{ "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", "dns": "cognee.grade.anchorterminal.com", "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 self-hosted REST server defaults to multi-tenant mode with authentication required (`ENABLE_BACKEND_ACCESS_CONTROL=true`) and takes a Bearer token; single-user mode turns auth off. Since 1.6.0 (18 September 2026) the library builds and searches text memory with local models and no LLM key. 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, delivered as a bring-your-own-cloud engagement (https://www.cognee.ai/pricing). The billing docs give the same rates but say the free workspace includes 10 million tokens. Credit is prepaid from $0.50, with optional auto-recharge, and a request the balance can't cover is rejected with HTTP 402 (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": null, "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": "2026-10-29", "graded": true, "anchor": { "graded": true, "score": 47.7, "grade": "D", "agentReady": false, "rank": 1146, "ranked": true, "rankOf": 1510, "categoryRank": 24, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 59, "maintenance": 82, "payments": 35, "reliability": 43, "schema": 85, "security": 39, "transparency": 72 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-04" }, "negative": -9, "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). Later breaking changes fold into this term. v1.6.3 (7 October) raises on a `node_set` that isn't a list of strings, v1.6.5 (16 October) turns `CYPHER` and `NATURAL_LANGUAGE` search off, and v1.6.6 (29 October) removes the `fs` session cache and the device-code login behind a bare `serve()`, each in a patch release with the change first posted in its release notes (https://docs.cognee.ai/changelog)", "2026-09-18 to 2026-10-29: released fixes of Cognee's own described flaws with no advisory on OSV, -3. v1.6.0 fixes a cross-tenant leak in which a manager of one tenant could read a user's roles in another, v1.6.3 stops agent connections being listed to other callers, v1.6.5 turns off raw Cypher search because any reader of a dataset could run arbitrary queries, and v1.6.6 confines prompt reads to the prompt directory (GHSA-35v8-jp26-7r4f, which osv.dev doesn't list) (https://docs.cognee.ai/changelog)", "2026-07-07: CVE-2026-58473 (GHSA-49f7-whx5-4256, PYSEC-2026-3816), Critical 9.3, assigned by VulnCheck with no repository advisory. Self-registered users could overwrite the global LLM configuration and send every tenant's prompts and documents to their own endpoint. Fixed (OSV gives 1.5.0), over two months old, -1 (https://osv.dev/vulnerability/GHSA-49f7-whx5-4256)", "2026-09-20 onwards: the privacy notice calls library telemetry \"anonymous\" with \"an anonymous installation identifier\", and the Security and Privacy page calls it anonymous, while default events carry the Cognee user and tenant UUIDs, a persistent machine ID, and, when connected to Cognee Cloud, the tenant ID and the `*.cognee.ai` host. A misleading claim, -2 (https://www.cognee.ai/privacy-notice)" ], "verdict": "Apache-2.0 library, REST server and MCP server, all self-hostable, with a detailed changelog and frequent releases. Cloud has no status page, rate limits or SOC 2, and runs in AWS us-east-1. Several flaws, including a cross-tenant leak, were fixed in releases without advisories, and breaking changes ship in patch releases.", "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", "REST reference pages publish their OpenAPI 3.1 operations, with documented error codes", "Metered Cloud at $1 per million tokens, 1 million free with no card", "More than ten stable releases from 8 August to 29 October 2026, each with dated release notes" ], "weaknesses": [ "No status page, rate limits, SLA figure or SOC 2 for Cloud, and Cloud runs in AWS us-east-1 with no EU region", "Security fixes, including a cross-tenant leak in 1.6.0, shipped without published advisories", "Breaking changes ship in patch releases (1.6.3, 1.6.5, 1.6.6), and 11 MCP tools went in May without a version bump", "Library telemetry is on by default and carries user and tenant UUIDs, while the privacy notice calls it anonymous", "Billing docs and pricing page disagree on the free token allowance" ], "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", "Treat HTTP 402 as an empty Cloud balance and set a client timeout, since a run that exhausts credit part-way reports Failed in dataset status instead", "Read the \"Upgrading\" list in each release's notes before moving to a new patch version" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 47.7 } ], "editorialScores": { "ergonomics": 59, "maintenance": 82, "payments": 35, "reliability": 43, "schema": 85, "security": 39, "transparency": 78 }, "provenanceScore": 65, "checked": { "categories": { "ergonomics": "2026-11-04", "maintenance": "2026-11-04", "payments": "2026-11-04", "reliability": "2026-11-04", "schema": "2026-11-04", "security": "2026-11-04", "transparency": "2026-11-04" }, "last": "2026-11-04", "lastMoved": "2026-11-04", "oldest": "2026-11-04", "stale": false, "staleAfterDays": 90 } }, "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": "2026-11-04", "notes": [ "The EU general terms (effective 27 March 2026) name Topoteretes UG (haftungsbeschränkt), Amtsgericht Charlottenburg HRB 252065 B, under German law. US general terms of the same date name Cognee Inc. (https://www.cognee.ai/gtc-us).", "No security.txt or status page found; SECURITY.md in the repository sends reports to security@cognee.ai or GitHub's private reporting, with a 2-business-day acknowledgement.", "The privacy notice, current version 20 September 2026, says Cognee Cloud is operated by Cognee Inc. and hosted in AWS us-east-1, and names Topoteretes UG as its EU operating subsidiary." ], "score": 65 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/cognee.json", "live": { "slug": "cognee", "probe": { "target": "https://\u003ctenant\u003e.aws.cognee.ai/api/v1", "method": "get", "lastAt": "2026-11-07T19:22:00.421590325Z", "lastOk": false, "lastStatus": 0, "lastMs": 0, "lastNote": "DNS lookup failed", "authRequired": false, "uptime24h": 0, "uptime30d": 0, "p50ms24h": 0, "p95ms24h": 0, "samples24h": 238, "samples30d": 7920, "days": [ { "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": 247, "ok": 0 }, { "date": "2026-10-11", "probes": 247, "ok": 0 }, { "date": "2026-10-12", "probes": 247, "ok": 0 }, { "date": "2026-10-13", "probes": 248, "ok": 0 }, { "date": "2026-10-14", "probes": 249, "ok": 0 }, { "date": "2026-10-15", "probes": 253, "ok": 0 }, { "date": "2026-10-16", "probes": 252, "ok": 0 }, { "date": "2026-10-17", "probes": 253, "ok": 0 }, { "date": "2026-10-18", "probes": 256, "ok": 0 }, { "date": "2026-10-19", "probes": 255, "ok": 0 }, { "date": "2026-10-20", "probes": 252, "ok": 0 }, { "date": "2026-10-21", "probes": 253, "ok": 0 }, { "date": "2026-10-22", "probes": 253, "ok": 0 }, { "date": "2026-10-23", "probes": 248, "ok": 0 }, { "date": "2026-10-24", "probes": 251, "ok": 0 }, { "date": "2026-10-25", "probes": 250, "ok": 0 }, { "date": "2026-10-26", "probes": 252, "ok": 0 }, { "date": "2026-10-27", "probes": 249, "ok": 0 }, { "date": "2026-10-28", "probes": 251, "ok": 0 }, { "date": "2026-10-29", "probes": 249, "ok": 0 }, { "date": "2026-10-30", "probes": 248, "ok": 0 }, { "date": "2026-10-31", "probes": 251, "ok": 0 }, { "date": "2026-11-01", "probes": 249, "ok": 0 }, { "date": "2026-11-02", "probes": 250, "ok": 0 }, { "date": "2026-11-03", "probes": 248, "ok": 0 }, { "date": "2026-11-04", "probes": 246, "ok": 0 }, { "date": "2026-11-05", "probes": 185, "ok": 0 }, { "date": "2026-11-06", "probes": 241, "ok": 0 }, { "date": "2026-11-07", "probes": 197, "ok": 0 } ] }, "versions": [ { "registry": "github", "name": "topoteretes/cognee", "version": "v1.6.7", "released": "2026-11-06", "seenAt": "2026-11-06T23:16:24.652822343Z" }, { "registry": "pypi", "name": "cognee", "version": "1.6.7", "released": "2026-11-06", "seenAt": "2026-11-06T23:16:24.544693781Z" } ], "githubStars": 33114, "pypiWeekly": 38033, "securityTxt": { "url": "https://cognee.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:00:38.055376681Z" }, "llmsTxt": { "url": "https://docs.cognee.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:05.867692681Z" }, "domain": { "domain": "cognee.ai", "registered": "2023-12-21", "source": "https://rdap.identitydigital.services/rdap/domain/cognee.ai", "checkedAt": "2026-11-01T14:17:40.492155131Z" }, "pages": [ { "url": "https://docs.cognee.ai/changelog", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-07T14:05:38.327099277Z", "changedAt": "2026-11-07T14:05:38.327099277Z", "fingerprint": "ce1ff92f1e6e" }, { "url": "https://www.cognee.ai/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:26:59.613514784Z", "changedAt": "2026-11-05T13:10:57.169704735Z", "fingerprint": "78b4a35f57a1" }, { "url": "https://www.cognee.ai/privacy-notice", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:27:01.748287383Z", "changedAt": "2026-11-05T13:10:59.22394133Z", "fingerprint": "b018b51db53f" }, { "url": "https://www.cognee.ai/gtc-eu", "kind": "terms", "status": 304, "checkedAt": "2026-11-07T14:26:57.492553915Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "9bd64eccc606" } ], "github": { "repo": "topoteretes/cognee", "checkedAt": "2026-11-02T09:32:30.198422991Z", "stars": 32996, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-02T07:53:50Z", "openIssues": 781, "openPRs": 294, "issuesOpened90d": 884, "issuesClosed90d": 263, "prsMerged90d": 796, "ci": { "branch": "main", "runs": 50, "success": 43, "failure": 6, "other": 1, "latest": "failure", "latestAt": "2026-10-29T22:20:34Z" }, "advisories": [ { "ghsa": "GHSA-8pr4-p4c8-8gr9", "cve": "CVE-2026-31231", "severity": "critical", "published": "2026-09-15T15:55:05Z" } ], "replies": { "sampled": 12, "unanswered": 12 } }, "updatedAt": "2026-11-07T19:22:00.421590325Z" } }, "answer": "EverOS scores 69.4 (B) on agent readiness against Cognee's 47.7 (D), and leads in 5 of 7 scored categories.", "b": { "slug": "everos", "name": "EverOS", "vendor": "Evermind AI, Inc.", "vendorUrl": "https://evermind.ai", "kind": "http-api", "category": "agent-memory", "summary": "EverOS, formerly EverMemOS, is EverMind's open-source memory runtime for agents. It stores conversations, files and agent trajectories as Markdown with SQLite and LanceDB indexes, behind a local HTTP API and MCP server, with a managed EverOS Cloud.", "url": "https://www.anchorterminal.com/tools/everos", "markdownUrl": "https://www.anchorterminal.com/tools/everos.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/everos.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/everos.json", "dns": "everos.grade.anchorterminal.com", "repo": "https://github.com/EverMind-AI/EverOS", "license": "Apache-2.0", "transports": [ "http", "stdio" ], "packages": [ { "registry": "pypi", "name": "everos" }, { "registry": "pypi", "name": "everos-mcp" } ], "auth": "none", "authNotes": "The self-hosted server has no authentication and binds to 127.0.0.1:8000 by default. The owner supplies LLM and embedding provider keys in ~/.everos/everos.toml. EverOS Cloud uses a bearer API key from the console at everos.evermind.ai, and its hosted MCP connector signs in with an EverOS account.", "pricing": "freemium", "pricingNotes": "Free under Apache-2.0 to run locally, with LLM and embedding costs paid to the chosen provider. EverOS Cloud has a console and API keys, but no plan or price was found on evermind.ai or docs.evermind.ai.", "priceSummary": "Freemium", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the repository, the OpenAPI document, llms.txt or the docs (checked 2026-11-06).", "endpoints": [] }, "toolCount": 7, "popularity": { "githubStars": 13839, "npmWeekly": null, "pypiWeekly": 4033, "asOf": "2026-11-06" }, "docsUrl": "https://docs.evermind.ai", "llmsTxt": "https://docs.evermind.ai/llms.txt", "openapi": "https://github.com/EverMind-AI/EverOS/blob/main/docs/openapi.json", "capabilities": [ "memory.store", "memory.search", "memory.user", "memory.delete" ], "tags": [ "open-source", "self-hosted", "local", "hosted", "apache-2.0", "python", "mcp", "openapi", "llms-txt", "markdown", "no-auth" ], "lastRelease": "2026-10-22", "graded": true, "anchor": { "graded": true, "score": 69.4, "grade": "B", "agentReady": false, "rank": 247, "ranked": true, "rankOf": 1510, "categoryRank": 6, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 78, "maintenance": 80, "payments": 40, "reliability": 79, "schema": 89, "security": 47, "transparency": 71 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "EverOS keeps agent and user memory as Markdown with SQLite and LanceDB indexes, behind a described OpenAPI with typed, retryable errors and an MCP server, under Apache-2.0 at version 1.5.1. The local server has no authentication, EverOS Cloud prices are not published, and the cloud terms forbid automated data extraction.", "bestFor": "Self-hosted memory for agents and apps that want Markdown as the source of truth and separate user and agent tracks.", "strengths": [ "Apache-2.0 Python library and local server at 1.5.1, with Keep a Changelog entries and semantic versioning declared", "OpenAPI document with 40 operations, every one described, and llms.txt plus llms-full.txt for the docs", "Retryable conditions are typed, such as 503 SESSION_BUSY and EXTERNAL_SERVICE_UNAVAILABLE for a busy database", "Memory is canonical Markdown on disk, editable by hand, with deletion by owner, session or memory id", "SECURITY.md with a five-day acknowledgement, plus a valid security.txt at evermind.ai" ], "weaknesses": [ "The local HTTP server has no authentication and relies on binding to 127.0.0.1", "EverOS Cloud prices, plans and rate limits were not found on any public page", "The MCP server's autonomy protocol tells hosts to save facts without being asked, and no prompt-injection guidance was found", "The cloud terms of 20 January 2026 forbid automated extraction and allow discontinuing the service without notice", "Several outside bug reports, such as a silent capture failure, have no reply" ], "agentNotes": [ "Write new code against `/api/v2`; `/api/v1` is a legacy alias that may go in a future major release", "Call `/api/v2/memory/flush` at the end of a session, since `add` is asynchronous and buffers recent messages", "Retry on 503 SESSION_BUSY or EXTERNAL_SERVICE_UNAVAILABLE after a pause; nothing was written", "Keep `host` at 127.0.0.1 unless something in front adds authentication", "Treat recalled memories as untrusted text, since they are extracted from past conversations" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 69.4 } ], "editorialScores": { "ergonomics": 78, "maintenance": 80, "payments": 40, "reliability": 79, "schema": 89, "security": 47, "transparency": 66 }, "provenanceScore": 75, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "uv pip install everos \u0026\u0026 everos init \u0026\u0026 everos server start", "http": "curl http://127.0.0.1:8000/health", "claudeCode": "claude mcp add everos -e EVEROS_BASE_URL=http://127.0.0.1:8000 -- uvx everos-mcp" }, "letme": { "capability": "https://letme.dev/memory.store", "tool": "https://letme.dev/everos" }, "area": "agent-runtime", "provenance": { "legalEntity": "Evermind AI, Inc.", "domain": "evermind.ai", "domainRegistered": "2020-02-22", "endpointOnVendorDomain": null, "terms": "https://evermind.ai/terms-of-service", "privacy": "https://evermind.ai/privacy-policy", "statusPage": "", "changelog": "https://github.com/EverMind-AI/EverOS/blob/main/CHANGELOG.md", "securityTxt": "valid", "checked": "2026-11-06", "notes": [ "Terms and privacy policy both say last updated 20 January 2026 and name Evermind AI, Inc. The terms choose Singapore law and forbid extracting data by bots, scripts, crawlers or data-mining tools, recorded here as a fact.", "evermind.ai/robots.txt allows all crawlers and names Claude-Web and anthropic-ai as allowed. docs.evermind.ai carries Content-Signal ai-input=yes.", "RDAP gives evermind.ai a registration date of 22 February 2020.", "security.txt at evermind.ai/.well-known/ gives contact@evermind.ai and a policy URL, expiring 28 February 2027.", "The about page is drawn by script and returned no readable text." ], "score": 75 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/everos.json", "live": { "slug": "everos", "versions": [ { "registry": "github", "name": "EverMind-AI/EverOS", "version": "v1.5.1", "released": "2026-10-22", "seenAt": "2026-11-06T23:24:44.540703115Z" }, { "registry": "pypi", "name": "everos", "version": "1.5.1", "released": "2026-10-22", "seenAt": "2026-11-06T23:24:41.488069905Z" }, { "registry": "pypi", "name": "everos-mcp", "version": "0.1.1", "released": "2026-10-15", "seenAt": "2026-11-06T23:24:42.65503941Z" } ], "githubStars": 13840, "pypiWeekly": 4033, "securityTxt": { "url": "https://evermind.ai/.well-known/security.txt", "state": "valid", "expires": "2027-02-28T00:00:00Z", "checkedAt": "2026-11-07T16:01:32.419431813Z" }, "llmsTxt": { "url": "https://docs.evermind.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:26.933711899Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/EverMind-AI/EverOS/main/CHANGELOG.md", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:18:19.185692468Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "40ab92cf4d99" }, { "url": "https://evermind.ai/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:09:24.819286526Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "dcd843ca72fe" }, { "url": "https://evermind.ai/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:09:28.72898661Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "009377ab61a3" } ], "updatedAt": "2026-11-07T16:01:32.419431813Z" } }, "edges": [ { "by": 36, "category": "reliability", "leads": "everos", "name": "Reliability", "reasons": { "a": "We departed from the checklist here. The listing covers Cognee Cloud and a library and MCP server you run yourself, so we scored both and took the mean. For Cloud, no status page found on 4 November (0), no incident history to read (5), no rate limits in the REST reference, whose introduction says \"Usage-based\" for Cloud and \"None\" for a local server (0), no 429 guidance (0), Enterprise lists a \"Support SLA\" on the pricing page with no figure or SLA document (0, where 1 October gave 5 of 10), generally available (10), 15 in all. For the local package, cognee on PyPI with Python 3.10 to 3.14 stated in SECURITY.md and pyproject.toml (20). 64 GitHub Actions workflows, and test_suites.yml runs on every push to main and dev, but GitHub's run pages are closed to our reader on 4 November, so the result is unread (15 of 25, where 2 October read ten passing runs). Open regressions not counted, per the 2 October check (10 of 25). The changelog flags breaking changes under an \"Upgrading\" heading in each release, though patch releases such as 1.6.3, 1.6.5 and 1.6.6 carry them and 11 MCP tools went in May without a version bump (10 of 15). Version 1.6.6 (15). 70 in all. Mean 42.5, rounded half up to 43.", "b": "Local-software lines, as a library and server the owner runs. `everos` on PyPI with Python 3.12 or newer stated, plus a Windows guide (20). ci.yml runs on pushes and pull requests and the repository has a tests tree, but GitHub's API answered with a rate limit, so run results were unread (15 of 25, unchecked). 43 open issues and pull requests against 82 commits in 90 days; several outside bug reports, including a silent capture failure in the DSH plugin, have no reply (14 of 25). Keep a Changelog with semantic versioning declared and a 1.0 migration guide (15). Version 1.5.1 (15). Total 79." }, "scores": { "a": 43, "b": 79 } }, { "by": 19, "category": "ergonomics", "leads": "everos", "name": "Agent ergonomics", "reasons": { "a": "The tools reference lists 7 MCP tools, remember, recall, forget, code_search, search_tools, call_tool and cognify_status, with search_tools and call_tool reaching further tools on demand and COGNEE_MCP_TOOL_MODE=minimal cutting the list to the memory tools (25). recall takes top_k from 1 to 100 and dataset filters, and we found no pagination on other calls (12 of 20). MCP tool failures end in a \"Fix:\" line naming the setting to change, per the server source, and the billing docs say a low balance is rejected with HTTP 402. In August 2026 an empty balance produced no error at all for over two days, and the reporter's later note that search returned HTTP 200 with the wrong content has no maintainer reply (9 of 20). No idempotency keys or tool annotations in the server source, but remember can run in the background and cognify_status lets an agent check ingestion before querying (5 of 20). Python only, and the MCP server starts with one docker run (8 of 15). On 4 November the tools reference and cognee-mcp 0.5.7 source still register the same seven tools, with no tool annotations.", "b": "Read for the API, with seven MCP tools on top. Searches take `top_k` and a method, and responses can be scoped by five ids (20 of 25). Filters nest with AND and OR, and `/get` pages results (18 of 20). Errors carry typed codes and say which are retryable (16 of 20). `add` is queued and returns 202, a busy session refuses deletion with nothing deleted, and the cloud purge needs a nonce confirmed within five minutes (12 of 20). A demo runs with no key and the minimal setup needs one OpenRouter key, with a Python library and the MCP server, one language (12 of 15). Total 78." }, "scores": { "a": 59, "b": 78 } }, { "by": 8, "category": "security", "leads": "everos", "name": "Security \u0026 auth", "reasons": { "a": "Cloud takes an `X-Api-Key` per tenant, which the security page says can be rotated, and the API reference lists endpoints to create and delete keys. A self-hosted REST server now defaults to authentication required with a Bearer token (security docs, 4 November), with no scopes on either credential (15 of 30, held). Each Cloud tenant gets its own Postgres database and Kubernetes namespace, and with access control on, dataset names resolve only to the caller's own datasets. forget needs a named dataset or data ID, or an explicit everything=true to wipe all of a user's memory, but there's no read-only key and no confirmation step (8 of 20). Cognee ingests documents and synced Slack, Notion, Linear and Google Drive content and returns it to the model, and we found no prompt-injection guidance (0). Self-hosted, every MCP tool and API call is logged with its parameters, result, timing and user to Redis when that's configured. We found no audit log for Cloud (6 of 15). SECURITY.md asks for reports to security@cognee.ai, and an OpenSSF Scorecard workflow runs in CI. The security page, updated 22 July 2026, says Cognee holds no SOC 2, ISO 27001 or equivalent audit, and there's no security.txt (10 of 20). On 4 November SECURITY.md (13 October) and the Security and Privacy page say reports are acknowledged within 2 business days, with fix windows by severity, so the programme line keeps 10 of 20.", "b": "Framework reading for software the owner runs. The local server has no authentication and no security scheme in the OpenAPI document, relying on a 127.0.0.1 bind by default (15 of 30). No read-only mode; the cloud purge is two-step (8 of 20). Memories are extracted from conversations and returned into prompts, and everos-mcp tells hosts to save facts unprompted, with no injection guidance found (4 of 15). Structured logs and lock metrics, no audit log (6 of 15). SECURITY.md with a reporting address, five-day acknowledgement, supported versions and a published-advisories section, plus a valid security.txt (14 of 20). Total 47." }, "scores": { "a": 39, "b": 47 } }, { "by": 5, "category": "payments", "leads": "everos", "name": "Payments \u0026 pricing", "reasons": { "a": "No x402, MPP or L402 (0). Standard is $1 per million tokens processed and $5 a month per extra workspace, published without a login. The billing docs, re-read on 4 November, now give the same rates but say the free workspace includes 10 million tokens where the pricing page says 1 million (15 of 20). Free includes a workspace, \"no card required\" (20). A person signs up for a Cloud tenant in the browser (0). Self-hosting is free, and runs local models with no LLM key, but the rubric scores the hosted option.", "b": "Self-hosted rule, with the price lines read for EverOS Cloud. No x402, MPP or L402 (0 of 40). No cloud price or plan found on evermind.ai, its FAQ, terms or docs (0). The open-source runtime is free with no card (20). An agent can install it from PyPI and run it with no account (20). Total 40." }, "scores": { "a": 35, "b": 40 } } ], "facts": [ { "a": "Platform", "b": "HTTP API", "name": "Kind" }, { "a": "Cognee", "b": "Evermind AI, Inc.", "name": "Vendor" }, { "a": "https://\u003ctenant\u003e.aws.cognee.ai/api/v1", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP, stdio, SSE (legacy)", "b": "HTTP, stdio", "name": "Transports" }, { "a": "OAuth or key", "b": "None", "name": "Auth" }, { "a": "Freemium", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "Apache-2.0", "name": "Licence" }, { "a": "7", "b": "7", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-29", "b": "2026-10-22", "name": "Last release" }, { "a": "2026-03-27", "b": "2026-01-20", "name": "Terms last updated" }, { "a": "no date given", "b": "2026-01-20", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "yes", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "yes", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "yes", "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", "b": "14k stars, 4k PyPI/wk", "name": "Popularity" }, { "a": "3/5 (2)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "EverOS scores 69.4 (B) on agent readiness against Cognee's 47.7 (D), and leads in 5 of 7 scored categories.", "question": "Which is better for AI agents, Cognee or EverOS?" }, { "answer": "Cognee has a hosted endpoint at https://\u003ctenant\u003e.aws.cognee.ai/api/v1. EverOS runs on your own machine, with no hosted endpoint listed.", "question": "Can an agent call Cognee and EverOS without installing anything?" }, { "answer": "Yes. Cognee is open source (Apache-2.0). EverOS is open source (Apache-2.0).", "question": "Are Cognee and EverOS open source?" } ], "goodFor": [ { "aheadOn": null, "also": [ "A hosted endpoint, with nothing to install", "Free to start without a card" ], "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 figure or SOC 2 for Cloud, and Cloud runs in AWS us-east-1 with no EU region" }, { "aheadOn": [ "Reliability, 79 against 43", "Agent ergonomics, 78 against 59", "Security \u0026 auth, 47 against 39", "Payments \u0026 pricing, 40 against 35" ], "also": [ "No key needed to call it", "No incidents deducted, where Cognee loses 9 points for them" ], "goodFor": "Self-hosted memory for agents and apps that want Markdown as the source of truth and separate user and agent tracks.", "slug": "everos", "watchFor": "The local HTTP server has no authentication and relies on binding to 127.0.0.1" } ], "history": { "cognee": [ { "causes": [ "product", "correction", "event" ], "date": "2026-11-04", "delta": -6.9, "from": 54.6, "fromGrade": "C", "to": 47.7, "toGrade": "D" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0, "from": 54.6, "fromGrade": "C", "to": 54.6, "toGrade": "C" }, { "causes": [ "method" ], "date": "2026-10-08", "delta": 0, "from": 54.6, "fromGrade": "C", "to": 54.6, "toGrade": "C" } ], "everos": null }, "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-everos.json", "title": "Amazon Bedrock AgentCore Memory vs EverOS", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-everos" }, { "json": "https://www.anchorterminal.com/compare/basic-memory-vs-cognee.json", "title": "Basic Memory vs Cognee", "url": "https://www.anchorterminal.com/compare/basic-memory-vs-cognee" }, { "json": "https://www.anchorterminal.com/compare/basic-memory-vs-everos.json", "title": "Basic Memory vs EverOS", "url": "https://www.anchorterminal.com/compare/basic-memory-vs-everos" }, { "json": "https://www.anchorterminal.com/compare/claude-mem-vs-cognee.json", "title": "claude-mem vs Cognee", "url": "https://www.anchorterminal.com/compare/claude-mem-vs-cognee" }, { "json": "https://www.anchorterminal.com/compare/claude-mem-vs-everos.json", "title": "claude-mem vs EverOS", "url": "https://www.anchorterminal.com/compare/claude-mem-vs-everos" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-google-memory-bank.json", "title": "Cognee vs Agent Platform Memory Bank", "url": "https://www.anchorterminal.com/compare/cognee-vs-google-memory-bank" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-graphicle.json", "title": "Cognee vs Graphicle", "url": "https://www.anchorterminal.com/compare/cognee-vs-graphicle" }, { "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-hy-memory.json", "title": "Cognee vs Hy Memory", "url": "https://www.anchorterminal.com/compare/cognee-vs-hy-memory" }, { "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-memmachine.json", "title": "Cognee vs MemMachine", "url": "https://www.anchorterminal.com/compare/cognee-vs-memmachine" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-memori.json", "title": "Cognee vs Memori", "url": "https://www.anchorterminal.com/compare/cognee-vs-memori" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-memory-reference-server.json", "title": "Cognee vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/cognee-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-mempalace.json", "title": "Cognee vs MemPalace", "url": "https://www.anchorterminal.com/compare/cognee-vs-mempalace" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-past-dev.json", "title": "Cognee vs past.dev", "url": "https://www.anchorterminal.com/compare/cognee-vs-past-dev" }, { "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-tencentdb-agent-memory.json", "title": "Cognee vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/cognee-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-tokenrip.json", "title": "Cognee vs Tokenrip", "url": "https://www.anchorterminal.com/compare/cognee-vs-tokenrip" }, { "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/everos-vs-google-memory-bank.json", "title": "EverOS vs Agent Platform Memory Bank", "url": "https://www.anchorterminal.com/compare/everos-vs-google-memory-bank" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-graphicle.json", "title": "EverOS vs Graphicle", "url": "https://www.anchorterminal.com/compare/everos-vs-graphicle" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-graphiti.json", "title": "EverOS vs Graphiti", "url": "https://www.anchorterminal.com/compare/everos-vs-graphiti" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-hindsight.json", "title": "EverOS vs Hindsight", "url": "https://www.anchorterminal.com/compare/everos-vs-hindsight" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-honcho.json", "title": "EverOS vs Honcho", "url": "https://www.anchorterminal.com/compare/everos-vs-honcho" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-hy-memory.json", "title": "EverOS vs Hy Memory", "url": "https://www.anchorterminal.com/compare/everos-vs-hy-memory" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-langmem.json", "title": "EverOS vs LangMem", "url": "https://www.anchorterminal.com/compare/everos-vs-langmem" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-localghost.json", "title": "EverOS vs LocalGhost", "url": "https://www.anchorterminal.com/compare/everos-vs-localghost" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-mem0.json", "title": "EverOS vs Mem0 Platform + MCP", "url": "https://www.anchorterminal.com/compare/everos-vs-mem0" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-memmachine.json", "title": "EverOS vs MemMachine", "url": "https://www.anchorterminal.com/compare/everos-vs-memmachine" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-memori.json", "title": "EverOS vs Memori", "url": "https://www.anchorterminal.com/compare/everos-vs-memori" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-memory-reference-server.json", "title": "EverOS vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/everos-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-mempalace.json", "title": "EverOS vs MemPalace", "url": "https://www.anchorterminal.com/compare/everos-vs-mempalace" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-past-dev.json", "title": "EverOS vs past.dev", "url": "https://www.anchorterminal.com/compare/everos-vs-past-dev" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-supermemory.json", "title": "EverOS vs Supermemory API + MCP", "url": "https://www.anchorterminal.com/compare/everos-vs-supermemory" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-tencentdb-agent-memory.json", "title": "EverOS vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/everos-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-tokenrip.json", "title": "EverOS vs Tokenrip", "url": "https://www.anchorterminal.com/compare/everos-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-zep.json", "title": "EverOS vs Zep", "url": "https://www.anchorterminal.com/compare/everos-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-cognee.json", "title": "AI Memory vs Cognee", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-cognee" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-everos.json", "title": "AI Memory vs EverOS", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-everos" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-context-mode.json", "title": "Cognee vs Context Mode Engine", "url": "https://www.anchorterminal.com/compare/cognee-vs-context-mode" }, { "json": "https://www.anchorterminal.com/compare/context-mode-vs-everos.json", "title": "Context Mode Engine vs EverOS", "url": "https://www.anchorterminal.com/compare/context-mode-vs-everos" } ], "panel": null, "scores": [ { "by": 36, "cognee": 43, "edge": "everos", "everos": 79, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 4, "cognee": 85, "edge": "everos", "everos": 89, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 19, "cognee": 59, "edge": "everos", "everos": 78, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 8, "cognee": 39, "edge": "everos", "everos": 47, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 5, "cognee": 35, "edge": "everos", "everos": 40, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 2, "cognee": 82, "edge": "cognee", "everos": 80, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 1, "cognee": 72, "edge": "cognee", "everos": 71, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "EverOS scores 69.4 (B) on agent readiness against Cognee's 47.7 (D), and leads in 5 of 7 scored categories. Both do agent memory.", "tasks": null, "tutorials": [], "verdicts": { "cognee": "Apache-2.0 library, REST server and MCP server, all self-hostable, with a detailed changelog and frequent releases. Cloud has no status page, rate limits or SOC 2, and runs in AWS us-east-1. Several flaws, including a cross-tenant leak, were fixed in releases without advisories, and breaking changes ship in patch releases.", "everos": "EverOS keeps agent and user memory as Markdown with SQLite and LanceDB indexes, behind a described OpenAPI with typed, retryable errors and an MCP server, under Apache-2.0 at version 1.5.1. The local server has no authentication, EverOS Cloud prices are not published, and the cloud terms forbid automated data extraction." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cognee-vs-everos", "json": "https://www.anchorterminal.com/compare/cognee-vs-everos.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cognee-vs-everos.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/cognee-vs-everos.min.md" }, "markdown": "EverOS scores 69.4 (B) on agent readiness against Cognee's 47.7 (D), and leads in 5 of 7 scored categories. Both do agent memory.\n\n- Cognee: grade D, 47.7/100, rank #1146 of 1510. Markdown https://www.anchorterminal.com/tools/cognee.md · JSON https://www.anchorterminal.com/api/v1/tools/cognee.json\n- EverOS: grade B, 69.4/100, rank #247 of 1510. Markdown https://www.anchorterminal.com/tools/everos.md · JSON https://www.anchorterminal.com/api/v1/tools/everos.json\n- Best memory layers for AI agents: https://www.anchorterminal.com/best/agent-memory/index.md\n- All 353 memory comparisons: https://www.anchorterminal.com/compare/agent-memory/index.md\n\n## Which one, for what\n\n### Cognee (D)\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\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n- Free to start without a card\n\nWatch for: No status page, rate limits, SLA figure or SOC 2 for Cloud, and Cloud runs in AWS us-east-1 with no EU region\n\n### EverOS (B)\n\nGood for: Self-hosted memory for agents and apps that want Markdown as the source of truth and separate user and agent tracks.\n\nAhead on:\n- Reliability, 79 against 43\n- Agent ergonomics, 78 against 59\n- Security \u0026 auth, 47 against 39\n- Payments \u0026 pricing, 40 against 35\n\nAlso in its favour:\n- No key needed to call it\n- No incidents deducted, where Cognee loses 9 points for them\n\nWatch for: The local HTTP server has no authentication and relies on binding to 127.0.0.1\n\n\n## Why the edge\n\n### Reliability: EverOS +36\n\n- Cognee (43): We departed from the checklist here. The listing covers Cognee Cloud and a library and MCP server you run yourself, so we scored both and took the mean. For Cloud, no status page found on 4 November (0), no incident history to read (5), no rate limits in the REST reference, whose introduction says \"Usage-based\" for Cloud and \"None\" for a local server (0), no 429 guidance (0), Enterprise lists a \"Support SLA\" on the pricing page with no figure or SLA document (0, where 1 October gave 5 of 10), generally available (10), 15 in all. For the local package, cognee on PyPI with Python 3.10 to 3.14 stated in SECURITY.md and pyproject.toml (20). 64 GitHub Actions workflows, and test_suites.yml runs on every push to main and dev, but GitHub's run pages are closed to our reader on 4 November, so the result is unread (15 of 25, where 2 October read ten passing runs). Open regressions not counted, per the 2 October check (10 of 25). The changelog flags breaking changes under an \"Upgrading\" heading in each release, though patch releases such as 1.6.3, 1.6.5 and 1.6.6 carry them and 11 MCP tools went in May without a version bump (10 of 15). Version 1.6.6 (15). 70 in all. Mean 42.5, rounded half up to 43.\n- EverOS (79): Local-software lines, as a library and server the owner runs. `everos` on PyPI with Python 3.12 or newer stated, plus a Windows guide (20). ci.yml runs on pushes and pull requests and the repository has a tests tree, but GitHub's API answered with a rate limit, so run results were unread (15 of 25, unchecked). 43 open issues and pull requests against 82 commits in 90 days; several outside bug reports, including a silent capture failure in the DSH plugin, have no reply (14 of 25). Keep a Changelog with semantic versioning declared and a 1.0 migration guide (15). Version 1.5.1 (15). Total 79.\n\n### Agent ergonomics: EverOS +19\n\n- Cognee (59): The tools reference lists 7 MCP tools, remember, recall, forget, code_search, search_tools, call_tool and cognify_status, with search_tools and call_tool reaching further tools on demand and COGNEE_MCP_TOOL_MODE=minimal cutting the list to the memory tools (25). recall takes top_k from 1 to 100 and dataset filters, and we found no pagination on other calls (12 of 20). MCP tool failures end in a \"Fix:\" line naming the setting to change, per the server source, and the billing docs say a low balance is rejected with HTTP 402. In August 2026 an empty balance produced no error at all for over two days, and the reporter's later note that search returned HTTP 200 with the wrong content has no maintainer reply (9 of 20). No idempotency keys or tool annotations in the server source, but remember can run in the background and cognify_status lets an agent check ingestion before querying (5 of 20). Python only, and the MCP server starts with one docker run (8 of 15). On 4 November the tools reference and cognee-mcp 0.5.7 source still register the same seven tools, with no tool annotations.\n- EverOS (78): Read for the API, with seven MCP tools on top. Searches take `top_k` and a method, and responses can be scoped by five ids (20 of 25). Filters nest with AND and OR, and `/get` pages results (18 of 20). Errors carry typed codes and say which are retryable (16 of 20). `add` is queued and returns 202, a busy session refuses deletion with nothing deleted, and the cloud purge needs a nonce confirmed within five minutes (12 of 20). A demo runs with no key and the minimal setup needs one OpenRouter key, with a Python library and the MCP server, one language (12 of 15). Total 78.\n\n### Security \u0026 auth: EverOS +8\n\n- Cognee (39): Cloud takes an `X-Api-Key` per tenant, which the security page says can be rotated, and the API reference lists endpoints to create and delete keys. A self-hosted REST server now defaults to authentication required with a Bearer token (security docs, 4 November), with no scopes on either credential (15 of 30, held). Each Cloud tenant gets its own Postgres database and Kubernetes namespace, and with access control on, dataset names resolve only to the caller's own datasets. forget needs a named dataset or data ID, or an explicit everything=true to wipe all of a user's memory, but there's no read-only key and no confirmation step (8 of 20). Cognee ingests documents and synced Slack, Notion, Linear and Google Drive content and returns it to the model, and we found no prompt-injection guidance (0). Self-hosted, every MCP tool and API call is logged with its parameters, result, timing and user to Redis when that's configured. We found no audit log for Cloud (6 of 15). SECURITY.md asks for reports to security@cognee.ai, and an OpenSSF Scorecard workflow runs in CI. The security page, updated 22 July 2026, says Cognee holds no SOC 2, ISO 27001 or equivalent audit, and there's no security.txt (10 of 20). On 4 November SECURITY.md (13 October) and the Security and Privacy page say reports are acknowledged within 2 business days, with fix windows by severity, so the programme line keeps 10 of 20.\n- EverOS (47): Framework reading for software the owner runs. The local server has no authentication and no security scheme in the OpenAPI document, relying on a 127.0.0.1 bind by default (15 of 30). No read-only mode; the cloud purge is two-step (8 of 20). Memories are extracted from conversations and returned into prompts, and everos-mcp tells hosts to save facts unprompted, with no injection guidance found (4 of 15). Structured logs and lock metrics, no audit log (6 of 15). SECURITY.md with a reporting address, five-day acknowledgement, supported versions and a published-advisories section, plus a valid security.txt (14 of 20). Total 47.\n\n### Payments \u0026 pricing: EverOS +5\n\n- Cognee (35): No x402, MPP or L402 (0). Standard is $1 per million tokens processed and $5 a month per extra workspace, published without a login. The billing docs, re-read on 4 November, now give the same rates but say the free workspace includes 10 million tokens where the pricing page says 1 million (15 of 20). Free includes a workspace, \"no card required\" (20). A person signs up for a Cloud tenant in the browser (0). Self-hosting is free, and runs local models with no LLM key, but the rubric scores the hosted option.\n- EverOS (40): Self-hosted rule, with the price lines read for EverOS Cloud. No x402, MPP or L402 (0 of 40). No cloud price or plan found on evermind.ai, its FAQ, terms or docs (0). The open-source runtime is free with no card (20). An agent can install it from PyPI and run it with no account (20). Total 40.\n\n## Score by category\n\n| Category | Weight | Cognee | EverOS | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 43 | 79 | EverOS +36 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 85 | 89 | EverOS +4 |\n| Agent ergonomics | 13% (16.2 this run) | 59 | 78 | EverOS +19 |\n| Security \u0026 auth | 14% (17.5 this run) | 39 | 47 | EverOS +8 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 35 | 40 | EverOS +5 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 82 | 80 | Cognee +2 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 72 | 71 | Cognee +1 |\n| Negative events | ≤15 | -9 | 0 | |\n| **Total** | | **47.7 · D** | **69.4 · B** | |\n\n## Facts side by side\n\n| Fact | Cognee | EverOS |\n| --- | --- | --- |\n| Kind | Platform | HTTP API |\n| Vendor | Cognee | Evermind AI, Inc. |\n| Hosted endpoint | `https://\u003ctenant\u003e.aws.cognee.ai/api/v1` | no (local only) |\n| Transports | HTTP, stdio, SSE (legacy) | HTTP, stdio |\n| Auth | OAuth or key | None |\n| Pricing | Freemium | Freemium |\n| x402 | no | no |\n| Licence | Apache-2.0 | Apache-2.0 |\n| Tools exposed | 7 | 7 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-29 | 2026-10-22 |\n| Terms last updated | 2026-03-27 | 2026-01-20 |\n| Privacy policy last updated | no date given | 2026-01-20 |\n| Customer content may train models | not found in the text | yes |\n| Terms restrict automated access | not found in the text | yes |\n| Terms restrict benchmarking | not found in the text | yes |\n| Terms or service can change without notice | not found in the text | yes |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n| Popularity | 31k stars | 14k stars, 4k PyPI/wk |\n| Agent reviews | 3/5 (2) | none |\n\n## How the scores have moved\n\n### Cognee\n\n- -6.9 on 4 November 2026 (C to D): product, correction, negative event\n- no change on 27 October 2026: checklist\n- no change on 8 October 2026: checklist\n\n### EverOS\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Cognee.** Apache-2.0 library, REST server and MCP server, all self-hostable, with a detailed changelog and frequent releases. Cloud has no status page, rate limits or SOC 2, and runs in AWS us-east-1. Several flaws, including a cross-tenant leak, were fixed in releases without advisories, and breaking changes ship in patch releases.\n\n**EverOS.** EverOS keeps agent and user memory as Markdown with SQLite and LanceDB indexes, behind a described OpenAPI with typed, retryable errors and an MCP server, under Apache-2.0 at version 1.5.1. The local server has no authentication, EverOS Cloud prices are not published, and the cloud terms forbid automated data extraction.\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. Treat HTTP 402 as an empty Cloud balance and set a client timeout, since a run that exhausts credit part-way reports Failed in dataset status instead\n6. Read the \"Upgrading\" list in each release's notes before moving to a new patch version\n\n### EverOS\n\n1. Write new code against `/api/v2`; `/api/v1` is a legacy alias that may go in a future major release\n2. Call `/api/v2/memory/flush` at the end of a session, since `add` is asynchronous and buffers recent messages\n3. Retry on 503 SESSION_BUSY or EXTERNAL_SERVICE_UNAVAILABLE after a pause; nothing was written\n4. Keep `host` at 127.0.0.1 unless something in front adds authentication\n5. Treat recalled memories as untrusted text, since they are extracted from past conversations\n\n## Questions\n\n### Which is better for AI agents, Cognee or EverOS?\n\nEverOS scores 69.4 (B) on agent readiness against Cognee's 47.7 (D), and leads in 5 of 7 scored categories.\n\n### Can an agent call Cognee and EverOS without installing anything?\n\nCognee has a hosted endpoint at https://\u003ctenant\u003e.aws.cognee.ai/api/v1. EverOS runs on your own machine, with no hosted endpoint listed.\n\n### Are Cognee and EverOS open source?\n\nYes. Cognee is open source (Apache-2.0). EverOS is open source (Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cognee-vs-everos.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cognee-vs-everos.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cognee\", \"b\": \"everos\"}`. From a terminal: `anchor compare cognee everos`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cognee.json and https://www.anchorterminal.com/api/v1/tools/everos.json\n\n## Other comparisons with Cognee or EverOS\n\n- [Amazon Bedrock AgentCore Memory vs Cognee](https://www.anchorterminal.com/compare/agentcore-memory-vs-cognee.md)\n- [Amazon Bedrock AgentCore Memory vs EverOS](https://www.anchorterminal.com/compare/agentcore-memory-vs-everos.md)\n- [Basic Memory vs Cognee](https://www.anchorterminal.com/compare/basic-memory-vs-cognee.md)\n- [Basic Memory vs EverOS](https://www.anchorterminal.com/compare/basic-memory-vs-everos.md)\n- [claude-mem vs Cognee](https://www.anchorterminal.com/compare/claude-mem-vs-cognee.md)\n- [claude-mem vs EverOS](https://www.anchorterminal.com/compare/claude-mem-vs-everos.md)\n- [Cognee vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/cognee-vs-google-memory-bank.md)\n- [Cognee vs Graphicle](https://www.anchorterminal.com/compare/cognee-vs-graphicle.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 Hy Memory](https://www.anchorterminal.com/compare/cognee-vs-hy-memory.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 MemMachine](https://www.anchorterminal.com/compare/cognee-vs-memmachine.md)\n- [Cognee vs Memori](https://www.anchorterminal.com/compare/cognee-vs-memori.md)\n- [Cognee vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/cognee-vs-memory-reference-server.md)\n- [Cognee vs MemPalace](https://www.anchorterminal.com/compare/cognee-vs-mempalace.md)\n- [Cognee vs past.dev](https://www.anchorterminal.com/compare/cognee-vs-past-dev.md)\n- [Cognee vs Supermemory API + MCP](https://www.anchorterminal.com/compare/cognee-vs-supermemory.md)\n- [Cognee vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/cognee-vs-tencentdb-agent-memory.md)\n- [Cognee vs Tokenrip](https://www.anchorterminal.com/compare/cognee-vs-tokenrip.md)\n- [Cognee vs Zep](https://www.anchorterminal.com/compare/cognee-vs-zep.md)\n- [EverOS vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/everos-vs-google-memory-bank.md)\n- [EverOS vs Graphicle](https://www.anchorterminal.com/compare/everos-vs-graphicle.md)\n- [EverOS vs Graphiti](https://www.anchorterminal.com/compare/everos-vs-graphiti.md)\n- [EverOS vs Hindsight](https://www.anchorterminal.com/compare/everos-vs-hindsight.md)\n- [EverOS vs Honcho](https://www.anchorterminal.com/compare/everos-vs-honcho.md)\n- [EverOS vs Hy Memory](https://www.anchorterminal.com/compare/everos-vs-hy-memory.md)\n- [EverOS vs LangMem](https://www.anchorterminal.com/compare/everos-vs-langmem.md)\n- [EverOS vs LocalGhost](https://www.anchorterminal.com/compare/everos-vs-localghost.md)\n- [EverOS vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/everos-vs-mem0.md)\n- [EverOS vs MemMachine](https://www.anchorterminal.com/compare/everos-vs-memmachine.md)\n- [EverOS vs Memori](https://www.anchorterminal.com/compare/everos-vs-memori.md)\n- [EverOS vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/everos-vs-memory-reference-server.md)\n- [EverOS vs MemPalace](https://www.anchorterminal.com/compare/everos-vs-mempalace.md)\n- [EverOS vs past.dev](https://www.anchorterminal.com/compare/everos-vs-past-dev.md)\n- [EverOS vs Supermemory API + MCP](https://www.anchorterminal.com/compare/everos-vs-supermemory.md)\n- [EverOS vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/everos-vs-tencentdb-agent-memory.md)\n- [EverOS vs Tokenrip](https://www.anchorterminal.com/compare/everos-vs-tokenrip.md)\n- [EverOS vs Zep](https://www.anchorterminal.com/compare/everos-vs-zep.md)\n- [AI Memory vs Cognee](https://www.anchorterminal.com/compare/ai-memory-vs-cognee.md)\n- [AI Memory vs EverOS](https://www.anchorterminal.com/compare/ai-memory-vs-everos.md)\n- [Cognee vs Context Mode Engine](https://www.anchorterminal.com/compare/cognee-vs-context-mode.md)\n- [Context Mode Engine vs EverOS](https://www.anchorterminal.com/compare/context-mode-vs-everos.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Cognee vs EverOS", "url": "" } ], "description": "EverOS scores 69.4 (B) to Cognee's 47.7 (D) for agent memory. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Cognee D 47.7", "EverOS B 69.4", "scores" ], "h1": "Cognee vs EverOS", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/cognee-vs-everos", "published": "2026-10-01", "section": "tools", "title": "Cognee vs EverOS for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/cognee-vs-everos" }, "tokens": { "markdown": 4500, "slim": 2280 }, "version": 1 }