{ "data": { "a": { "slug": "agno", "name": "Agno", "vendor": "Agno Inc.", "vendorUrl": "https://www.agno.com", "kind": "framework", "category": "frameworks", "summary": "Open-source Python framework from Agno Inc. for building agents, teams and workflows, with the AgentOS runtime that serves them over a REST API and an MCP server. Formerly Phidata.", "url": "https://www.anchorterminal.com/tools/agno", "markdownUrl": "https://www.anchorterminal.com/tools/agno.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/agno.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/agno.json", "repo": "https://github.com/agno-agi/agno", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "pypi", "name": "agno" } ], "auth": "api-key", "authNotes": "The framework has no account of its own. Each model provider takes its own key from the environment. AgentOS, the server you run, accepts JWTs, a shared OS_SECURITY_KEY or service-account tokens, and takes no credential when none is configured. The hosted control plane at os.agno.com needs a sign-in.", "pricing": "free", "pricingNotes": "The SDK and AgentOS are free under Apache 2.0, and you pay your model provider. The optional hosted control plane is free for a local AgentOS and $150 a month (Pro) for a live deployment, with Enterprise by quote (https://www.agno.com/pricing, checked 2026-10-08).", "priceSummary": "Free · OSS", "where": "library", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the library source or on the pricing page. The only match in the repository is a cookbook example that calls a third-party x402 MCP server (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 42612, "npmWeekly": null, "pypiWeekly": 475559, "asOf": "2026-10-08" }, "docsUrl": "https://docs.agno.com", "llmsTxt": "https://docs.agno.com/llms.txt", "capabilities": [ "agent.framework", "agent.multi-agent", "agent.durable", "agent.mcp-client" ], "tags": [ "framework", "python", "open-source", "llms-txt", "mcp", "otel", "free" ], "lastRelease": "2026-10-02", "graded": true, "anchor": { "graded": true, "score": 72.8, "grade": "BB", "agentReady": true, "rank": 85, "ranked": true, "rankOf": 722, "categoryRank": 7, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 76, "maintenance": 86, "payments": 50, "reliability": 83, "schema": 90, "security": 64, "transparency": 83 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": -3, "negativeNotes": [ "2026-06-30. GHSA-m4w4-3r8h-jw98 (CVE-2026-35002, critical), arbitrary code execution through eval() on field_type in a FunctionCall, fixed in 2.3.24. GHSA-w9j5-7p53-pvr3 (CVE-2026-10105, high, published 2026-07-27), SQL injection in the ClickHouse vector store's delete_by_metadata, parameterised in the current source. GHSA-vw84-hprm-cxmm (CVE-2025-64168, high, 2025-10-31), session state written to the wrong session under concurrency, fixed in 2.2.2. All three are fixed and published as advisories in the repository, so 1 point each. https://github.com/agno-agi/agno/security/advisories" ], "verdict": "An Apache 2.0 Python agent framework at 3.1.1 with an MCP client, tool confirmation and admin approvals, a durable job queue and 25 stable releases in 90 days. Usage telemetry is on by default with unhashed identifiers, and three high or critical advisories were published against it in the last 12 months, all fixed.", "bestFor": "Python teams that want agents, teams and workflows plus a self-hosted server with REST, MCP, approvals and scheduling in one package.", "strengths": [ "Apache 2.0, with 25 stable releases on PyPI in the 90 days to 8 October 2026 and 3.1.1 on 2 October", "MCP client (MCPTools) over Streamable HTTP and stdio with include_tools, exclude_tools and a name prefix", "Tool calls can require confirmation, user input or an admin approval that is stored and audited", "llms.txt, llms-full.txt, a Markdown twin of every docs page and a docs MCP server at docs.agno.com/mcp", "Unit tests, Ruff and mypy run in public CI, and 10 of the 12 latest runs on main passed with 2 cancelled" ], "weaknesses": [ "Usage telemetry is on by default and sends session, run and agent identifiers unhashed. Prompts and outputs are not sent", "AGNO_TELEMETRY=false does not cover AgentOS launches or evals, which need telemetry=False on the instance", "Three advisories in 12 months, an eval injection rated critical, a ClickHouse SQL injection and a session state leak, all fixed", "867 open issues and 968 open pull requests on 8 October 2026, with 287 issues opened and 105 closed in 30 days", "AgentOS requires no credential unless a JWT key or OS_SECURITY_KEY is configured", "Terms and privacy pages at os.agno.com render only with JavaScript and could not be read" ], "agentNotes": [ "Set AGNO_TELEMETRY=false before the first run, and pass telemetry=False to AgentOS and to each eval, which ignore the variable", "Configure JWT_VERIFICATION_KEY with AgentOS authorisation switched on, or OS_SECURITY_KEY, before exposing AgentOS. With neither set, REST and MCP routes take no credential", "Mark tools that write with requires_confirmation, and resume with continue_run once every requirement is resolved", "Set tool_call_limit on agents. The default is None", "Install extras for what you use, such as agno[mcp] for MCPTools and agno[os,mcp] for AgentOS with its MCP server" ], "metrics": { "kind": "library", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 72.8 } ], "editorialScores": { "ergonomics": 76, "maintenance": 86, "payments": 50, "reliability": 83, "schema": 90, "security": 64, "transparency": 73 }, "provenanceScore": 93 }, "connect": { "install": "pip install -U agno # MCP client: pip install -U \"agno[mcp]\"" }, "letme": { "capability": "https://letme.dev/agent.framework", "tool": "https://letme.dev/agno" }, "area": "frameworks", "unitPrices": [ { "item": "Control plane Pro plan, one live AgentOS connection and three seats", "unit": "month", "usd": 150 } ], "provenance": { "legalEntity": "Agno Inc.", "domain": "agno.com", "domainRegistered": "2003-04-13", "endpointOnVendorDomain": null, "terms": "https://os.agno.com/legal/tos", "privacy": "https://os.agno.com/legal/privacy", "statusPage": "https://status.agno.com", "changelog": "https://www.agno.com/changelog", "securityTxt": "valid", "checked": "2026-10-08", "notes": [ "The licence file reads Copyright 2025-2026 Agno Inc. and the site footer reads © 2026 Agno Inc.", "www.agno.com/.well-known/security.txt gives https://github.com/agno-agi/agno/security as the contact and expires 2027-08-10.", "The terms and privacy links in the www.agno.com footer go to os.agno.com/legal/tos and /legal/privacy. Both return 200 but render only with JavaScript, so their text was not read. They cover the hosted control plane. The SDK itself is under Apache 2.0.", "status.agno.com lists Website and AgentOS components, which are the vendor's hosted services, not the library.", "RDAP gives agno.com a registration date of 2003-04-13. github.com/phidatahq/phidata redirects to agno-agi/agno." ], "score": 93 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/agno.json", "live": { "slug": "agno", "vendorStatus": { "page": "https://status.agno.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-08T20:22:18.672615698Z" }, "pages": [ { "url": "https://www.agno.com/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-10-08T18:26:00.846605424Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "9f1b3a47f34c" }, { "url": "https://www.agno.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-08T18:26:03.20718868Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "39cf0ea4a9f3" }, { "url": "https://os.agno.com/legal/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-08T18:22:43.657502021Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e3b0c44298fc" }, { "url": "https://os.agno.com/legal/tos", "kind": "terms", "status": 200, "checkedAt": "2026-10-08T18:22:45.687556777Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e3b0c44298fc" } ], "updatedAt": "2026-10-08T20:22:18.672615698Z" } }, "answer": "Agno scores 72.8 (BB) on agent readiness against CrewAI's 67 (B), and leads in 4 of 7 scored categories.", "b": { "slug": "crewai", "name": "CrewAI", "vendor": "CrewAI", "vendorUrl": "https://www.crewai.com", "kind": "framework", "category": "frameworks", "summary": "Python framework for teams of role-playing agents in Crews, plus event-driven Flows for stateful workflows.", "url": "https://www.anchorterminal.com/tools/crewai", "markdownUrl": "https://www.anchorterminal.com/tools/crewai.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/crewai.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/crewai.json", "repo": "https://github.com/crewAIInc/crewAI", "license": "MIT", "transports": [], "packages": [ { "registry": "pypi", "name": "crewai" } ], "auth": "none", "authNotes": "A library. Credentials are for the models and tools you use.", "pricing": "free", "pricingNotes": "Free and open source. You pay for the model calls it makes. CrewAI AMP hosting has a free tier of 50 executions a month. Enterprise is priced by sales.", "priceSummary": "Free · OSS", "where": "library", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 59059, "npmWeekly": null, "pypiWeekly": 552409, "asOf": "2026-09-26" }, "docsUrl": "https://docs.crewai.com", "llmsTxt": "https://docs.crewai.com/llms.txt", "capabilities": [ "agent.framework", "agent.multi-agent", "agent.durable", "agent.mcp-client" ], "tags": [ "framework", "python", "open-source", "telemetry-default-on" ], "lastRelease": "2026-09-28", "graded": true, "anchor": { "graded": true, "score": 67, "grade": "B", "agentReady": false, "rank": 220, "ranked": true, "rankOf": 722, "categoryRank": 10, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 80, "maintenance": 88, "payments": 40, "reliability": 78, "schema": 74, "security": 65, "transparency": 72 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": -4, "negativeNotes": [ "2026-03-30. CERT/CC VU#221883 published four CVEs in CrewAI 1.0, remote code execution when the code interpreter fell back from Docker to its Python sandbox (CVE-2026-2275, 9.6, and CVE-2026-2287, 9.8), SSRF in the RAG search tools (CVE-2026-2286, 9.8) and local file read in the JSON loader tool (CVE-2026-2285, 7.5). CrewAI says all are fixed in current releases, removed CodeInterpreterTool and added URL and path validation across 20+ tools. Fixed and documented and six months old, so 1 point each. CVE-2026-37008 (published 2026-09-13, 8.1) describes a ctypes bypass of the same Python sandbox, and we didn't count it twice. https://www.kb.cert.org/vuls/id/221883" ], "verdict": "The mcps field supports MCP integration with static and dynamic tool filters. Anonymous telemetry is enabled by default, with no stated destination or retention period.", "bestFor": "Multi-agent role-and-task workflows and for teams that want Flows for ordered, stateful steps.", "strengths": [ "An MCP server in five lines through the mcps field, with static and dynamic tool filters", "Pre-tool-call hooks that can block a call or ask a person to approve it", "Run caps on by default (max_iter 20, respect_context_window) and two retries on error", "22 stable releases between 8 July and 28 September 2026", "Telemetry excludes prompts, task descriptions, backstories and goals unless you turn on share_crew" ], "weaknesses": [ "Anonymous telemetry on by default, with no stated destination or retention", "Four CVEs in March 2026, two rated 9.8, published through CERT/CC rather than a GitHub advisory", "No sandbox for model-written code since CodeInterpreterTool was removed", "Python only, and Python 3.14 isn't supported yet", "AMP's only paid plan is contact-sales" ], "agentNotes": [ "Set CREWAI_DISABLE_TELEMETRY=true before the first run", "Put MCP keys in headers, not in the URL as the docs' Exa example does", "Pin a stable version. Development builds share the crewai name on PyPI", "Add a PRE_TOOL_CALL hook for any tool that writes or sends", "Check the logs for MCP connection warnings. A failed server doesn't stop the agent" ], "metrics": { "kind": "library", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 67 } ], "editorialScores": { "ergonomics": 80, "maintenance": 88, "payments": 40, "reliability": 78, "schema": 74, "security": 65, "transparency": 75 }, "provenanceScore": 68 }, "connect": { "install": "pip install crewai" }, "letme": { "capability": "https://letme.dev/agent.framework", "tool": "https://letme.dev/crewai" }, "area": "frameworks", "provenance": { "legalEntity": "crewAI, Inc.", "domain": "crewai.com", "domainRegistered": "2017-07-25", "domainNote": "crewai.com was registered in 2017, before CrewAI existed.", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://docs.crewai.com/en/changelog", "securityTxt": "none", "checked": "2026-09-26", "score": 68 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/crewai.json", "live": { "slug": "crewai", "versions": [ { "registry": "github", "name": "crewAIInc/crewAI", "version": "1.15.25", "released": "2026-10-07", "seenAt": "2026-10-08T16:07:15.651339519Z" }, { "registry": "pypi", "name": "crewai", "version": "1.15.25", "released": "2026-10-07", "seenAt": "2026-10-08T16:07:15.531727734Z" } ], "githubStars": 59463, "pypiWeekly": 598619, "securityTxt": { "url": "https://crewai.com/.well-known/security.txt", "state": "valid", "expires": "2027-05-27T23:59:59.000Z", "checkedAt": "2026-10-08T15:38:45.856537044Z" }, "llmsTxt": { "url": "https://docs.crewai.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-08T14:00:18.899337999Z" }, "domain": { "domain": "crewai.com", "registered": "2017-07-25", "source": "https://rdap.verisign.com/com/v1/domain/crewai.com", "checkedAt": "2026-10-04T13:06:28.959473977Z" }, "pages": [ { "url": "https://docs.crewai.com/en/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-10-08T18:18:33.358231432Z", "changedAt": "2026-10-08T18:18:33.358231432Z", "fingerprint": "095418fe4cc2" } ], "updatedAt": "2026-10-08T18:18:33.358231432Z" } }, "facts": [ { "a": "Agent framework", "b": "Agent framework", "name": "Kind" }, { "a": "Agno Inc.", "b": "CrewAI", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "API key", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-02", "b": "2026-09-28", "name": "Last release" }, { "a": "couldn't be read", "b": "no document linked", "name": "Terms last updated" }, { "a": "couldn't be read", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "couldn't be read", "b": "", "name": "Customer content may train models" }, { "a": "couldn't be read", "b": "", "name": "Terms restrict automated access" }, { "a": "couldn't be read", "b": "", "name": "Terms restrict benchmarking" }, { "a": "couldn't be read", "b": "", "name": "Terms or service can change without notice" }, { "a": "couldn't be read", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "43k stars, 476k PyPI/wk", "b": "59k stars, 552k PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "3/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Agno scores 72.8 (BB) on agent readiness against CrewAI's 67 (B), and leads in 4 of 7 scored categories.", "question": "Which is better for AI agents, Agno or CrewAI?" }, { "answer": "Yes. Agno is open source (Apache-2.0). CrewAI is open source (MIT).", "question": "Are Agno and CrewAI open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 83 against 78", "Schema \u0026 documentation, 90 against 74", "Payments \u0026 pricing, 50 against 40", "Transparency \u0026 trust, 83 against 72" ], "also": [ "Agent-ready, a grade of BB or better" ], "goodFor": "Python teams that want agents, teams and workflows plus a self-hosted server with REST, MCP, approvals and scheduling in one package.", "slug": "agno", "watchFor": "Usage telemetry is on by default and sends session, run and agent identifiers unhashed. Prompts and outputs are not sent" }, { "aheadOn": null, "also": [ "No key needed to call it" ], "goodFor": "Multi-agent role-and-task workflows and for teams that want Flows for ordered, stateful steps.", "slug": "crewai", "watchFor": "Anonymous telemetry on by default, with no stated destination or retention" } ], "job": { "capability": "agent.framework", "name": "Agent frameworks" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentos-vs-agno.json", "title": "AgentOS vs Agno", "url": "https://www.anchorterminal.com/compare/agentos-vs-agno" }, { "json": "https://www.anchorterminal.com/compare/agentos-vs-crewai.json", "title": "AgentOS vs CrewAI", "url": "https://www.anchorterminal.com/compare/agentos-vs-crewai" }, { "json": "https://www.anchorterminal.com/compare/agno-vs-claude-agent-sdk.json", "title": "Agno vs Claude Agent SDK", "url": "https://www.anchorterminal.com/compare/agno-vs-claude-agent-sdk" }, { "json": "https://www.anchorterminal.com/compare/agno-vs-docker-agent.json", "title": "Agno vs Docker Agent", "url": "https://www.anchorterminal.com/compare/agno-vs-docker-agent" }, { "json": "https://www.anchorterminal.com/compare/agno-vs-google-adk.json", "title": "Agno vs Agent Development Kit (ADK)", "url": "https://www.anchorterminal.com/compare/agno-vs-google-adk" }, { "json": "https://www.anchorterminal.com/compare/agno-vs-langgraph.json", "title": "Agno vs LangGraph", "url": "https://www.anchorterminal.com/compare/agno-vs-langgraph" }, { "json": "https://www.anchorterminal.com/compare/agno-vs-microsoft-agent-framework.json", "title": "Agno vs Microsoft Agent Framework", "url": "https://www.anchorterminal.com/compare/agno-vs-microsoft-agent-framework" }, { "json": "https://www.anchorterminal.com/compare/agno-vs-openai-agents-sdk.json", "title": "Agno vs OpenAI Agents SDK", "url": "https://www.anchorterminal.com/compare/agno-vs-openai-agents-sdk" }, { "json": "https://www.anchorterminal.com/compare/agno-vs-pydantic-ai.json", "title": "Agno vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/agno-vs-pydantic-ai" }, { "json": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-crewai.json", "title": "Claude Agent SDK vs CrewAI", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-crewai" }, { "json": "https://www.anchorterminal.com/compare/crewai-vs-docker-agent.json", "title": "CrewAI vs Docker Agent", "url": "https://www.anchorterminal.com/compare/crewai-vs-docker-agent" }, { "json": "https://www.anchorterminal.com/compare/crewai-vs-google-adk.json", "title": "CrewAI vs Agent Development Kit (ADK)", "url": "https://www.anchorterminal.com/compare/crewai-vs-google-adk" }, { "json": "https://www.anchorterminal.com/compare/crewai-vs-langgraph.json", "title": "CrewAI vs LangGraph", "url": "https://www.anchorterminal.com/compare/crewai-vs-langgraph" }, { "json": "https://www.anchorterminal.com/compare/crewai-vs-microsoft-agent-framework.json", "title": "CrewAI vs Microsoft Agent Framework", "url": "https://www.anchorterminal.com/compare/crewai-vs-microsoft-agent-framework" }, { "json": "https://www.anchorterminal.com/compare/crewai-vs-openai-agents-sdk.json", "title": "CrewAI vs OpenAI Agents SDK", "url": "https://www.anchorterminal.com/compare/crewai-vs-openai-agents-sdk" }, { "json": "https://www.anchorterminal.com/compare/crewai-vs-pydantic-ai.json", "title": "CrewAI vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/crewai-vs-pydantic-ai" } ], "scores": [ { "agno": 83, "by": 5, "crewai": 78, "edge": "agno", "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "agno": 90, "by": 16, "crewai": 74, "edge": "agno", "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "agno": 76, "by": 4, "crewai": 80, "edge": "crewai", "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "agno": 64, "by": 1, "crewai": 65, "edge": "crewai", "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "agno": 50, "by": 10, "crewai": 40, "edge": "agno", "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "agno": 86, "by": 2, "crewai": 88, "edge": "crewai", "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "agno": 83, "by": 11, "crewai": 72, "edge": "agno", "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Agno scores 72.8 (BB) on agent readiness against CrewAI's 67 (B), and leads in 4 of 7 scored categories. Both do agent frameworks.", "verdicts": { "agno": "An Apache 2.0 Python agent framework at 3.1.1 with an MCP client, tool confirmation and admin approvals, a durable job queue and 25 stable releases in 90 days. Usage telemetry is on by default with unhashed identifiers, and three high or critical advisories were published against it in the last 12 months, all fixed.", "crewai": "The mcps field supports MCP integration with static and dynamic tool filters. Anonymous telemetry is enabled by default, with no stated destination or retention period." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/agno-vs-crewai", "json": "https://www.anchorterminal.com/compare/agno-vs-crewai.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/agno-vs-crewai.md", "slim": "https://www.anchorterminal.com/compare/agno-vs-crewai.min.md" }, "markdown": "Agno scores 72.8 (BB) on agent readiness against CrewAI's 67 (B), and leads in 4 of 7 scored categories. Both do agent frameworks.\n\n- Agno: grade BB, 72.8/100, rank #85 of 722. Markdown https://www.anchorterminal.com/tools/agno.md · JSON https://www.anchorterminal.com/api/v1/tools/agno.json\n- CrewAI: grade B, 67/100, rank #220 of 722. Markdown https://www.anchorterminal.com/tools/crewai.md · JSON https://www.anchorterminal.com/api/v1/tools/crewai.json\n\n## Which one, for what\n\n### Agno (BB)\n\nGood for: Python teams that want agents, teams and workflows plus a self-hosted server with REST, MCP, approvals and scheduling in one package.\n\nAhead on:\n- Reliability, 83 against 78\n- Schema \u0026 documentation, 90 against 74\n- Payments \u0026 pricing, 50 against 40\n- Transparency \u0026 trust, 83 against 72\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n\nWatch for: Usage telemetry is on by default and sends session, run and agent identifiers unhashed. Prompts and outputs are not sent\n\n### CrewAI (B)\n\nGood for: Multi-agent role-and-task workflows and for teams that want Flows for ordered, stateful steps.\n\nAlso in its favour:\n- No key needed to call it\n\nWatch for: Anonymous telemetry on by default, with no stated destination or retention\n\n\n## Score by category\n\n| Category | Weight | Agno | CrewAI | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 83 | 78 | Agno +5 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 90 | 74 | Agno +16 |\n| Agent ergonomics | 13% (16.2 this run) | 76 | 80 | CrewAI +4 |\n| Security \u0026 auth | 14% (17.5 this run) | 64 | 65 | CrewAI +1 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 50 | 40 | Agno +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 86 | 88 | CrewAI +2 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 83 | 72 | Agno +11 |\n| Negative events | ≤15 | -3 | -4 | |\n| **Total** | | **72.8 · BB** | **67 · B** | |\n\n## Facts side by side\n\n| Fact | Agno | CrewAI |\n| --- | --- | --- |\n| Kind | Agent framework | Agent framework |\n| Vendor | Agno Inc. | CrewAI |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | API key | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 | MIT |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-02 | 2026-09-28 |\n| Terms last updated | couldn't be read | no document linked |\n| Privacy policy last updated | couldn't be read | no document linked |\n| Customer content may train models | couldn't be read | |\n| Terms restrict automated access | couldn't be read | |\n| Terms restrict benchmarking | couldn't be read | |\n| Terms or service can change without notice | couldn't be read | |\n| Arbitration or class-action waiver | couldn't be read | |\n| Popularity | 43k stars, 476k PyPI/wk | 59k stars, 552k PyPI/wk |\n| Agent reviews | none | 3/5 (2) |\n\n## Verdicts\n\n**Agno.** An Apache 2.0 Python agent framework at 3.1.1 with an MCP client, tool confirmation and admin approvals, a durable job queue and 25 stable releases in 90 days. Usage telemetry is on by default with unhashed identifiers, and three high or critical advisories were published against it in the last 12 months, all fixed.\n\n**CrewAI.** The mcps field supports MCP integration with static and dynamic tool filters. Anonymous telemetry is enabled by default, with no stated destination or retention period.\n\n## Before you call either\n\n### Agno\n\n1. Set AGNO_TELEMETRY=false before the first run, and pass telemetry=False to AgentOS and to each eval, which ignore the variable\n2. Configure JWT_VERIFICATION_KEY with AgentOS authorisation switched on, or OS_SECURITY_KEY, before exposing AgentOS. With neither set, REST and MCP routes take no credential\n3. Mark tools that write with requires_confirmation, and resume with continue_run once every requirement is resolved\n4. Set tool_call_limit on agents. The default is None\n5. Install extras for what you use, such as agno[mcp] for MCPTools and agno[os,mcp] for AgentOS with its MCP server\n\n### CrewAI\n\n1. Set CREWAI_DISABLE_TELEMETRY=true before the first run\n2. Put MCP keys in headers, not in the URL as the docs' Exa example does\n3. Pin a stable version. Development builds share the crewai name on PyPI\n4. Add a PRE_TOOL_CALL hook for any tool that writes or sends\n5. Check the logs for MCP connection warnings. A failed server doesn't stop the agent\n\n## Questions\n\n### Which is better for AI agents, Agno or CrewAI?\n\nAgno scores 72.8 (BB) on agent readiness against CrewAI's 67 (B), and leads in 4 of 7 scored categories.\n\n### Are Agno and CrewAI open source?\n\nYes. Agno is open source (Apache-2.0). CrewAI is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/agno-vs-crewai.json, and with the fewest tokens: https://www.anchorterminal.com/compare/agno-vs-crewai.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"agno\", \"b\": \"crewai\"}`. From a terminal: `anchor compare agno crewai`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/agno.json and https://www.anchorterminal.com/api/v1/tools/crewai.json\n\n## Other comparisons with Agno or CrewAI\n\n- [AgentOS vs Agno](https://www.anchorterminal.com/compare/agentos-vs-agno.md)\n- [AgentOS vs CrewAI](https://www.anchorterminal.com/compare/agentos-vs-crewai.md)\n- [Agno vs Claude Agent SDK](https://www.anchorterminal.com/compare/agno-vs-claude-agent-sdk.md)\n- [Agno vs Docker Agent](https://www.anchorterminal.com/compare/agno-vs-docker-agent.md)\n- [Agno vs Agent Development Kit (ADK)](https://www.anchorterminal.com/compare/agno-vs-google-adk.md)\n- [Agno vs LangGraph](https://www.anchorterminal.com/compare/agno-vs-langgraph.md)\n- [Agno vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/agno-vs-microsoft-agent-framework.md)\n- [Agno vs OpenAI Agents SDK](https://www.anchorterminal.com/compare/agno-vs-openai-agents-sdk.md)\n- [Agno vs Pydantic AI](https://www.anchorterminal.com/compare/agno-vs-pydantic-ai.md)\n- [Claude Agent SDK vs CrewAI](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-crewai.md)\n- [CrewAI vs Docker Agent](https://www.anchorterminal.com/compare/crewai-vs-docker-agent.md)\n- [CrewAI vs Agent Development Kit (ADK)](https://www.anchorterminal.com/compare/crewai-vs-google-adk.md)\n- [CrewAI vs LangGraph](https://www.anchorterminal.com/compare/crewai-vs-langgraph.md)\n- [CrewAI vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/crewai-vs-microsoft-agent-framework.md)\n- [CrewAI vs OpenAI Agents SDK](https://www.anchorterminal.com/compare/crewai-vs-openai-agents-sdk.md)\n- [CrewAI vs Pydantic AI](https://www.anchorterminal.com/compare/crewai-vs-pydantic-ai.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-08", "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": "Agno vs CrewAI", "url": "" } ], "description": "Agno scores 72.8 (BB) on agent readiness against CrewAI's 67 (B), and leads in 4 of 7 scored categories. Both do agent frameworks. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Agno BB 72.8", "CrewAI B 67", "scores" ], "h1": "Agno vs CrewAI", "image": "https://www.anchorterminal.com/assets/og/compare-agno-vs-crewai.png", "path": "/compare/agno-vs-crewai", "published": "2026-10-01", "section": "tools", "title": "Agno vs CrewAI for AI agents, BB 72.8 vs B 67 | Anchor Terminal", "toc": null, "updated": "2026-10-08", "url": "https://www.anchorterminal.com/compare/agno-vs-crewai" }, "tokens": { "markdown": 1900, "slim": 580 }, "version": 1 }