "url": "https://elastic.co/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-09T15:39:54.193710383Z" }, "llmsTxt": { "url": "https://www.elastic.co/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-09T14:01:50.325575586Z" }, "pages": [ { "url": "https://www.elastic.co/docs/release-notes/elasticsearch", "kind": "changelog", "status": 200, "checkedAt": "2026-10-09T18:49:52.532544613Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "b089eced2b1b" }, { "url": "https://www.elastic.co/pricing/serverless-search", "kind": "pricing", "status": 200, "checkedAt": "2026-10-09T18:49:58.534687729Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "2aedb044e960" }, { "url": "https://www.elastic.co/legal/product-privacy-statement", "kind": "privacy", "status": 200, "checkedAt": "2026-10-09T18:49:56.471944811Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "c61e39fadb3e" }, { "url": "https://www.elastic.co/agreements/cloud-monthly", "kind": "terms", "status": 200, "checkedAt": "2026-10-09T18:49:49.860754605Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "9558ef2f6571" } ], "updatedAt": "2026-10-10T02:05:56.44505885Z" } }, "answer": "OpenSearch and Elasticsearch score within a point of each other on agent readiness, 68 (B) and 67.7 (B). Elasticsearch leads on schema \u0026 documentation and transparency \u0026 trust.", "b": { "slug": "opensearch", "name": "OpenSearch", "vendor": "OpenSearch Software Foundation", "vendorUrl": "https://opensearch.org", "kind": "http-api", "category": "vector-search", "summary": "OpenSearch is an open-source search and analytics engine with vector, text and hybrid search, run by its owner. Agents reach it through a REST API, official clients, an OpenSearch MCP Server and an MCP endpoint inside the cluster.", "url": "https://www.anchorterminal.com/tools/opensearch", "markdownUrl": "https://www.anchorterminal.com/tools/opensearch.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/opensearch.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/opensearch.json", "repo": "https://github.com/opensearch-project/OpenSearch", "license": "Apache-2.0 for the engine, the plugins, the clients, the API specification and the MCP server", "transports": [ "http", "stdio" ], "packages": [ { "registry": "oci", "name": "opensearchproject/opensearch" }, { "registry": "pypi", "name": "opensearch-mcp-server-py" }, { "registry": "pypi", "name": "opensearch-py" } ], "auth": "mixed", "authNotes": "The owner sets access up on their own cluster. The Security plugin accepts basic auth, client certificates, JWT, OpenID Connect and SAML, and since 3.7 API keys sent as `Authorization: ApiKey \u003ctoken\u003e`. Only a security administrator can create, list or revoke a key. Each key names cluster permissions and index patterns with allowed actions, lasts 90 days at most, and cannot reach system indexes or the Security API. API keys are off until enabled in `config.yml`. The MCP server takes basic auth, AWS IAM, request headers or mTLS, or no authentication.", "pricing": "free", "pricingNotes": "Free software under Apache-2.0 with nothing to buy from the foundation, so an agent can start on a local Docker container with no account or contract. The owner pays for the machines. Three certified vendors sell long-term support, and opensearch.org lists no price for it (checked 2026-10-09).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the documentation source, the API specification or the MCP server source (checked 2026-10-09).", "endpoints": [] }, "toolCount": 9, "popularity": { "githubStars": 13800, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-09" }, "docsUrl": "https://docs.opensearch.org/latest/vector-search/", "openapi": "https://api-spec.opensearch.org/opensearch-openapi.yaml", "capabilities": [ "db.vector", "db.hybrid", "db.fulltext", "db.filters" ], "tags": [ "open-source", "self-hosted", "http-api", "mcp", "docker", "openapi", "api-key", "python", "javascript", "java", "go", "free" ], "lastRelease": "2026-09-22", "graded": true, "anchor": { "graded": true, "score": 68, "grade": "B", "agentReady": false, "rank": 233, "ranked": true, "rankOf": 950, "categoryRank": 6, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 80, "maintenance": 84, "payments": 60, "reliability": 77, "schema": 77, "security": 70, "transparency": 57 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-09" }, "negative": -5, "negativeNotes": [ "Until 0.12.0 (fix merged 3 August 2026, released 17 September 2026) the OpenSearch MCP Server attached its own configured credentials to any cluster URL a caller named in dynamic connection mode, which had shipped in 0.10.0 on 2 June 2026. The fix is described in the changelog and commit, and the repository lists no published advisory. Three points (https://github.com/opensearch-project/opensearch-mcp-server-py/blob/main/CHANGELOG.md).", "The Security plugin published four advisories on 30 April 2026, one moderate (GHSA-x83w-23jp-g6pw, document-level security not applied to documents linked by `has_child` or `has_parent`) and three low. Fixed and disclosed, so two points (https://github.com/opensearch-project/security/security/advisories)." ], "verdict": "OpenSearch 3.9.0 runs vector, text and hybrid search under Apache-2.0, with an OpenAPI 3.1 description of its REST API and API keys limited by permission and index pattern. The owner runs the cluster, no status page or SLA comes with the software, and no tool in the MCP server sets a read-only or destructive annotation.", "bestFor": "A team that already runs OpenSearch for logs or text search and wants vectors and hybrid search in the same cluster, with fine-grained access control.", "strengths": [ "Apache-2.0 for the engine, the plugins, the clients and the MCP server, under a foundation hosted by The Linux Foundation", "An OpenAPI 3.1 description of the REST API is published as one file, with about 717 operations in 36 namespace files in the source repository", "API keys since 3.7 carry cluster and index permissions, expire within 90 days at most, and are revoked on every node at once", "Approximate k-NN with filters applied during the search on the Lucene and Faiss engines, plus hybrid and neural sparse search", "Releases follow a published schedule about every eight weeks. 3.8.0 was tagged on 31 July and 3.9.0 on 22 September 2026" ], "weaknesses": [ "No hosted service from the foundation. The owner installs, secures and runs the cluster, and no status page or SLA exists for the software", "No `llms.txt` on docs.opensearch.org (HTTP 404), and doc pages carry about 160 KB of navigation text each", "The MCP server allows writes by default (`OPENSEARCH_SETTINGS_ALLOW_WRITE` is `true`) and no tool sets `readOnlyHint` or `destructiveHint`", "Before version 0.12.0 the MCP server sent its own configured credentials to any cluster URL a caller named. No advisory was published", "The core repository shows about 2,500 open issues, and 21 of the 25 newest carried the `untriaged` label on 9 October 2026" ], "agentNotes": [ "Create the index with `index.knn` set to true and a `knn_vector` field of the right dimension before indexing vectors", "Put the `filter` clause inside the `knn` query for filtering during the search. A filter outside it runs afterwards and can return fewer than `k` hits", "Ask a security administrator for an API key and send it as `Authorization: ApiKey \u003ctoken\u003e`. The token is shown once and lasts 90 days at most", "Use `size`, `_source` and `filter_path` to keep responses small, and `search_after` with a point in time for deep paging", "Set `OPENSEARCH_SETTINGS_ALLOW_WRITE=false` on the MCP server unless writes are needed. `GenericOpenSearchApiTool` can call any endpoint" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 68 } ], "editorialScores": { "ergonomics": 80, "maintenance": 84, "payments": 60, "reliability": 77, "schema": 77, "security": 70, "transparency": 69 }, "provenanceScore": 45 }, "connect": { "install": "docker run -d -p 9200:9200 -p 9600:9600 -e \"discovery.type=single-node\" -e \"OPENSEARCH_INITIAL_ADMIN_PASSWORD=\u003ccustom-admin-password\u003e\" opensearchproject/opensearch:latest", "http": "curl https://localhost:9200 -ku admin:\"\u003ccustom-admin-password\u003e\"", "config": { "mcpServers": { "opensearch": { "args": [ "opensearch-mcp-server-py" ], "command": "uvx" } } } }, "letme": { "capability": "https://letme.dev/db.vector", "tool": "https://letme.dev/opensearch" }, "area": "developer", "provenance": { "legalEntity": "OpenSearch Software Foundation, a project of The Linux Foundation", "domain": "opensearch.org", "domainRegistered": "2003-05-15", "endpointOnVendorDomain": false, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://docs.opensearch.org/latest/version-history/", "securityTxt": "none", "checked": "2026-10-09", "notes": [ "The foundation page says the OpenSearch Software Foundation is a project of The Linux Foundation and is not involved in technical oversight of the open source project.", "No terms or privacy document is set. The site footer links The Linux Foundation's general terms and privacy policy, which are a parent body's website notices. The Apache-2.0 licence stands in for the software.", "The software runs on the owner's machines, so no endpoint is on the vendor's domain and there is no status page.", "https://opensearch.org/.well-known/security.txt answered 404 on 9 October 2026. `SECURITY.md` in the core repository asks for reports by email to security@opensearch.org.", "RDAP for opensearch.org gives a registration date of 2003-05-15 and a transfer on 13 November 2024.", "The first release date is the 1.0 general availability date in the maintenance table on the releases page." ], "score": 45 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/opensearch.json", "live": { "slug": "opensearch", "versions": [ { "registry": "github", "name": "opensearch-project/OpenSearch", "version": "3.9.0", "released": "2026-09-29", "seenAt": "2026-10-09T17:11:12.76716689Z" }, { "registry": "pypi", "name": "opensearch-mcp-server-py", "version": "0.12.0", "released": "2026-09-17", "seenAt": "2026-10-09T17:11:10.759906653Z" }, { "registry": "pypi", "name": "opensearch-py", "version": "3.2.0", "released": "2026-04-27", "seenAt": "2026-10-09T17:11:10.949518654Z" } ], "githubStars": 13832, "pypiWeekly": 75145, "pages": [ { "url": "https://docs.opensearch.org/latest/version-history/", "kind": "changelog", "status": 200, "checkedAt": "2026-10-09T18:37:58.648544982Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "9aa4527e824d" } ], "updatedAt": "2026-10-09T18:37:58.648544982Z" } }, "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Elastic", "b": "OpenSearch Software Foundation", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP, stdio", "name": "Transports" }, { "a": "OAuth or key", "b": "OAuth or key", "name": "Auth" }, { "a": "Pay per use", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "AGPL-3.0, SSPL-1.0 or Elastic Licence 2.0 at the user's choice for most source. The `x-pack` folder is under Elastic Licence 2.0 only. Elastic Cloud is a proprietary service under Elastic's terms", "b": "Apache-2.0 for the engine, the plugins, the clients, the API specification and the MCP server", "name": "Licence" }, { "a": "none", "b": "9", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-10-06", "b": "2026-09-22", "name": "Last release" }, { "a": "couldn't be read", "b": "no document linked", "name": "Terms last updated" }, { "a": "2026-09-07", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "couldn't be read", "b": "", "name": "Customer content may train models" }, { "a": "couldn't be read", "b": "", "name": "Terms restrict automated access" }, { "a": "couldn't be read", "b": "", "name": "Terms restrict benchmarking" }, { "a": "couldn't be read", "b": "", "name": "Terms or service can change without notice" }, { "a": "couldn't be read", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "3.1M npm/wk, 7.8M PyPI/wk", "b": "14k stars", "name": "Popularity" } ], "faq": [ { "answer": "OpenSearch and Elasticsearch score within a point of each other on agent readiness, 68 (B) and 67.7 (B). Elasticsearch leads on schema \u0026 documentation and transparency \u0026 trust.", "question": "Which is better for AI agents, Elasticsearch or OpenSearch?" }, { "answer": "Both take an API key or an OAuth sign-in.", "question": "Do Elasticsearch and OpenSearch need an API key?" }, { "answer": "No hosted endpoint is listed for Elasticsearch. OpenSearch runs on your own machine, with no hosted endpoint listed.", "question": "Can an agent call Elasticsearch and OpenSearch without installing anything?" }, { "answer": "Yes. Elasticsearch is open source (AGPL-3.0, SSPL-1.0 or Elastic Licence 2.0 at the user's choice for most source. The `x-pack` folder is under Elastic Licence 2.0 only. Elastic Cloud is a proprietary service under Elastic's terms). OpenSearch is open source (Apache-2.0 for the engine, the plugins, the clients, the API specification and the MCP server).", "question": "Are Elasticsearch and OpenSearch open source?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 88 against 77", "Transparency \u0026 trust, 71 against 57" ], "also": [ "Free to start without a card" ], "goodFor": "Retrieval that needs keyword relevance, filters and vectors in one query, and teams already running Elastic for logs or security.", "slug": "elasticsearch", "watchFor": "More than 20 status notices marked major between 10 July and 8 October 2026, three of them regional service incidents" }, { "aheadOn": [ "Reliability, 77 against 62", "Payments \u0026 pricing, 60 against 35" ], "also": [ "Runs on your own machine" ], "goodFor": "A team that already runs OpenSearch for logs or text search and wants vectors and hybrid search in the same cluster, with fine-grained access control.", "slug": "opensearch", "watchFor": "No hosted service from the foundation. The owner installs, secures and runs the cluster, and no status page or SLA exists for the software" } ], "job": { "capability": "db.vector", "name": "Vector search" }, "others": [ { "json": "https://www.anchorterminal.com/compare/chroma-vs-elasticsearch.json", "title": "Chroma API + MCP vs Elasticsearch", "url": "https://www.anchorterminal.com/compare/chroma-vs-elasticsearch" }, { "json": "https://www.anchorterminal.com/compare/chroma-vs-opensearch.json", "title": "Chroma API + MCP vs OpenSearch", "url": "https://www.anchorterminal.com/compare/chroma-vs-opensearch" }, { "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-lancedb.json", "title": "Elasticsearch vs LanceDB", "url": "https://www.anchorterminal.com/compare/elasticsearch-vs-lancedb" }, { "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/elasticsearch-vs-milvus-zilliz.json", "title": "Elasticsearch vs Milvus and Zilliz Cloud API + MCP", "url": "https://www.anchorterminal.com/compare/elasticsearch-vs-milvus-zilliz" }, { "json": "https://www.anchorterminal.com/compare/elasticsearch-vs-pinecone.json", "title": "Elasticsearch vs Pinecone API + MCP", "url": "https://www.anchorterminal.com/compare/elasticsearch-vs-pinecone" }, { "json": "https://www.anchorterminal.com/compare/elasticsearch-vs-qdrant.json", "title": "Elasticsearch vs Qdrant API + MCP", "url": "https://www.anchorterminal.com/compare/elasticsearch-vs-qdrant" }, { "json": "https://www.anchorterminal.com/compare/elasticsearch-vs-typesense.json", "title": "Elasticsearch vs Typesense API + MCP", "url": "https://www.anchorterminal.com/compare/elasticsearch-vs-typesense" }, { "json": "https://www.anchorterminal.com/compare/elasticsearch-vs-upstash-vector.json", "title": "Elasticsearch vs Upstash Vector API + MCP", "url": "https://www.anchorterminal.com/compare/elasticsearch-vs-upstash-vector" }, { "json": "https://www.anchorterminal.com/compare/elasticsearch-vs-vespa.json", "title": "Elasticsearch vs Vespa", "url": "https://www.anchorterminal.com/compare/elasticsearch-vs-vespa" }, { "json": "https://www.anchorterminal.com/compare/elasticsearch-vs-weaviate.json", "title": "Elasticsearch vs Weaviate API + MCP", "url": "https://www.anchorterminal.com/compare/elasticsearch-vs-weaviate" }, { "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/lancedb-vs-opensearch.json", "title": "LanceDB vs OpenSearch", "url": "https://www.anchorterminal.com/compare/lancedb-vs-opensearch" }, { "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/milvus-zilliz-vs-opensearch.json", "title": "Milvus and Zilliz Cloud API + MCP vs OpenSearch", "url": "https://www.anchorterminal.com/compare/milvus-zilliz-vs-opensearch" }, { "json": "https://www.anchorterminal.com/compare/opensearch-vs-pinecone.json", "title": "OpenSearch vs Pinecone API + MCP", "url": "https://www.anchorterminal.com/compare/opensearch-vs-pinecone" }, { "json": "https://www.anchorterminal.com/compare/opensearch-vs-qdrant.json", "title": "OpenSearch vs Qdrant API + MCP", "url": "https://www.anchorterminal.com/compare/opensearch-vs-qdrant" }, { "json": "https://www.anchorterminal.com/compare/opensearch-vs-typesense.json", "title": "OpenSearch vs Typesense API + MCP", "url": "https://www.anchorterminal.com/compare/opensearch-vs-typesense" }, { "json": "https://www.anchorterminal.com/compare/opensearch-vs-upstash-vector.json", "title": "OpenSearch vs Upstash Vector API + MCP", "url": "https://www.anchorterminal.com/compare/opensearch-vs-upstash-vector" }, { "json": "https://www.anchorterminal.com/compare/opensearch-vs-vespa.json", "title": "OpenSearch vs Vespa", "url": "https://www.anchorterminal.com/compare/opensearch-vs-vespa" }, { "json": "https://www.anchorterminal.com/compare/opensearch-vs-weaviate.json", "title": "OpenSearch vs Weaviate API + MCP", "url": "https://www.anchorterminal.com/compare/opensearch-vs-weaviate" } ], "scores": [ { "by": 15, "edge": "opensearch", "elasticsearch": 62, "key": "reliability", "name": "Reliability", "opensearch": 77, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 11, "edge": "elasticsearch", "elasticsearch": 88, "key": "schema", "name": "Schema \u0026 documentation", "opensearch": 77, "weight": 13 }, { "by": 3, "edge": "opensearch", "elasticsearch": 77, "key": "ergonomics", "name": "Agent ergonomics", "opensearch": 80, "weight": 13 }, { "by": 2, "edge": "elasticsearch", "elasticsearch": 72, "key": "security", "name": "Security \u0026 auth", "opensearch": 70, "weight": 14 }, { "by": 25, "edge": "opensearch", "elasticsearch": 35, "key": "payments", "name": "Payments \u0026 pricing", "opensearch": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 1, "edge": "opensearch", "elasticsearch": 83, "key": "maintenance", "name": "Maintenance \u0026 community", "opensearch": 84, "weight": 7 }, { "by": 14, "edge": "elasticsearch", "elasticsearch": 71, "key": "transparency", "name": "Transparency \u0026 trust", "opensearch": 57, "weight": 7 } ], "summary": "OpenSearch and Elasticsearch score within a point of each other on agent readiness, 68 (B) and 67.7 (B). Elasticsearch leads on schema \u0026 documentation and transparency \u0026 trust. Both do vector search.", "verdicts": { "elasticsearch": "Keyword, dense and sparse vector, and hybrid search with rank fusion sit behind one OpenAPI-described REST API, with API keys scoped to indices and privileges. The status page lists more than 20 incidents marked major since July 2026, and Elasticsearch 9.5.0 returned incorrect results for some queries without raising an error.", "opensearch": "OpenSearch 3.9.0 runs vector, text and hybrid search under Apache-2.0, with an OpenAPI 3.1 description of its REST API and API keys limited by permission and index pattern. The owner runs the cluster, no status page or SLA comes with the software, and no tool in the MCP server sets a read-only or destructive annotation." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/elasticsearch-vs-opensearch", "json": "https://www.anchorterminal.com/compare/elasticsearch-vs-opensearch.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/elasticsearch-vs-opensearch.md", "slim": "https://www.anchorterminal.com/compare/elasticsearch-vs-opensearch.min.md" }, "markdown": "OpenSearch and Elasticsearch score within a point of each other on agent readiness, 68 (B) and 67.7 (B). Elasticsearch leads on schema \u0026 documentation and transparency \u0026 trust. Both do vector search.\n\n- Elasticsearch: grade B, 67.7/100, rank #242 of 950. Markdown https://www.anchorterminal.com/tools/elasticsearch.md · JSON https://www.anchorterminal.com/api/v1/tools/elasticsearch.json\n- OpenSearch: grade B, 68/100, rank #233 of 950. Markdown https://www.anchorterminal.com/tools/opensearch.md · JSON https://www.anchorterminal.com/api/v1/tools/opensearch.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### Elasticsearch (B)\n\nGood for: Retrieval that needs keyword relevance, filters and vectors in one query, and teams already running Elastic for logs or security.\n\nAhead on:\n- Schema \u0026 documentation, 88 against 77\n- Transparency \u0026 trust, 71 against 57\n\nAlso in its favour:\n- Free to start without a card\n\nWatch for: More than 20 status notices marked major between 10 July and 8 October 2026, three of them regional service incidents\n\n### OpenSearch (B)\n\nGood for: A team that already runs OpenSearch for logs or text search and wants vectors and hybrid search in the same cluster, with fine-grained access control.\n\nAhead on:\n- Reliability, 77 against 62\n- Payments \u0026 pricing, 60 against 35\n\nAlso in its favour:\n- Runs on your own machine\n\nWatch for: No hosted service from the foundation. The owner installs, secures and runs the cluster, and no status page or SLA exists for the software\n\n\n## Score by category\n\n| Category | Weight | Elasticsearch | OpenSearch | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 62 | 77 | OpenSearch +15 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 88 | 77 | Elasticsearch +11 |\n| Agent ergonomics | 13% (16.2 this run) | 77 | 80 | OpenSearch +3 |\n| Security \u0026 auth | 14% (17.5 this run) | 72 | 70 | Elasticsearch +2 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 35 | 60 | OpenSearch +25 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 83 | 84 | OpenSearch +1 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 71 | 57 | Elasticsearch +14 |\n| Negative events | ≤15 | -2 | -5 | |\n| **Total** | | **67.7 · B** | **68 · B** | |\n\n## Facts side by side\n\n| Fact | Elasticsearch | OpenSearch |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Elastic | OpenSearch Software Foundation |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | HTTP | HTTP, stdio |\n| Auth | OAuth or key | OAuth or key |\n| Pricing | Pay per use | Free |\n| x402 | no | no |\n| Licence | AGPL-3.0, SSPL-1.0 or Elastic Licence 2.0 at the user's choice for most source. The `x-pack` folder is under Elastic Licence 2.0 only. Elastic Cloud is a proprietary service under Elastic's terms | Apache-2.0 for the engine, the plugins, the clients, the API specification and the MCP server |\n| Tools exposed | none | 9 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-10-06 | 2026-09-22 |\n| Terms last updated | couldn't be read | no document linked |\n| Privacy policy last updated | 2026-09-07 | no document linked |\n| Customer content may train models | couldn't be read | |\n| Terms restrict automated access | couldn't be read | |\n| Terms restrict benchmarking | couldn't be read | |\n| Terms or service can change without notice | couldn't be read | |\n| Arbitration or class-action waiver | couldn't be read | |\n| Popularity | 3.1M npm/wk, 7.8M PyPI/wk | 14k stars |\n\n## Verdicts\n\n**Elasticsearch.** Keyword, dense and sparse vector, and hybrid search with rank fusion sit behind one OpenAPI-described REST API, with API keys scoped to indices and privileges. The status page lists more than 20 incidents marked major since July 2026, and Elasticsearch 9.5.0 returned incorrect results for some queries without raising an error.\n\n**OpenSearch.** OpenSearch 3.9.0 runs vector, text and hybrid search under Apache-2.0, with an OpenAPI 3.1 description of its REST API and API keys limited by permission and index pattern. The owner runs the cluster, no status page or SLA comes with the software, and no tool in the MCP server sets a read-only or destructive annotation.\n\n## Before you call either\n\n### Elasticsearch\n\n1. Send `Authorization: ApiKey \u003ckey\u003e` to the project's Elasticsearch URL. The MCP server is on the Kibana URL at `/api/agent_builder/mcp`\n2. Create the MCP key with `feature_agentBuilder.read` and only the index patterns needed, or the endpoint answers 403\n3. On 429, wait and retry with exponential backoff. Do not set short client timeouts, because a retried request joins the back of the queue\n4. Page past 10,000 hits with `search_after`, not `from` and `size`\n5. Tool calls made directly through the Tools API skip Agent Builder's confirmation prompts, so restrict the key instead\n\n### OpenSearch\n\n1. Create the index with `index.knn` set to true and a `knn_vector` field of the right dimension before indexing vectors\n2. Put the `filter` clause inside the `knn` query for filtering during the search. A filter outside it runs afterwards and can return fewer than `k` hits\n3. Ask a security administrator for an API key and send it as `Authorization: ApiKey \u003ctoken\u003e`. The token is shown once and lasts 90 days at most\n4. Use `size`, `_source` and `filter_path` to keep responses small, and `search_after` with a point in time for deep paging\n5. Set `OPENSEARCH_SETTINGS_ALLOW_WRITE=false` on the MCP server unless writes are needed. `GenericOpenSearchApiTool` can call any endpoint\n\n## Questions\n\n### Which is better for AI agents, Elasticsearch or OpenSearch?\n\nOpenSearch and Elasticsearch score within a point of each other on agent readiness, 68 (B) and 67.7 (B). Elasticsearch leads on schema \u0026 documentation and transparency \u0026 trust.\n\n### Do Elasticsearch and OpenSearch need an API key?\n\nBoth take an API key or an OAuth sign-in.\n\n### Can an agent call Elasticsearch and OpenSearch without installing anything?\n\nNo hosted endpoint is listed for Elasticsearch. OpenSearch runs on your own machine, with no hosted endpoint listed.\n\n### Are Elasticsearch and OpenSearch open source?\n\nYes. Elasticsearch is open source (AGPL-3.0, SSPL-1.0 or Elastic Licence 2.0 at the user's choice for most source. The `x-pack` folder is under Elastic Licence 2.0 only. Elastic Cloud is a proprietary service under Elastic's terms). OpenSearch is open source (Apache-2.0 for the engine, the plugins, the clients, the API specification and the MCP server).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/elasticsearch-vs-opensearch.json, and with the fewest tokens: https://www.anchorterminal.com/compare/elasticsearch-vs-opensearch.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"elasticsearch\", \"b\": \"opensearch\"}`. From a terminal: `anchor compare elasticsearch opensearch`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/elasticsearch.json and https://www.anchorterminal.com/api/v1/tools/opensearch.json\n\n## Other comparisons with Elasticsearch or OpenSearch\n\n- [Chroma API + MCP vs Elasticsearch](https://www.anchorterminal.com/compare/chroma-vs-elasticsearch.md)\n- [Chroma API + MCP vs OpenSearch](https://www.anchorterminal.com/compare/chroma-vs-opensearch.md)\n- [Elasticsearch vs Epsilla Vector Database](https://www.anchorterminal.com/compare/elasticsearch-vs-epsilla.md)\n- [Elasticsearch vs LanceDB](https://www.anchorterminal.com/compare/elasticsearch-vs-lancedb.md)\n- [Elasticsearch vs Meilisearch](https://www.anchorterminal.com/compare/elasticsearch-vs-meilisearch.md)\n- [Elasticsearch vs Milvus and Zilliz Cloud API + MCP](https://www.anchorterminal.com/compare/elasticsearch-vs-milvus-zilliz.md)\n- [Elasticsearch vs Pinecone API + MCP](https://www.anchorterminal.com/compare/elasticsearch-vs-pinecone.md)\n- [Elasticsearch vs Qdrant API + MCP](https://www.anchorterminal.com/compare/elasticsearch-vs-qdrant.md)\n- [Elasticsearch vs Typesense API + MCP](https://www.anchorterminal.com/compare/elasticsearch-vs-typesense.md)\n- [Elasticsearch vs Upstash Vector API + MCP](https://www.anchorterminal.com/compare/elasticsearch-vs-upstash-vector.md)\n- [Elasticsearch vs Vespa](https://www.anchorterminal.com/compare/elasticsearch-vs-vespa.md)\n- [Elasticsearch vs Weaviate API + MCP](https://www.anchorterminal.com/compare/elasticsearch-vs-weaviate.md)\n- [Epsilla Vector Database vs OpenSearch](https://www.anchorterminal.com/compare/epsilla-vs-opensearch.md)\n- [LanceDB vs OpenSearch](https://www.anchorterminal.com/compare/lancedb-vs-opensearch.md)\n- [Meilisearch vs OpenSearch](https://www.anchorterminal.com/compare/meilisearch-vs-opensearch.md)\n- [Milvus and Zilliz Cloud API + MCP vs OpenSearch](https://www.anchorterminal.com/compare/milvus-zilliz-vs-opensearch.md)\n- [OpenSearch vs Pinecone API + MCP](https://www.anchorterminal.com/compare/opensearch-vs-pinecone.md)\n- [OpenSearch vs Qdrant API + MCP](https://www.anchorterminal.com/compare/opensearch-vs-qdrant.md)\n- [OpenSearch vs Typesense API + MCP](https://www.anchorterminal.com/compare/opensearch-vs-typesense.md)\n- [OpenSearch vs Upstash Vector API + MCP](https://www.anchorterminal.com/compare/opensearch-vs-upstash-vector.md)\n- [OpenSearch vs Vespa](https://www.anchorterminal.com/compare/opensearch-vs-vespa.md)\n- [OpenSearch vs Weaviate API + MCP](https://www.anchorterminal.com/compare/opensearch-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": "Elasticsearch vs OpenSearch", "url": "" } ], "description": "OpenSearch and Elasticsearch score within a point of each other for vector search, 68 and 67.7 out of 100. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Elasticsearch B 67.7", "OpenSearch B 68", "scores" ], "h1": "Elasticsearch vs OpenSearch", "image": "https://www.anchorterminal.com/assets/og/compare-elasticsearch-vs-opensearch.png", "path": "/compare/elasticsearch-vs-opensearch", "published": "2026-10-01", "section": "tools", "title": "Elasticsearch vs OpenSearch for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/elasticsearch-vs-opensearch" }, "tokens": { "markdown": 2600, "slim": 730 }, "version": 1 }