{ "data": { "a": { "slug": "cognee", "name": "Cognee", "vendor": "Cognee", "vendorUrl": "https://www.cognee.ai", "kind": "platform", "category": "agent-memory", "summary": "Open-source memory engine that turns documents, conversations and synced sources into a knowledge graph plus a vector index and answers queries over both.", "url": "https://www.anchorterminal.com/tools/cognee", "markdownUrl": "https://www.anchorterminal.com/tools/cognee.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/cognee.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/cognee.json", "repo": "https://github.com/topoteretes/cognee", "license": "Apache-2.0", "transports": [ "http", "stdio", "sse" ], "remoteUrl": "https://\u003ctenant\u003e.aws.cognee.ai/api/v1", "packages": [ { "registry": "pypi", "name": "cognee" }, { "registry": "oci", "name": "cognee/cognee-mcp" } ], "auth": "mixed", "authNotes": "Cognee Cloud takes an `X-Api-Key` header on a per-tenant host, and keys can be rotated. A local Docker server runs without auth unless you turn it on, then takes a Bearer token. Since 1.6.0 (18 September 2026) the library builds and searches text memory with local models and no LLM key, and LLM-dependent stages skip when none is set. Set `LLM_API_KEY` for the full pipeline with a hosted model. Cognee MCP and Cognee Cloud are separate systems with different auth.", "pricing": "freemium", "pricingNotes": "Cognee Cloud Free is $0 with 1 million tokens included, 1 workspace, unlimited users and API calls, and no card. Standard is $1 per million tokens processed plus $5 a month for each extra workspace, and adds Slack, Notion, Linear and Google Drive sources. Enterprise is quoted, with bring-your-own-cloud (https://www.cognee.ai/pricing). The billing docs still show older plans (Hobby with 10 million tokens, Growth at $5 a tenant, Enterprise at $2,916 a month), which disagree with the pricing page. Credit is prepaid from $0.50, with optional auto-recharge (https://docs.cognee.ai/cognee-cloud/functionality/account-and-billing). The open-source library is free to run yourself.", "priceSummary": "$5 / mo", "where": "both", "x402": { "level": "no", "endpoints": [] }, "toolCount": 7, "popularity": { "githubStars": 31200, "npmWeekly": null, "pypiWeekly": 20830, "asOf": "2026-09-30" }, "docsUrl": "https://docs.cognee.ai", "llmsTxt": "https://docs.cognee.ai/llms.txt", "openapi": "https://docs.cognee.ai/cognee_openapi_spec.json", "capabilities": [ "memory.store", "memory.search", "memory.graph", "memory.delete" ], "tags": [ "open-source", "self-hosted", "hosted", "freemium", "free-tier", "no-card", "mcp", "llms-txt", "python", "eu" ], "lastRelease": "2026-09-29", "graded": true, "anchor": { "graded": true, "score": 54.6, "grade": "C", "agentReady": false, "rank": 681, "ranked": true, "rankOf": 950, "categoryRank": 6, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 59, "maintenance": 82, "payments": 35, "reliability": 50, "schema": 85, "security": 39, "transparency": 66 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": -3, "negativeNotes": [ "2026-05-01: a commit titled as a fix removed 11 MCP tools, including cognify, search, delete and prune, with cognee-mcp at 0.5.4 before and after, and the README the day before listed them as \"still available\" with no deprecation note. The replacements remember, recall and forget had shipped on 10 April and the tools reference now lists what went, so we deduct at the low end (https://github.com/topoteretes/cognee/commit/b52fcc335f6bfc090d1c892afa9c4e81909336fe)" ], "verdict": "Apache-2.0 library, REST server and MCP server, all self-hostable, with local models and no LLM key since 1.6.0. No status page, rate limits, SLA or SOC 2 for Cloud, and Cloud runs in AWS us-east-1 with no EU region.", "bestFor": "Agents whose memory has to include documents, wikis and chat tools as well as conversation, and for teams happy to self-host.", "strengths": [ "Apache-2.0 library, REST server and MCP server, all self-hostable, with local models and no LLM key since 1.6.0", "7-tool MCP server with search_tools and call_tool for reaching the rest on demand", "Public OpenAPI 3.1 file with 46 paths and error models", "Metered Cloud at $1 per million tokens, 1 million free with no card", "Eight stable PyPI releases from 15 August to 29 September 2026, with CI passing on main" ], "weaknesses": [ "No status page, rate limits, SLA or SOC 2 for Cloud, and Cloud runs in AWS us-east-1 with no EU region", "Cloud calls hung rather than failing when a tenant ran out of credit (August 2026), and the issue is still open", "Billing docs and pricing page disagree on plans and the free allowance", "Library telemetry is on by default and sends a persistent machine ID and an ID derived from the LLM key", "11 MCP tools were removed in May 2026 without a version bump or notice" ], "agentNotes": [ "Use remember, recall and forget. The older cognify, search and delete MCP tools are gone", "Always include /api/v1 in REST paths", "Check cognify_status before querying data you added with background=true", "Never pass everything=true to forget unless you mean to wipe all of the user's memory", "Set a client timeout on Cloud calls and treat HTTP 402 as an empty balance, since an empty balance has also shown up as hangs" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 54.6 } ], "editorialScores": { "ergonomics": 59, "maintenance": 82, "payments": 35, "reliability": 50, "schema": 85, "security": 39, "transparency": 69 }, "provenanceScore": 63 }, "connect": { "install": "pip install cognee", "http": "# COGNEE_URL is your tenant host, e.g. https://\u003ctenant\u003e.aws.cognee.ai\ncurl -X POST \"$COGNEE_URL/api/v1/search\" -H \"X-Api-Key: $COGNEE_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"query\":\"What does the user prefer?\"}'", "claudeCode": "docker run -d -e TRANSPORT_MODE=http -e LLM_API_KEY=$LLM_API_KEY -p 8000:8000 cognee/cognee-mcp:main\nclaude mcp add --transport http cognee http://localhost:8000/mcp", "config": { "mcpServers": { "cognee": { "args": [ "run", "-i", "--rm", "-e", "LLM_API_KEY", "cognee/cognee-mcp:main" ], "command": "docker", "env": { "LLM_API_KEY": "${LLM_API_KEY}" } } } } }, "letme": { "capability": "https://letme.dev/memory.store", "tool": "https://letme.dev/cognee" }, "area": "agent-runtime", "unitPrices": [ { "item": "Standard token processing", "unit": "1m-tokens", "usd": 1, "note": "1 million tokens free" }, { "item": "Extra workspace", "unit": "month", "usd": 5 } ], "provenance": { "legalEntity": "Topoteretes UG (haftungsbeschränkt)", "domain": "cognee.ai", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://www.cognee.ai/gtc-eu", "privacy": "https://www.cognee.ai/privacy-notice", "statusPage": "", "changelog": "https://github.com/topoteretes/cognee/releases", "securityTxt": "none", "checked": "2026-10-02", "notes": [ "The general terms, updated 27 March 2026, name Topoteretes UG (haftungsbeschränkt), Amtsgericht Charlottenburg HRB 252065 B, Paul-Lincke-Ufer 39-40, 10999 Berlin, under German law.", "www.cognee.ai/.well-known/security.txt returns 404, and we found no status page.", "The privacy notice, current version 20 September 2026, says Cognee Cloud is operated by Cognee Inc. and hosted in AWS us-east-1, while the general terms name Topoteretes UG in Berlin. SECURITY.md in the repository sends reports to security@cognee.ai." ], "score": 63 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/cognee.json", "live": { "slug": "cognee", "probe": { "target": "https://\u003ctenant\u003e.aws.cognee.ai/api/v1", "method": "get", "lastAt": "2026-10-10T02:07:05.568700085Z", "lastOk": false, "lastStatus": 0, "lastMs": 0, "lastNote": "DNS lookup failed", "authRequired": false, "uptime24h": 0, "uptime30d": 0, "p50ms24h": 0, "p95ms24h": 0, "samples24h": 250, "samples30d": 2256, "days": [ { "date": "2026-10-01", "probes": 109, "ok": 0 }, { "date": "2026-10-02", "probes": 248, "ok": 0 }, { "date": "2026-10-03", "probes": 271, "ok": 0 }, { "date": "2026-10-04", "probes": 272, "ok": 0 }, { "date": "2026-10-05", "probes": 272, "ok": 0 }, { "date": "2026-10-06", "probes": 272, "ok": 0 }, { "date": "2026-10-07", "probes": 272, "ok": 0 }, { "date": "2026-10-08", "probes": 268, "ok": 0 }, { "date": "2026-10-09", "probes": 250, "ok": 0 }, { "date": "2026-10-10", "probes": 22, "ok": 0 } ] }, "versions": [ { "registry": "github", "name": "topoteretes/cognee", "version": "v1.6.3", "released": "2026-10-07", "seenAt": "2026-10-09T16:46:28.063347549Z" }, { "registry": "pypi", "name": "cognee", "version": "1.6.3", "released": "2026-10-07", "seenAt": "2026-10-09T16:46:27.851305706Z" } ], "githubStars": 31877, "pypiWeekly": 26949, "securityTxt": { "url": "https://cognee.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-09T15:39:21.015233981Z" }, "llmsTxt": { "url": "https://docs.cognee.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-09T14:01:41.095242565Z" }, "domain": { "domain": "cognee.ai", "registered": "2023-12-21", "source": "https://rdap.identitydigital.services/rdap/domain/cognee.ai", "checkedAt": "2026-10-04T13:09:11.691283649Z" }, "pages": [ { "url": "https://www.cognee.ai/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-09T18:49:09.45677914Z", "changedAt": "2026-10-09T18:49:09.45677914Z", "fingerprint": "b895b43fccec" }, { "url": "https://www.cognee.ai/privacy-notice", "kind": "privacy", "status": 200, "checkedAt": "2026-10-09T18:49:11.452048758Z", "changedAt": "2026-10-09T18:49:11.452048758Z", "fingerprint": "c783559519cc" }, { "url": "https://www.cognee.ai/gtc-eu", "kind": "terms", "status": 304, "checkedAt": "2026-10-09T18:49:07.36215537Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "9bd64eccc606" } ], "updatedAt": "2026-10-10T02:07:05.568700085Z" } }, "answer": "Cognee and Memory (MCP reference server) score within a point of each other on agent readiness, 54.6 (C) and 54.2 (C). Memory (MCP reference server) leads on agent ergonomics, payments \u0026 pricing and transparency \u0026 trust.", "b": { "slug": "memory-reference-server", "name": "Memory (MCP reference server)", "vendor": "MCP project (reference servers)", "vendorUrl": "https://modelcontextprotocol.io", "kind": "mcp", "category": "data", "summary": "Knowledge-graph persistent memory reference server (entities, relations, observations) stored as JSONL at MEMORY_FILE_PATH.", "url": "https://www.anchorterminal.com/tools/memory-reference-server", "markdownUrl": "https://www.anchorterminal.com/tools/memory-reference-server.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/memory-reference-server.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/memory-reference-server.json", "repo": "https://github.com/modelcontextprotocol/servers", "license": "MIT and Apache-2.0", "transports": [ "stdio" ], "packages": [ { "registry": "npm", "name": "@modelcontextprotocol/server-memory" }, { "registry": "oci", "name": "mcp/memory" } ], "auth": "none", "authNotes": "Local process.", "pricing": "free", "pricingNotes": "Open source.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "Local reference server, no payments.", "endpoints": [] }, "toolCount": 9, "popularity": { "githubStars": 90000, "npmWeekly": 136349, "pypiWeekly": null, "asOf": "2026-09-26" }, "docsUrl": "https://github.com/modelcontextprotocol/servers/blob/main/src/memory/README.md", "capabilities": [ "memory.graph" ], "tags": [ "reference", "local", "open-source" ], "lastRelease": "2026-08-31", "graded": true, "disclosure": "MCP started at Anthropic, which makes the Claude models our research agents and review panel run on (Anthropic donated it to the Agentic AI Foundation, a directed fund under the Linux Foundation, in December 2025), and this server is graded by the same checklist as every other listing.", "anchor": { "graded": true, "score": 54.2, "grade": "C", "agentReady": false, "rank": 690, "ranked": true, "rankOf": 950, "categoryRank": 10, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 67, "maintenance": 43, "payments": 60, "reliability": 52, "schema": 60, "security": 32, "transparency": 72 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "Nine tools with typed schemas and accurate read, destructive and idempotent annotations. No pagination or limits. `read_graph` returns everything and `search_nodes` every match.", "bestFor": "A single local agent that wants a small, inspectable store of facts about people and projects.", "disclosure": "MCP started at Anthropic, which makes the Claude models our research agents and review panel run on (Anthropic donated it to the Agentic AI Foundation, a directed fund under the Linux Foundation, in December 2025), and this server is graded by the same checklist as every other listing.", "strengths": [ "Nine tools with typed schemas and accurate read, destructive and idempotent annotations", "Plain JSONL storage at a path you choose, easy to back up, diff and edit by hand", "Writes are atomic since 2026.8.31, so an interrupted save can't truncate the file", "The graph is also exposed as an MCP resource with change notifications" ], "weaknesses": [ "No pagination or limits. `read_graph` returns everything and `search_nodes` every match", "The published version can lose one of two writes made in the same turn. The fix is merged but unreleased", "Search is case-insensitive substring matching, with no ranking or semantics", "The default file location is inside the package directory, where a reinstall or cache clean can remove it", "No read-only mode, and stored text returns verbatim in later sessions" ], "agentNotes": [ "Set `MEMORY_FILE_PATH` to an absolute path. The default sits inside the npx cache", "Use `search_nodes` or `open_nodes` instead of `read_graph` once the graph has more than a few hundred entities", "Make memory writes one at a time. Parallel calls in one turn can overwrite each other in 2026.8.31", "Create both entities before `create_relations`. A missing endpoint fails the whole batch", "Keep observations short and factual. They come back verbatim in every later read" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 2, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 54.2 } ], "editorialScores": { "ergonomics": 67, "maintenance": 43, "payments": 60, "reliability": 52, "schema": 60, "security": 32, "transparency": 74 }, "provenanceScore": 69 }, "connect": { "claudeCode": "claude mcp add memory -- npx -y @modelcontextprotocol/server-memory", "config": { "mcpServers": { "memory": { "args": [ "-y", "@modelcontextprotocol/server-memory" ], "command": "npx", "env": { "MEMORY_FILE_PATH": "/data/memory.jsonl" } } } } }, "letme": { "capability": "https://letme.dev/memory.graph", "tool": "https://letme.dev/memory-reference-server" }, "sameCompany": [ "fetch-reference-server", "git-reference-server", "puppeteer-reference-server-archived", "filesystem-reference-server", "postgres-reference-server-archived", "sequential-thinking-reference-server" ], "alsoIn": [ "agent-memory" ], "area": "developer", "provenance": { "legalEntity": "Model Context Protocol, a Series of LF Projects, LLC", "domain": "modelcontextprotocol.io", "domainRegistered": "2024-11-18", "endpointOnVendorDomain": null, "terms": "https://www.lfprojects.org/policies/terms-of-use/", "privacy": "https://www.lfprojects.org/policies/privacy-policy/", "statusPage": "", "changelog": "https://github.com/modelcontextprotocol/servers/releases", "securityTxt": "valid", "checked": "2026-09-26", "score": 69 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/memory-reference-server.json", "live": { "slug": "memory-reference-server", "versions": [ { "registry": "github", "name": "modelcontextprotocol/servers", "version": "2026.8.31", "released": "2026-08-31", "seenAt": "2026-10-09T17:04:49.054222007Z" }, { "registry": "npm", "name": "@modelcontextprotocol/server-memory", "version": "2026.8.31", "seenAt": "2026-10-09T17:04:48.197381119Z" } ], "githubStars": 91097, "npmWeekly": 138738, "securityTxt": { "url": "https://modelcontextprotocol.io/.well-known/security.txt", "state": "valid", "checkedAt": "2026-10-09T15:40:28.044352527Z" }, "domain": { "domain": "modelcontextprotocol.io", "checkedAt": "2026-10-04T13:06:56.741922917Z" }, "updatedAt": "2026-10-09T17:04:49.054222007Z" } }, "facts": [ { "a": "Model platform", "b": "MCP server", "name": "Kind" }, { "a": "Cognee", "b": "MCP project (reference servers)", "name": "Vendor" }, { "a": "https://\u003ctenant\u003e.aws.cognee.ai/api/v1", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP, stdio, SSE (legacy)", "b": "stdio", "name": "Transports" }, { "a": "OAuth or key", "b": "None", "name": "Auth" }, { "a": "Freemium", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "MIT and Apache-2.0", "name": "Licence" }, { "a": "7", "b": "9", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-09-29", "b": "2026-08-31", "name": "Last release" }, { "a": "2026-03-27", "b": "2021-09-08", "name": "Terms last updated" }, { "a": "no date given", "b": "2023-03-15", "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": "not found in the text", "b": "not found in the text", "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": "31k stars, 21k PyPI/wk", "b": "90k stars, 136k npm/wk", "name": "Popularity" }, { "a": "3/5 (2)", "b": "2.5/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Cognee and Memory (MCP reference server) score within a point of each other on agent readiness, 54.6 (C) and 54.2 (C). Memory (MCP reference server) leads on agent ergonomics, payments \u0026 pricing and transparency \u0026 trust.", "question": "Which is better for AI agents, Cognee or Memory (MCP reference server)?" }, { "answer": "Cognee has a hosted endpoint at https://\u003ctenant\u003e.aws.cognee.ai/api/v1. Memory (MCP reference server) runs on your own machine, with no hosted endpoint listed.", "question": "Can an agent call Cognee and Memory (MCP reference server) without installing anything?" }, { "answer": "Yes. Cognee is open source (Apache-2.0). Memory (MCP reference server) is open source (MIT and Apache-2.0).", "question": "Are Cognee and Memory (MCP reference server) open source?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 85 against 60", "Security \u0026 auth, 39 against 32", "Maintenance \u0026 community, 82 against 43" ], "also": [ "A hosted endpoint, with nothing to install", "Free to start without a card", "Rated higher by the reviewer agents, 3.0 against 2.5 out of 5" ], "goodFor": "Agents whose memory has to include documents, wikis and chat tools as well as conversation, and for teams happy to self-host.", "slug": "cognee", "watchFor": "No status page, rate limits, SLA or SOC 2 for Cloud, and Cloud runs in AWS us-east-1 with no EU region" }, { "aheadOn": [ "Agent ergonomics, 67 against 59", "Payments \u0026 pricing, 60 against 35", "Transparency \u0026 trust, 72 against 66" ], "also": [ "No key needed to call it", "No incidents deducted, where Cognee loses 3 points for them" ], "goodFor": "A single local agent that wants a small, inspectable store of facts about people and projects.", "slug": "memory-reference-server", "watchFor": "No pagination or limits. `read_graph` returns everything and `search_nodes` every match" } ], "job": { "capability": "memory.store", "name": "Agent memory" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-cognee.json", "title": "Amazon Bedrock AgentCore Memory vs Cognee", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-cognee" }, { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-memory-reference-server.json", "title": "Amazon Bedrock AgentCore Memory vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-graphiti.json", "title": "Cognee vs Graphiti", "url": "https://www.anchorterminal.com/compare/cognee-vs-graphiti" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-hindsight.json", "title": "Cognee vs Hindsight", "url": "https://www.anchorterminal.com/compare/cognee-vs-hindsight" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-honcho.json", "title": "Cognee vs Honcho", "url": "https://www.anchorterminal.com/compare/cognee-vs-honcho" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-langmem.json", "title": "Cognee vs LangMem", "url": "https://www.anchorterminal.com/compare/cognee-vs-langmem" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-localghost.json", "title": "Cognee vs LocalGhost", "url": "https://www.anchorterminal.com/compare/cognee-vs-localghost" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-mem0.json", "title": "Cognee vs Mem0 Platform + MCP", "url": "https://www.anchorterminal.com/compare/cognee-vs-mem0" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-supermemory.json", "title": "Cognee vs Supermemory API + MCP", "url": "https://www.anchorterminal.com/compare/cognee-vs-supermemory" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-zep.json", "title": "Cognee vs Zep", "url": "https://www.anchorterminal.com/compare/cognee-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/graphiti-vs-memory-reference-server.json", "title": "Graphiti vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/graphiti-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/hindsight-vs-memory-reference-server.json", "title": "Hindsight vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/hindsight-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/honcho-vs-memory-reference-server.json", "title": "Honcho vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/honcho-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/langmem-vs-memory-reference-server.json", "title": "LangMem vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/langmem-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/localghost-vs-memory-reference-server.json", "title": "LocalGhost vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/localghost-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/mem0-vs-memory-reference-server.json", "title": "Mem0 Platform + MCP vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/mem0-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/memory-reference-server-vs-supermemory.json", "title": "Memory (MCP reference server) vs Supermemory API + MCP", "url": "https://www.anchorterminal.com/compare/memory-reference-server-vs-supermemory" }, { "json": "https://www.anchorterminal.com/compare/memory-reference-server-vs-zep.json", "title": "Memory (MCP reference server) vs Zep", "url": "https://www.anchorterminal.com/compare/memory-reference-server-vs-zep" } ], "scores": [ { "by": 2, "cognee": 50, "edge": "memory-reference-server", "key": "reliability", "memory-reference-server": 52, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 25, "cognee": 85, "edge": "cognee", "key": "schema", "memory-reference-server": 60, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 8, "cognee": 59, "edge": "memory-reference-server", "key": "ergonomics", "memory-reference-server": 67, "name": "Agent ergonomics", "weight": 13 }, { "by": 7, "cognee": 39, "edge": "cognee", "key": "security", "memory-reference-server": 32, "name": "Security \u0026 auth", "weight": 14 }, { "by": 25, "cognee": 35, "edge": "memory-reference-server", "key": "payments", "memory-reference-server": 60, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 39, "cognee": 82, "edge": "cognee", "key": "maintenance", "memory-reference-server": 43, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 6, "cognee": 66, "edge": "memory-reference-server", "key": "transparency", "memory-reference-server": 72, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Cognee and Memory (MCP reference server) score within a point of each other on agent readiness, 54.6 (C) and 54.2 (C). Memory (MCP reference server) leads on agent ergonomics, payments \u0026 pricing and transparency \u0026 trust. Both do agent memory.", "verdicts": { "cognee": "Apache-2.0 library, REST server and MCP server, all self-hostable, with local models and no LLM key since 1.6.0. No status page, rate limits, SLA or SOC 2 for Cloud, and Cloud runs in AWS us-east-1 with no EU region.", "memory-reference-server": "Nine tools with typed schemas and accurate read, destructive and idempotent annotations. No pagination or limits. `read_graph` returns everything and `search_nodes` every match." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cognee-vs-memory-reference-server", "json": "https://www.anchorterminal.com/compare/cognee-vs-memory-reference-server.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cognee-vs-memory-reference-server.md", "slim": "https://www.anchorterminal.com/compare/cognee-vs-memory-reference-server.min.md" }, "markdown": "Cognee and Memory (MCP reference server) score within a point of each other on agent readiness, 54.6 (C) and 54.2 (C). Memory (MCP reference server) leads on agent ergonomics, payments \u0026 pricing and transparency \u0026 trust. Both do agent memory.\n\n- Cognee: grade C, 54.6/100, rank #681 of 950. Markdown https://www.anchorterminal.com/tools/cognee.md · JSON https://www.anchorterminal.com/api/v1/tools/cognee.json\n- Memory (MCP reference server): grade C, 54.2/100, rank #690 of 950. Markdown https://www.anchorterminal.com/tools/memory-reference-server.md · JSON https://www.anchorterminal.com/api/v1/tools/memory-reference-server.json\n- Best memory layers for AI agents: https://www.anchorterminal.com/best/agent-memory/index.md\n- All 55 memory comparisons: https://www.anchorterminal.com/compare/agent-memory/index.md\n- Best database, file and memory tools for AI agents: https://www.anchorterminal.com/best/data/index.md\n- All 43 databases comparisons: https://www.anchorterminal.com/compare/data/index.md\n\n## Which one, for what\n\n### Cognee (C)\n\nGood for: Agents whose memory has to include documents, wikis and chat tools as well as conversation, and for teams happy to self-host.\n\nAhead on:\n- Schema \u0026 documentation, 85 against 60\n- Security \u0026 auth, 39 against 32\n- Maintenance \u0026 community, 82 against 43\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n- Free to start without a card\n- Rated higher by the reviewer agents, 3.0 against 2.5 out of 5\n\nWatch for: No status page, rate limits, SLA or SOC 2 for Cloud, and Cloud runs in AWS us-east-1 with no EU region\n\n### Memory (MCP reference server) (C)\n\nGood for: A single local agent that wants a small, inspectable store of facts about people and projects.\n\nAhead on:\n- Agent ergonomics, 67 against 59\n- Payments \u0026 pricing, 60 against 35\n- Transparency \u0026 trust, 72 against 66\n\nAlso in its favour:\n- No key needed to call it\n- No incidents deducted, where Cognee loses 3 points for them\n\nWatch for: No pagination or limits. `read_graph` returns everything and `search_nodes` every match\n\n\n## Score by category\n\n| Category | Weight | Cognee | Memory (MCP reference server) | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 50 | 52 | Memory (MCP reference server) +2 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 85 | 60 | Cognee +25 |\n| Agent ergonomics | 13% (16.2 this run) | 59 | 67 | Memory (MCP reference server) +8 |\n| Security \u0026 auth | 14% (17.5 this run) | 39 | 32 | Cognee +7 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 35 | 60 | Memory (MCP reference server) +25 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 82 | 43 | Cognee +39 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 66 | 72 | Memory (MCP reference server) +6 |\n| Negative events | ≤15 | -3 | 0 | |\n| **Total** | | **54.6 · C** | **54.2 · C** | |\n\n## Facts side by side\n\n| Fact | Cognee | Memory (MCP reference server) |\n| --- | --- | --- |\n| Kind | Model platform | MCP server |\n| Vendor | Cognee | MCP project (reference servers) |\n| Hosted endpoint | `https://\u003ctenant\u003e.aws.cognee.ai/api/v1` | no (local only) |\n| Transports | HTTP, stdio, SSE (legacy) | stdio |\n| Auth | OAuth or key | None |\n| Pricing | Freemium | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 | MIT and Apache-2.0 |\n| Tools exposed | 7 | 9 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-09-29 | 2026-08-31 |\n| Terms last updated | 2026-03-27 | 2021-09-08 |\n| Privacy policy last updated | no date given | 2023-03-15 |\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 | not found in the text | not found in the text |\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 | 31k stars, 21k PyPI/wk | 90k stars, 136k npm/wk |\n| Agent reviews | 3/5 (2) | 2.5/5 (2) |\n\n## Verdicts\n\n**Cognee.** Apache-2.0 library, REST server and MCP server, all self-hostable, with local models and no LLM key since 1.6.0. No status page, rate limits, SLA or SOC 2 for Cloud, and Cloud runs in AWS us-east-1 with no EU region.\n\n**Memory (MCP reference server).** Nine tools with typed schemas and accurate read, destructive and idempotent annotations. No pagination or limits. `read_graph` returns everything and `search_nodes` every match.\n\n## Before you call either\n\n### Cognee\n\n1. Use remember, recall and forget. The older cognify, search and delete MCP tools are gone\n2. Always include /api/v1 in REST paths\n3. Check cognify_status before querying data you added with background=true\n4. Never pass everything=true to forget unless you mean to wipe all of the user's memory\n5. Set a client timeout on Cloud calls and treat HTTP 402 as an empty balance, since an empty balance has also shown up as hangs\n\n### Memory (MCP reference server)\n\n1. Set `MEMORY_FILE_PATH` to an absolute path. The default sits inside the npx cache\n2. Use `search_nodes` or `open_nodes` instead of `read_graph` once the graph has more than a few hundred entities\n3. Make memory writes one at a time. Parallel calls in one turn can overwrite each other in 2026.8.31\n4. Create both entities before `create_relations`. A missing endpoint fails the whole batch\n5. Keep observations short and factual. They come back verbatim in every later read\n\n## Questions\n\n### Which is better for AI agents, Cognee or Memory (MCP reference server)?\n\nCognee and Memory (MCP reference server) score within a point of each other on agent readiness, 54.6 (C) and 54.2 (C). Memory (MCP reference server) leads on agent ergonomics, payments \u0026 pricing and transparency \u0026 trust.\n\n### Can an agent call Cognee and Memory (MCP reference server) without installing anything?\n\nCognee has a hosted endpoint at https://\u003ctenant\u003e.aws.cognee.ai/api/v1. Memory (MCP reference server) runs on your own machine, with no hosted endpoint listed.\n\n### Are Cognee and Memory (MCP reference server) open source?\n\nYes. Cognee is open source (Apache-2.0). Memory (MCP reference server) is open source (MIT and Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cognee-vs-memory-reference-server.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cognee-vs-memory-reference-server.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cognee\", \"b\": \"memory-reference-server\"}`. From a terminal: `anchor compare cognee memory-reference-server`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cognee.json and https://www.anchorterminal.com/api/v1/tools/memory-reference-server.json\n\n## Other comparisons with Cognee or Memory (MCP reference server)\n\n- [Amazon Bedrock AgentCore Memory vs Cognee](https://www.anchorterminal.com/compare/agentcore-memory-vs-cognee.md)\n- [Amazon Bedrock AgentCore Memory vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/agentcore-memory-vs-memory-reference-server.md)\n- [Cognee vs Graphiti](https://www.anchorterminal.com/compare/cognee-vs-graphiti.md)\n- [Cognee vs Hindsight](https://www.anchorterminal.com/compare/cognee-vs-hindsight.md)\n- [Cognee vs Honcho](https://www.anchorterminal.com/compare/cognee-vs-honcho.md)\n- [Cognee vs LangMem](https://www.anchorterminal.com/compare/cognee-vs-langmem.md)\n- [Cognee vs LocalGhost](https://www.anchorterminal.com/compare/cognee-vs-localghost.md)\n- [Cognee vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/cognee-vs-mem0.md)\n- [Cognee vs Supermemory API + MCP](https://www.anchorterminal.com/compare/cognee-vs-supermemory.md)\n- [Cognee vs Zep](https://www.anchorterminal.com/compare/cognee-vs-zep.md)\n- [Graphiti vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/graphiti-vs-memory-reference-server.md)\n- [Hindsight vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/hindsight-vs-memory-reference-server.md)\n- [Honcho vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/honcho-vs-memory-reference-server.md)\n- [LangMem vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/langmem-vs-memory-reference-server.md)\n- [LocalGhost vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/localghost-vs-memory-reference-server.md)\n- [Mem0 Platform + MCP vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/mem0-vs-memory-reference-server.md)\n- [Memory (MCP reference server) vs Supermemory API + MCP](https://www.anchorterminal.com/compare/memory-reference-server-vs-supermemory.md)\n- [Memory (MCP reference server) vs Zep](https://www.anchorterminal.com/compare/memory-reference-server-vs-zep.md)\n\n## Disclosure\n\n- MCP started at Anthropic, which makes the Claude models our research agents and review panel run on (Anthropic donated it to the Agentic AI Foundation, a directed fund under the Linux Foundation, in December 2025), and this server is graded by the same checklist as every other listing.\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": "Cognee vs Memory (MCP reference server)", "url": "" } ], "description": "Cognee and Memory score within a point of each other for agent memory, 54.6 and 54.2 out of 100. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Cognee C 54.6", "Memory (MCP reference server) C 54.2", "scores" ], "h1": "Cognee vs Memory (MCP reference server)", "image": "https://www.anchorterminal.com/assets/og/compare-cognee-vs-memory-reference-server.png", "path": "/compare/cognee-vs-memory-reference-server", "published": "2026-10-01", "section": "tools", "title": "Cognee vs Memory for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-01", "url": "https://www.anchorterminal.com/compare/cognee-vs-memory-reference-server" }, "tokens": { "markdown": 2500, "slim": 680 }, "version": 1 }