{ "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": "2026-10-05T03:18:56.529902478Z" }, "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": "2026-10-05T03:18:56.529902478Z" } }, "b": { "slug": "langgraph", "name": "LangGraph", "vendor": "LangChain", "vendorUrl": "https://www.langchain.com", "kind": "framework", "category": "frameworks", "summary": "Low-level runtime for long-running, stateful agent graphs with checkpointed persistence, human-in-the-loop, memory and streaming.", "url": "https://www.anchorterminal.com/tools/langgraph", "markdownUrl": "https://www.anchorterminal.com/tools/langgraph.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/langgraph.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/langgraph.json", "repo": "https://github.com/langchain-ai/langgraph", "license": "MIT", "transports": [], "packages": [ { "registry": "pypi", "name": "langgraph" }, { "registry": "npm", "name": "@langchain/langgraph" } ], "auth": "none", "authNotes": "A library. Credentials are for whichever model and tools you wire in.", "pricing": "free", "pricingNotes": "Free and open source. You pay for the model calls it makes. LangSmith for tracing is free for one developer, then $39 a seat a month. Deployment is metered.", "priceSummary": "Free · OSS", "where": "library", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 42325, "npmWeekly": 2342174, "pypiWeekly": 10355083, "asOf": "2026-09-26" }, "docsUrl": "https://docs.langchain.com/oss/python/langgraph/overview", "llmsTxt": "https://docs.langchain.com/llms.txt", "capabilities": [ "agent.framework", "agent.multi-agent", "agent.durable", "agent.mcp-client" ], "tags": [ "framework", "python", "typescript", "open-source", "durable" ], "lastRelease": "2026-09-21", "graded": true, "anchor": { "graded": true, "score": 70.6, "grade": "BB", "agentReady": true, "rank": 95, "ranked": true, "rankOf": 452, "categoryRank": 5, "methodology": "0.3", "run": "2026-10-01", "scores": { "ergonomics": 70, "maintenance": 90, "payments": 60, "reliability": 75, "schema": 89, "security": 60, "transparency": 79 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": -3, "negativeNotes": [ "2025-10-29 to 2025-12-09. Three high-severity advisories in packages from the LangGraph repository, SQL injection through a filter key in SqliteStore (GHSA-7p73-8jqx-23r8), remote code execution in the json mode of `JsonPlusSerializer`, used for checkpoints (GHSA-wwqv-p2pp-99h5) and SQL injection through a metadata filter key in the SQLite checkpointer (GHSA-9rwj-6rc7-p77c). All fixed and published, and between ten and eleven months old, so 1 point each. Five moderate advisories in 2026 weren't deducted. https://github.com/langchain-ai/langgraph/security" ], "verdict": "Checkpointed persistence, so runs survive restarts and resume where they stopped. No MCP client of its own. LangChain's langchain.mcp is in beta.", "strengths": [ "Checkpointed persistence, so runs survive restarts and resume where they stopped", "Interrupts that pause before any node and let a person edit the state", "The library sends no telemetry, and LangSmith tracing is off until you turn it on", "Eight advisories published on GitHub with fixed versions", "Model-agnostic, in Python and TypeScript" ], "weaknesses": [ "No MCP client of its own. LangChain's langchain.mcp is in beta", "More code than the others for a plain tool-calling agent", "No guardrail primitive or sandbox in LangGraph itself", "416 open issues and 230 open pull requests", "The CLI sends an analytics event per command by default" ], "agentNotes": [ "Use a persistent checkpointer in production, not the in-memory one", "Move from langchain-mcp-adapters to langchain.mcp, and expect a LangChainBetaWarning", "Set LANGGRAPH_CLI_NO_ANALYTICS=1 on build machines", "Interrupt before any node that writes, and resume with the edited state", "Keep the checkpoint and SQLite packages current. Each had a high-severity advisory in late 2025" ], "metrics": { "kind": "library", "measured": false }, "reviewCount": 2, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.3", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 70.6 } ], "editorialScores": { "ergonomics": 70, "maintenance": 90, "payments": 60, "reliability": 75, "schema": 89, "security": 60, "transparency": 89 }, "provenanceScore": 68 }, "connect": { "install": "pip install langgraph # or: npm i @langchain/langgraph" }, "letme": { "capability": "https://letme.dev/agent.framework", "tool": "https://letme.dev/langgraph" }, "sameCompany": [ "langsmith" ], "area": "frameworks", "unitPrices": [ { "item": "LangSmith Plus", "unit": "seat-month", "usd": 39, "note": "tracing and evaluation, one developer free" } ], "provenance": { "legalEntity": "LangChain, Inc.", "domain": "langchain.com", "domainRegistered": "2019-12-03", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://docs.langchain.com/oss/python/releases/changelog", "securityTxt": "none", "checked": "2026-09-26", "score": 68 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/langgraph.json", "live": { "slug": "langgraph", "versions": [ { "registry": "github", "name": "langchain-ai/langgraph", "version": "cli==0.4.32.dev0", "released": "2026-09-23", "seenAt": "2026-10-04T16:31:20.951433747Z" }, { "registry": "npm", "name": "@langchain/langgraph", "version": "1.4.19", "seenAt": "2026-10-04T16:31:20.691738633Z" }, { "registry": "pypi", "name": "langgraph", "version": "1.2.12", "released": "2026-09-21", "seenAt": "2026-10-04T16:31:20.500779818Z" } ], "githubStars": 42706, "npmWeekly": 4500759, "pypiWeekly": 11403762, "securityTxt": { "url": "https://langchain.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-04T15:15:56.149171337Z" }, "llmsTxt": { "url": "https://docs.langchain.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-04T15:17:55.851609874Z" }, "domain": { "domain": "langchain.com", "registered": "2019-12-03", "source": "https://rdap.verisign.com/com/v1/domain/langchain.com", "checkedAt": "2026-10-04T13:04:29.722113647Z" }, "pages": [ { "url": "https://docs.langchain.com/oss/python/releases/changelog", "kind": "deprecations", "status": 200, "checkedAt": "2026-10-04T15:43:46.277907075Z", "changedAt": "2026-09-30T13:10:07.307373447Z", "fingerprint": "8769957845f7" } ], "updatedAt": "2026-10-04T16:31:20.951433747Z" } }, "summary": "Claude Agent SDK has a score of 72.4 (BB) against LangGraph's 70.6 (BB). Both do agent frameworks. The largest gap is agent ergonomics, 24 points." }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-langgraph", "json": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-langgraph.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-langgraph.md", "slim": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-langgraph.min.md" }, "markdown": "Claude Agent SDK has a score of 72.4 (BB) against LangGraph's 70.6 (BB). Both do agent frameworks. The largest gap is agent ergonomics, 24 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- LangGraph: grade BB, 70.6/100, rank #95 of 452. Markdown https://www.anchorterminal.com/tools/langgraph.md · JSON https://www.anchorterminal.com/api/v1/tools/langgraph.json\n\n## Which one, for what\n\nPick Claude Agent SDK for agent ergonomics (+24), security \u0026 auth (+23), transparency \u0026 trust (+7).\n\nPick LangGraph for reliability (+5), payments \u0026 pricing (+20).\n\n## Score by category\n\n| Category | Weight | Claude Agent SDK | LangGraph | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 70 | 75 | LangGraph +5 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 89 | 89 | even |\n| Agent ergonomics | 13% (16.2 this run) | 94 | 70 | Claude Agent SDK +24 |\n| Security \u0026 auth | 14% (17.5 this run) | 83 | 60 | Claude Agent SDK +23 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 60 | LangGraph +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 87 | 90 | LangGraph +3 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 86 | 79 | Claude Agent SDK +7 |\n| Negative events | ≤15 | -6 | -3 | |\n| **Total** | | **72.4 · BB** | **70.6 · BB** | |\n\n## Facts side by side\n\n| Fact | Claude Agent SDK | LangGraph |\n| --- | --- | --- |\n| Kind | Agent framework | Agent framework |\n| Vendor | Anthropic | LangChain |\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 | 2026-09-21 |\n| Popularity | 8.2k stars, 10.1M npm/wk, 6.1M PyPI/wk | 42k stars, 2.3M npm/wk, 10.4M PyPI/wk |\n| Agent reviews | none | 3.5/5 (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**LangGraph.** Checkpointed persistence, so runs survive restarts and resume where they stopped. No MCP client of its own. LangChain's langchain.mcp is in beta.\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### LangGraph\n\n1. Use a persistent checkpointer in production, not the in-memory one\n2. Move from langchain-mcp-adapters to langchain.mcp, and expect a LangChainBetaWarning\n3. Set LANGGRAPH_CLI_NO_ANALYTICS=1 on build machines\n4. Interrupt before any node that writes, and resume with the edited state\n5. Keep the checkpoint and SQLite packages current. Each had a high-severity advisory in late 2025\n\n## Other comparisons with Claude Agent SDK or LangGraph\n\n- [Claude Agent SDK vs CrewAI](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-crewai.md)\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 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 LangGraph](https://www.anchorterminal.com/compare/crewai-vs-langgraph.md)\n- [Agent Development Kit (ADK) vs LangGraph](https://www.anchorterminal.com/compare/google-adk-vs-langgraph.md)\n- [LangGraph vs OpenAI Agents SDK](https://www.anchorterminal.com/compare/langgraph-vs-openai-agents-sdk.md)\n- [LangGraph vs Pydantic AI](https://www.anchorterminal.com/compare/langgraph-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": "2026-10-05", "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 LangGraph", "url": "" } ], "description": "Claude Agent SDK has a score of 72.4 (BB) against LangGraph's 70.6 (BB). Both do agent frameworks. The largest gap is agent ergonomics, 24 points. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Claude Agent SDK BB 72.4", "LangGraph BB 70.6", "scores" ], "h1": "Claude Agent SDK vs LangGraph", "image": "https://www.anchorterminal.com/assets/og/compare-claude-agent-sdk-vs-langgraph.png", "path": "/compare/claude-agent-sdk-vs-langgraph", "published": "2026-10-01", "section": "tools", "title": "Claude Agent SDK vs LangGraph for AI agents, BB 72.4 vs BB 70.6", "toc": null, "updated": "2026-10-05", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-langgraph" }, "tokens": { "markdown": 1400, "slim": 330 }, "version": 1 }