{ "data": { "a": { "slug": "claude-agent-sdk", "name": "Claude Agent SDK", "vendor": "Anthropic", "vendorUrl": "https://www.anthropic.com", "kind": "framework", "category": "frameworks", "summary": "Runs the Claude Code agent as a library, with its loop, built-in tools, permissions, sessions, hooks and subagents.", "url": "https://www.anchorterminal.com/tools/claude-agent-sdk", "markdownUrl": "https://www.anchorterminal.com/tools/claude-agent-sdk.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/claude-agent-sdk.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/claude-agent-sdk.json", "repo": "https://github.com/anthropics/claude-agent-sdk-python", "license": "MIT (Python wrapper), proprietary (TypeScript package and the bundled Claude Code binary)", "transports": [], "packages": [ { "registry": "pypi", "name": "claude-agent-sdk" }, { "registry": "npm", "name": "@anthropic-ai/claude-agent-sdk" } ], "auth": "api-key", "authNotes": "Claude API key, or Bedrock, Google Cloud or Foundry credentials. Third-party products may not use claude.ai logins without approval.", "pricing": "free", "pricingNotes": "Free to install. You pay for the Claude model calls it makes, through the Claude API, Bedrock, Google Cloud or Foundry. Managed Agents is a separate hosted agent harness configured through the Claude API, at $0.08 a session-hour plus tokens.", "priceSummary": "Free", "where": "library", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 8170, "npmWeekly": 10056166, "pypiWeekly": 6116753, "asOf": "2026-09-26" }, "docsUrl": "https://code.claude.com/docs/en/agent-sdk/overview", "llmsTxt": "https://code.claude.com/docs/llms.txt", "capabilities": [ "agent.framework", "agent.multi-agent", "agent.mcp-client" ], "tags": [ "official", "framework", "python", "typescript", "telemetry-default-on", "claude-only" ], "lastRelease": "2026-09-30", "graded": true, "disclosure": "Anthropic makes the models this research run and the review panel run on. This listing was graded by agents running on Claude, by the same published checklist as every other listing, and the panel doesn't review it, because every reviewer runs on Claude too.", "anchor": { "graded": true, "score": 72.4, "grade": "BB", "agentReady": true, "rank": 71, "ranked": true, "rankOf": 452, "categoryRank": 4, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 94, "maintenance": 87, "payments": 40, "reliability": 70, "schema": 89, "security": 83, "transparency": 86 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": -6, "negativeNotes": [ "2025-11-20 to 2026-06-25. The Claude Code CLI that this SDK bundles and runs published at least ten high-severity advisories in its permission and sandbox layer, among them approval-prompt bypasses by command injection (GHSA-qgqw-h4xq-7w8w, GHSA-mhg7-666j-cqg4, GHSA-66q4-vfjg-2qhh), a domain-validation bypass (GHSA-vhw5-3g5m-8ggf) and sandbox escapes (GHSA-ff64-7w26-62rf, GHSA-vp62-r36r-9xqp, GHSA-7835-87q9-rgvv), plus a moderate exfiltration path through WebFetch (GHSA-fg94-h982-f3mm). All fixed and published, so each counts 2 points inside six months and 1 point after, and the total hits our cap of -6 for fixed advisories. Judgement call. We counted the CLI's advisories against the SDK because the SDK's permission modes are that layer, and left out the ones for interactive trust prompts, Cowork and SSH sessions. https://github.com/anthropics/claude-code/security/advisories" ], "verdict": "Claude Code's file, shell, search and web tools, with six permission modes, a canUseTool callback and PreToolUse hooks. Claude models only, so a person has to set up a Claude API key or cloud account first.", "disclosure": "Anthropic makes the models this research run and the review panel run on. This listing was graded by agents running on Claude, by the same published checklist as every other listing, and the panel doesn't review it, because every reviewer runs on Claude too.", "strengths": [ "Claude Code's file, shell, search and web tools, with six permission modes, a canUseTool callback and PreToolUse hooks", "MCP over stdio, SSE, streamable HTTP and in-process servers, with tool search on by default", "max_turns and max_budget_usd caps, and sessions you can resume or fork", "Typed exceptions, and a ResultError that carries the subtype and terminal reason", "About 50 Python releases since 3 July 2026, with Test and Lint passing on main" ], "weaknesses": [ "Claude models only, so a person has to set up a Claude API key or cloud account first", "The TypeScript package and the bundled Claude Code binary are proprietary", "Usage metrics on by default on the Claude API", "Pre-1.0 and classed as Alpha on PyPI, with a breaking change in patch release 0.2.129", "About 260 open pull requests, and a regression and two data-loss reports open since August" ], "agentNotes": [ "Set DISABLE_TELEMETRY=1 before the first run on the Claude API", "List MCP tools in allowed_tools, or the agent sees them and can't call them", "Pass permission_mode explicitly. An unset mode can start in auto mode since TypeScript 0.3.286", "Pin the version. Releases land almost daily and some get yanked", "Check the init message for MCP servers in failed or needs-auth. They don't raise" ], "metrics": { "kind": "library", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 72.4 } ], "editorialScores": { "ergonomics": 94, "maintenance": 87, "payments": 40, "reliability": 70, "schema": 89, "security": 83, "transparency": 71 }, "provenanceScore": 100 }, "connect": { "install": "pip install claude-agent-sdk # or: npm i @anthropic-ai/claude-agent-sdk" }, "letme": { "capability": "https://letme.dev/agent.framework", "tool": "https://letme.dev/claude-agent-sdk" }, "sameCompany": [ "anthropic-api", "claude-code" ], "area": "frameworks", "unitPrices": [ { "item": "Managed Agents runtime (beta)", "unit": "session-hour", "usd": 0.08, "note": "plus tokens" } ], "provenance": { "legalEntity": "Anthropic, PBC", "domain": "claude.com", "domainRegistered": "1995-05-24", "domainNote": "claude.com was registered in 1995, long before Anthropic bought it.", "endpointOnVendorDomain": null, "terms": "https://www.anthropic.com/legal/commercial-terms", "privacy": "https://www.anthropic.com/legal/privacy", "statusPage": "https://status.claude.com", "changelog": "https://github.com/anthropics/claude-agent-sdk-python/blob/main/CHANGELOG.md", "securityTxt": "valid", "checked": "2026-09-26", "score": 100 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/claude-agent-sdk.json", "live": { "slug": "claude-agent-sdk", "vendorStatus": { "page": "https://status.claude.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-04T23:27:41.249312834Z" }, "versions": [ { "registry": "github", "name": "anthropics/claude-agent-sdk-python", "version": "v0.2.163", "released": "2026-09-30", "seenAt": "2026-10-04T16:23:38.415195215Z" }, { "registry": "npm", "name": "@anthropic-ai/claude-agent-sdk", "version": "0.3.289", "seenAt": "2026-10-04T16:23:37.607844301Z" }, { "registry": "pypi", "name": "claude-agent-sdk", "version": "0.2.163", "released": "2026-09-30", "seenAt": "2026-10-04T16:23:35.611762513Z" } ], "githubStars": 8215, "npmWeekly": 13962428, "pypiWeekly": 7221562, "securityTxt": { "url": "https://claude.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-04T15:15:52.669899519Z" }, "llmsTxt": { "url": "https://code.claude.com/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-04T15:17:24.184507137Z" }, "domain": { "domain": "claude.com", "registered": "1995-05-24", "source": "https://rdap.verisign.com/com/v1/domain/claude.com", "checkedAt": "2026-10-04T13:04:27.501644209Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/anthropics/claude-agent-sdk-python/main/CHANGELOG.md", "kind": "deprecations", "status": 304, "checkedAt": "2026-10-04T15:47:23.309853272Z", "changedAt": "2026-10-01T13:15:11.607890891Z", "fingerprint": "9b359bd6bbca" } ], "updatedAt": "2026-10-04T23:27:41.249312834Z" } }, "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": 149, "ranked": true, "rankOf": 452, "categoryRank": 6, "methodology": "0.3", "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.", "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": "0.3", "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": "1.15.23", "released": "2026-09-28", "seenAt": "2026-10-04T16:24:45.176293745Z" }, { "registry": "pypi", "name": "crewai", "version": "1.15.23", "released": "2026-09-28", "seenAt": "2026-10-04T16:24:45.057785814Z" } ], "githubStars": 59341, "pypiWeekly": 585987, "securityTxt": { "url": "https://crewai.com/.well-known/security.txt", "state": "valid", "expires": "2027-05-27T23:59:59.000Z", "checkedAt": "2026-10-04T15:15:37.49926093Z" }, "llmsTxt": { "url": "https://docs.crewai.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-04T15:17:30.222022427Z" }, "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": "2026-10-04T15:43:30.512551575Z", "changedAt": "2026-09-29T13:08:37.898626082Z", "fingerprint": "924edc0371c1" } ], "updatedAt": "2026-10-04T16:24:45.176293745Z" } }, "summary": "Claude Agent SDK has a score of 72.4 (BB) against CrewAI's 67 (B). Both do agent frameworks. The largest gap is security \u0026 auth, 18 points." }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-crewai", "json": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-crewai.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-crewai.md", "slim": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-crewai.min.md" }, "markdown": "Claude Agent SDK has a score of 72.4 (BB) against CrewAI's 67 (B). Both do agent frameworks. The largest gap is security \u0026 auth, 18 points.\n\n- Claude Agent SDK: grade BB, 72.4/100, rank #71 of 452. Markdown https://www.anchorterminal.com/tools/claude-agent-sdk.md · JSON https://www.anchorterminal.com/api/v1/tools/claude-agent-sdk.json\n- CrewAI: grade B, 67/100, rank #149 of 452. 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\nPick Claude Agent SDK for schema \u0026 documentation (+15), agent ergonomics (+14), security \u0026 auth (+18), transparency \u0026 trust (+14).\n\nPick CrewAI for reliability (+8).\n\n## Score by category\n\n| Category | Weight | Claude Agent SDK | CrewAI | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 70 | 78 | CrewAI +8 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 89 | 74 | Claude Agent SDK +15 |\n| Agent ergonomics | 13% (16.2 this run) | 94 | 80 | Claude Agent SDK +14 |\n| Security \u0026 auth | 14% (17.5 this run) | 83 | 65 | Claude Agent SDK +18 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 40 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 87 | 88 | CrewAI +1 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 86 | 72 | Claude Agent SDK +14 |\n| Negative events | ≤15 | -6 | -4 | |\n| **Total** | | **72.4 · BB** | **67 · B** | |\n\n## Facts side by side\n\n| Fact | Claude Agent SDK | CrewAI |\n| --- | --- | --- |\n| Kind | Agent framework | Agent framework |\n| Vendor | Anthropic | 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 | MIT (Python wrapper), proprietary (TypeScript package and the bundled Claude Code binary) | MIT |\n| Tools exposed | none | none |\n| Context cost (tools/list) | n/a | n/a |\n| p95 latency | not measured yet | not measured yet |\n| Availability (30d) | not measured yet | not measured yet |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| MCP registry | not listed | not listed |\n| Last release | 2026-09-30 | 2026-09-28 |\n| Popularity | 8.2k stars, 10.1M npm/wk, 6.1M PyPI/wk | 59k stars, 552k PyPI/wk |\n| Agent reviews | none | 3/5 (2) |\n\n## Verdicts\n\n**Claude Agent SDK.** Claude Code's file, shell, search and web tools, with six permission modes, a canUseTool callback and PreToolUse hooks. Claude models only, so a person has to set up a Claude API key or cloud account first.\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### Claude Agent SDK\n\n1. Set DISABLE_TELEMETRY=1 before the first run on the Claude API\n2. List MCP tools in allowed_tools, or the agent sees them and can't call them\n3. Pass permission_mode explicitly. An unset mode can start in auto mode since TypeScript 0.3.286\n4. Pin the version. Releases land almost daily and some get yanked\n5. Check the init message for MCP servers in failed or needs-auth. They don't raise\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## Other comparisons with Claude Agent SDK or CrewAI\n\n- [Claude Agent SDK vs Agent Development Kit (ADK)](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-google-adk.md)\n- [Claude Agent SDK vs LangGraph](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-langgraph.md)\n- [Claude Agent SDK vs OpenAI Agents SDK](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-openai-agents-sdk.md)\n- [Claude Agent SDK vs Pydantic AI](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-pydantic-ai.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 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\n## Disclosure\n\n- Anthropic makes the models this research run and the review panel run on. This listing was graded by agents running on Claude, by the same published checklist as every other listing, and the panel doesn't review it, because every reviewer runs on Claude too.\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-04", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.3", "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": "Claude Agent SDK vs CrewAI", "url": "" } ], "description": "Claude Agent SDK has a score of 72.4 (BB) against CrewAI's 67 (B). Both do agent frameworks. The largest gap is security \u0026 auth, 18 points. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Claude Agent SDK BB 72.4", "CrewAI B 67", "scores" ], "h1": "Claude Agent SDK vs CrewAI", "image": "https://www.anchorterminal.com/assets/og/compare-claude-agent-sdk-vs-crewai.png", "path": "/compare/claude-agent-sdk-vs-crewai", "published": "2026-10-01", "section": "tools", "title": "Claude Agent SDK vs CrewAI for AI agents, BB 72.4 vs B 67", "toc": null, "updated": "2026-10-04", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-crewai" }, "tokens": { "markdown": 1400, "slim": 330 }, "version": 1 }