{ "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" }, "tool": { "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" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 70, "points": 14, "reason": "Official packages on PyPI (Requires-Python \u003e=3.10) and npm (node \u003e=18) (20). Test and Lint workflows pass on main (25). 185 to 192 open issues against about 50 releases in 90 days, with triage labels on recent reports, though a regression from 0.2.140 (#1226) and two data-loss reports (#1191, #1200) were still open after five weeks (18). The changelog has Breaking Changes headings but no dates, 0.2.129 broke skill names in a patch-level bump, and TypeScript 0.3.286 changed what an unset permission mode does (7). Python 0.2.163 and TypeScript 0.3.286 are pre-1.0 and PyPI classes the package as 3 - Alpha (0)." }, { "key": "performance", "name": "Performance", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes." }, { "key": "schema", "name": "Schema \u0026 documentation", "weight": 13, "effectiveWeight": 16.25, "score": 89, "points": 14.46, "reason": "Typed public interfaces with a full Python and TypeScript reference, options as dataclasses and TypedDicts (25). llms.txt at code.claude.com/docs/llms.txt and Markdown pages (10). The overview has a table of when to use the Agent SDK, the CLI, the Client SDK or Managed Agents, and each permission mode says when to use it, but permissions run through a six-step evaluation order with many exceptions, and open issue #1220 says as much (15). Permission modes and MCP server configs are typed variants, though TypedDicts aren't validated at runtime (12). Python and TypeScript examples on every page, with the exception classes and terminal reasons documented (15). A changelog per package, with version headings and no dates (12)." }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 94, "points": 15.28, "reason": "The documented agent with one MCP server is about 15 lines with the built-in client, and tool search withholds MCP tool definitions by default (25). max_turns and max_budget_usd stop runs, and MCP results over 25,000 tokens go to a file instead of the context (20). A typed exception hierarchy with ResultError carrying the subtype and terminal reason, but a failed MCP server doesn't raise and has to be read from the init message or polled (18). Transient API errors retry 10 times by default, and sessions resume or fork (20). query() needs only a prompt, but MCP tools can't be called until you list them in allowed_tools, and since TypeScript 0.3.286 an unset permission mode can start in auto mode (6). Python and TypeScript (5)." }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 83, "points": 14.53, "reason": "Usage metrics go to Anthropic and third-party logging by default on the Claude API, without code, prompts or file paths, and DISABLE_TELEMETRY=1 turns them off. They're off by default on Bedrock, Google Cloud and Foundry. WebFetch sends hostnames to api.anthropic.com for a blocklist check on every provider, with its own opt-out (20). canUseTool approval callback and PreToolUse hooks, plan and dontAsk modes with deny rules, and sandbox settings for shell commands (20). Hooks can block a call and auto mode runs a classifier on actions, but there's no input or output guardrail primitive (10). OpenTelemetry export to your own collector, opt-in (15). HackerOne bug bounty, advisories published with fixed versions on the claude-code repo and a valid security.txt, but the Python SDK repo has no SECURITY.md (18). Framework reading, so SOC 2 isn't scored. The bundled CLI's advisories are counted under negative events, not here." }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 40, "points": 5, "reason": "No payment protocol (0). Claude model prices and Managed Agents at $0.08 a session-hour are published without a login (20). The package is free and needs no card (20). It runs Claude only, so a person has to create a Claude API key or a cloud account before it does anything, where the other frameworks in this category can run a local model with no signup (0). Judgement call, and it goes against Anthropic's own listing. We didn't treat Managed Agents as this SDK's hosted option, since it doesn't run SDK code, and the score would be the same if we had." }, { "key": "tasks", "name": "Task success", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored." }, { "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7, "effectiveWeight": 8.75, "score": 87, "points": 7.61, "reason": "Python 0.2.163 on 2026-09-30 (30). About 50 Python releases since 2026-07-03 (20). Recent bug reports carry triage labels (bug, regression, invalid), but 185 open issues and about 260 open pull requests is a large backlog, and we couldn't see reply times (15). Python and TypeScript packages both current (15). CI and a dependency-graph workflow pass, but some releases are yanked and #1234 reports a partial publish of 0.2.144 (7)." }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 86, "points": 7.53, "note": "editorial 71, provenance 100", "reason": "The Python wrapper is MIT, but its wheel bundles the proprietary Claude Code binary, and the TypeScript package says All rights reserved under Anthropic's Commercial Terms (18). The data-usage page states 30-day retention for API users, zero data retention on request, no training on commercial data and 30 days of local transcripts in ~/.claude/projects, but names the logging and error-tracking services only as third parties (25). Deprecations appear in the changelog without dates, and there's no written deprecation policy for the SDK (8). Telemetry is documented per provider, with an opt-out for each service (20). Judgement call on the licence line, written on Claude." } ], "assessment": { "date": "2026-10-01", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "The documented agent with one MCP server is about 15 lines with the built-in client, and tool search withholds MCP tool definitions by default (25). max_turns and max_budget_usd stop runs, and MCP results over 25,000 tokens go to a file instead of the context (20). A typed exception hierarchy with ResultError carrying the subtype and terminal reason, but a failed MCP server doesn't raise and has to be read from the init message or polled (18). Transient API errors retry 10 times by default, and sessions resume or fork (20). query() needs only a prompt, but MCP tools can't be called until you list them in allowed_tools, and since TypeScript 0.3.286 an unset permission mode can start in auto mode (6). Python and TypeScript (5).", "maintenance": "Python 0.2.163 on 2026-09-30 (30). About 50 Python releases since 2026-07-03 (20). Recent bug reports carry triage labels (bug, regression, invalid), but 185 open issues and about 260 open pull requests is a large backlog, and we couldn't see reply times (15). Python and TypeScript packages both current (15). CI and a dependency-graph workflow pass, but some releases are yanked and #1234 reports a partial publish of 0.2.144 (7).", "payments": "No payment protocol (0). Claude model prices and Managed Agents at $0.08 a session-hour are published without a login (20). The package is free and needs no card (20). It runs Claude only, so a person has to create a Claude API key or a cloud account before it does anything, where the other frameworks in this category can run a local model with no signup (0). Judgement call, and it goes against Anthropic's own listing. We didn't treat Managed Agents as this SDK's hosted option, since it doesn't run SDK code, and the score would be the same if we had.", "reliability": "Official packages on PyPI (Requires-Python \u003e=3.10) and npm (node \u003e=18) (20). Test and Lint workflows pass on main (25). 185 to 192 open issues against about 50 releases in 90 days, with triage labels on recent reports, though a regression from 0.2.140 (#1226) and two data-loss reports (#1191, #1200) were still open after five weeks (18). The changelog has Breaking Changes headings but no dates, 0.2.129 broke skill names in a patch-level bump, and TypeScript 0.3.286 changed what an unset permission mode does (7). Python 0.2.163 and TypeScript 0.3.286 are pre-1.0 and PyPI classes the package as 3 - Alpha (0).", "schema": "Typed public interfaces with a full Python and TypeScript reference, options as dataclasses and TypedDicts (25). llms.txt at code.claude.com/docs/llms.txt and Markdown pages (10). The overview has a table of when to use the Agent SDK, the CLI, the Client SDK or Managed Agents, and each permission mode says when to use it, but permissions run through a six-step evaluation order with many exceptions, and open issue #1220 says as much (15). Permission modes and MCP server configs are typed variants, though TypedDicts aren't validated at runtime (12). Python and TypeScript examples on every page, with the exception classes and terminal reasons documented (15). A changelog per package, with version headings and no dates (12).", "security": "Usage metrics go to Anthropic and third-party logging by default on the Claude API, without code, prompts or file paths, and DISABLE_TELEMETRY=1 turns them off. They're off by default on Bedrock, Google Cloud and Foundry. WebFetch sends hostnames to api.anthropic.com for a blocklist check on every provider, with its own opt-out (20). canUseTool approval callback and PreToolUse hooks, plan and dontAsk modes with deny rules, and sandbox settings for shell commands (20). Hooks can block a call and auto mode runs a classifier on actions, but there's no input or output guardrail primitive (10). OpenTelemetry export to your own collector, opt-in (15). HackerOne bug bounty, advisories published with fixed versions on the claude-code repo and a valid security.txt, but the Python SDK repo has no SECURITY.md (18). Framework reading, so SOC 2 isn't scored. The bundled CLI's advisories are counted under negative events, not here.", "transparency": "The Python wrapper is MIT, but its wheel bundles the proprietary Claude Code binary, and the TypeScript package says All rights reserved under Anthropic's Commercial Terms (18). The data-usage page states 30-day retention for API users, zero data retention on request, no training on commercial data and 30 days of local transcripts in ~/.claude/projects, but names the logging and error-tracking services only as third parties (25). Deprecations appear in the changelog without dates, and there's no written deprecation policy for the SDK (8). Telemetry is documented per provider, with an opt-out for each service (20). Judgement call on the licence line, written on Claude." }, "sources": [ { "what": "PyPI release history", "url": "https://pypi.org/project/claude-agent-sdk/#history", "seen": "2026-10-01" }, { "what": "npm latest", "url": "https://registry.npmjs.org/@anthropic-ai/claude-agent-sdk/latest", "seen": "2026-10-01" }, { "what": "Python repo and README (bundled CLI)", "url": "https://github.com/anthropics/claude-agent-sdk-python", "seen": "2026-10-01" }, { "what": "CI runs on main", "url": "https://github.com/anthropics/claude-agent-sdk-python/actions", "seen": "2026-10-01" }, { "what": "open issues", "url": "https://github.com/anthropics/claude-agent-sdk-python/issues", "seen": "2026-10-01" }, { "what": "changelog", "url": "https://github.com/anthropics/claude-agent-sdk-python/blob/main/CHANGELOG.md", "seen": "2026-10-01" }, { "what": "overview, licence and terms", "url": "https://code.claude.com/docs/en/agent-sdk/overview", "seen": "2026-10-01" }, { "what": "permissions", "url": "https://code.claude.com/docs/en/agent-sdk/permissions", "seen": "2026-10-01" }, { "what": "MCP", "url": "https://code.claude.com/docs/en/agent-sdk/mcp", "seen": "2026-10-01" }, { "what": "Python reference", "url": "https://code.claude.com/docs/en/agent-sdk/python", "seen": "2026-10-01" }, { "what": "data usage and telemetry", "url": "https://code.claude.com/docs/en/data-usage", "seen": "2026-10-01" }, { "what": "pricing (Managed Agents)", "url": "https://platform.claude.com/docs/en/about-claude/pricing", "seen": "2026-10-01" }, { "what": "Claude Code security policy and advisories", "url": "https://github.com/anthropics/claude-code/security/advisories", "seen": "2026-10-01" }, { "what": "CVE-2026-35022, rejected by the CNA", "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-35022", "seen": "2026-10-01" } ], "openQuestions": [ "We couldn't load the observability page this run, so the OpenTelemetry line rests on the listing's check of 2026-09-26", "The pricing page says new API accounts get a small amount of free credit but not whether that needs a card", "We found no public statement on whether Managed Agents is still in beta, so the listing's beta label is unconfirmed", "Reply times on open issues weren't visible in the pages we could load", "We didn't check whether the TypeScript repo has a SECURITY.md" ] }, "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" ], "notable": [ "The TypeScript package's LICENSE.md says \"All rights reserved\" under Anthropic's commercial terms (https://github.com/anthropics/claude-agent-sdk-typescript/blob/main/LICENSE.md)", "The bundled Claude Code CLI sends usage metrics by default on the Claude API, not on Bedrock, Google Cloud or Foundry. `DISABLE_TELEMETRY=1` turns it off (https://code.claude.com/docs/en/data-usage)", "About 50 Python releases in 90 days (https://pypi.org/project/claude-agent-sdk/)" ], "area": "frameworks", "details": [ { "label": "Languages", "value": "Python, TypeScript" }, { "label": "Models", "value": "Claude only, through the Claude API, Bedrock, Google Cloud or Foundry" }, { "label": "MCP client", "value": "stdio, SSE, streamable HTTP, in-process" }, { "label": "Multi-agent", "value": "Subagents" }, { "label": "Durable state", "value": "Local sessions with resume and fork" }, { "label": "Human approval", "value": "Permission modes, approval callback, hooks" }, { "label": "Tracing", "value": "OpenTelemetry, opt-in" }, { "label": "Telemetry", "value": "On by default via the bundled CLI. `DISABLE_TELEMETRY=1`" }, { "label": "Releases in 90 days", "value": "About 50" }, { "label": "Hosted runtime", "value": "Managed Agents (beta), $0.08 a session-hour plus tokens" } ], "unitPrices": [ { "item": "Managed Agents runtime (beta)", "unit": "session-hour", "usd": 0.08, "note": "plus tokens" } ], "deprecations": [ { "what": "0.2.129 raises `ValueError` on invalid skill names", "date": "2026-08-04", "source": "https://github.com/anthropics/claude-agent-sdk-python/blob/main/CHANGELOG.md", "kind": "breaking" } ], "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, "checks": [ { "check": "Legal entity named", "value": "Anthropic, PBC", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "claude.com, registered 1995-05-24 (31 years)", "points": 15, "max": 15, "state": "ok" }, { "check": "Endpoint on the vendor's domain", "value": "no hosted endpoint", "points": 0, "max": 0, "state": "na" }, { "check": "Terms of service", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "Privacy policy", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "Status page", "value": "status.claude.com", "points": 10, "max": 10, "state": "ok" }, { "check": "Changelog", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "security.txt", "value": "valid", "points": 10, "max": 10, "state": "ok" } ] }, "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": "2026-10-05T02:28:52.216557522Z" }, "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": "2026-10-05T02:28:52.216557522Z" } } }