{ "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", "dns": "claude-agent-sdk.grade.anchorterminal.com", "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": "2026-10-31", "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 re-checked on 15 October 2026 with every judgement call written in the note. Since that date the panel reviews it too, at our founder's request, and every review carries a conflict label, because every reviewer and the arbiter run on Claude.", "anchor": { "graded": true, "score": 70.3, "grade": "BB", "agentReady": true, "rank": 204, "ranked": true, "rankOf": 1510, "categoryRank": 10, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 95, "maintenance": 87, "payments": 40, "reliability": 70, "schema": 89, "security": 83, "transparency": 83 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": -8, "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. On 1 November all fall inside twelve months, those before 1 May at 1 point, and the total still passes 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", "2026-10-05. The Claude Code advisories page lists GHSA-5j29-h97v-84ch, \"Arbitrary File Write via Write-Time Symlink Following (TOCTOU) in Claude Code\", rated High and published on 5 October 2026, and the SDK bundles that CLI and its file-writing tools. The advisory itself didn't load for us on 15 October, so its fixed version is unchecked. A published advisory is read as fixed and documented, like the others in the line above, so it sits under the -6 cap already reached and adds nothing. Counting it as unfixed because our reader couldn't open the page would let our own fetch limits read as the vendor failing. We left out GHSA-gfvf-j8jh-jxxw (Low, 29 September, managed settings) and GHSA-v234-4jrq-mgg6 (High, 25 September, Claude Desktop through a Cowork folder) as outside the permission and sandbox layer, and for the same reason GHSA-pq7j-f95f-qfcv (High, published 15 October 2026, a plugin hash-pin bypass in the plugin install flow, fixed in Claude Code 2.1.179), found in GitHub's reviewed database through OSV on 17 October. It would sit under the cap either way. The advisories list wasn't readable on 1 November (github.com answered the proxy's 403), so advisories published after 17 October are unchecked; any for the permission and sandbox layer would sit under the same cap. https://github.com/anthropics/claude-code/security/advisories and https://api.osv.dev/v1/vulns/GHSA-pq7j-f95f-qfcv", "2026-10-02 to 2026-10-31. The Claude Code CLI this SDK bundles fixed, in its changelog for 2.1.288 to 2.1.300, a dangerous `rm` inside `bash -c` running without a prompt under a shell allow rule, Bash deny and ask rules missed behind an environment-variable prefix, hook approvals and auto mode skipping the prompt for reads from network (UNC) paths (marked Security), sandboxed commands writing into a `--plugin-dir` folder or reaching a denied path through a symlink on macOS, and agent hooks whose model was unavailable allowing the action instead of falling back (2.1.300). The same pattern continued to 31 October. 2.1.310 (23 October) fixed PreToolUse and PermissionRequest hooks on Windows letting a call through when Git Bash was missing. 2.1.314 (30 October) fixed sandbox protections not applying to a worktree entered by `claude -p --resume`, Bash hooks not running on commands the Monitor tool starts, a settings file excluded with `--setting-sources` still supplying auto mode rules and saved permission consents (also TypeScript 0.3.314), and `forceRemoteSettingsRefresh` letting sessions start without policy. 2.1.316 (31 October) fixed a managed `autoMode.allow` list getting the built-in exceptions back. TypeScript 0.3.309 (22 October) fixed host-supplied `managedSettings` dropping `disableAllHooks`. No advisory for the October group appeared on the advisories list read on 15 October or in GitHub's reviewed database read through OSV on 17 October, and the list couldn't be read on 1 November, so they're disclosed only in the changelogs, all released. Judgement call, the same as the Claude Code listing's. The SDK's permission modes are that layer, so the group counts -2 here as it does there, the deduction GitHub Copilot CLI got for one changelog-only enforcement-gap fix, and the later fixes fold into the same term, as repeated breaks in one package fold into one term (monday, microsoft-agent-framework). https://code.claude.com/docs/en/changelog and https://github.com/anthropics/claude-agent-sdk-typescript/blob/main/CHANGELOG.md" ], "verdict": "Claude Code's file, shell, search and web tools as a library, 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, and the bundled CLI keeps fixing permission and sandbox gaps in its changelog.", "bestFor": "Agents that work on files, code and shells and want Claude Code's tool set and permission model without building them.", "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 re-checked on 15 October 2026 with every judgement call written in the note. Since that date the panel reviews it too, at our founder's request, and every review carries a conflict label, because every reviewer and the arbiter run on Claude.", "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", "47 Python and 81 TypeScript release tags between 4 August and 31 October 2026" ], "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, with behaviour changes in patch releases (0.2.129, TypeScript 0.3.286, 0.3.300, 0.3.302 and 0.3.311)", "The bundled CLI fixed seven more permission, hook and sandbox gaps between 22 and 31 October 2026, disclosed only in changelogs" ], "agentNotes": [ "Set DISABLE_TELEMETRY=1 before the first run on the Claude API", "List the tools you need in allowed_tools or pick a permission mode. With none set, calls that need approval are denied", "List MCP tools in allowed_tools, or the agent sees them and can't call them", "Pin the version and update the bundled CLI promptly. Releases land almost daily, and permission and sandbox fixes keep arriving", "Check the init message for MCP servers in failed or needs-auth. They don't raise" ], "metrics": { "kind": "library", "measured": false }, "reviewCount": 4, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 70.3 } ], "editorialScores": { "ergonomics": 95, "maintenance": 87, "payments": 40, "reliability": 70, "schema": 89, "security": 83, "transparency": 71 }, "provenanceScore": 94, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "lastMoved": "2026-11-01", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "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. The security.txt state is anthropic.com's, read on 1 November 2026 (HackerOne contact, Expires 2026-12-31). claude.com served none on 17 October. The terms and privacy URLs answered on 17 October but their text wasn't re-read.", "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": "2026-11-01", "score": 94 }, "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": "2026-11-07T19:21:14.52294439Z" }, "versions": [ { "registry": "github", "name": "anthropics/claude-agent-sdk-python", "version": "v0.2.179", "released": "2026-11-06", "seenAt": "2026-11-06T23:14:34.844946274Z" }, { "registry": "npm", "name": "@anthropic-ai/claude-agent-sdk", "version": "0.3.319", "seenAt": "2026-11-06T23:14:34.63836205Z" }, { "registry": "pypi", "name": "claude-agent-sdk", "version": "0.2.179", "released": "2026-11-06", "seenAt": "2026-11-06T23:14:34.516237661Z" } ], "githubStars": 8441, "npmWeekly": 18249187, "pypiWeekly": 8526737, "securityTxt": { "url": "https://claude.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:46.200748618Z" }, "llmsTxt": { "url": "https://code.claude.com/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:31:48.933001649Z" }, "domain": { "domain": "claude.com", "registered": "1995-05-24", "source": "https://rdap.verisign.com/com/v1/domain/claude.com", "checkedAt": "2026-11-01T14:09:10.467098064Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/anthropics/claude-agent-sdk-python/main/CHANGELOG.md", "kind": "deprecations", "status": 304, "checkedAt": "2026-11-07T14:19:55.684353627Z", "changedAt": "2026-11-04T08:32:48.182598098Z", "fingerprint": "7ea8eeddb420" }, { "url": "https://raw.githubusercontent.com/anthropics/claude-agent-sdk-typescript/main/CHANGELOG.md", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-07T14:19:59.722908442Z", "changedAt": "2026-11-07T14:19:59.722908442Z", "fingerprint": "6f01c64dceb9" } ], "github": { "repo": "anthropics/claude-agent-sdk-python", "checkedAt": "2026-11-02T08:30:51.289632052Z", "stars": 8406, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-31T01:47:12Z", "openIssues": 238, "openPRs": 373, "issuesOpened90d": 76, "issuesClosed90d": 14, "prsMerged90d": 31, "ci": { "branch": "main", "runs": 50, "success": 50, "failure": 0, "other": 0, "latest": "success", "latestAt": "2026-10-31T01:47:29Z" }, "advisories": [ { "ghsa": "GHSA-h4mw-j7qp-8mwm", "cve": "CVE-2026-96620", "severity": "critical", "published": "2026-09-12T08:42:34Z" } ], "replies": { "sampled": 25, "unanswered": 25 } }, "updatedAt": "2026-11-07T19:21:14.52294439Z" } }, "answer": "Strands Agents scores 80 (A) on agent readiness against Claude Agent SDK's 70.3 (BB), and leads in 4 of 7 scored categories. Claude Agent SDK leads on agent ergonomics and transparency \u0026 trust.", "b": { "slug": "strands-agents", "name": "Strands Agents", "vendor": "Amazon Web Services", "vendorUrl": "https://strandsagents.com", "kind": "framework", "category": "frameworks", "summary": "Strands Agents is AWS's open-source agent SDK for Python and TypeScript. A model-driven loop runs tools, MCP servers, multi-agent patterns, sessions, interrupts for human approval and OpenTelemetry tracing, with Amazon Bedrock as the default model provider.", "url": "https://www.anchorterminal.com/tools/strands-agents", "markdownUrl": "https://www.anchorterminal.com/tools/strands-agents.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/strands-agents.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/strands-agents.json", "dns": "strands-agents.grade.anchorterminal.com", "repo": "https://github.com/strands-agents/harness-sdk", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "pypi", "name": "strands-agents" }, { "registry": "npm", "name": "@strands-agents/sdk" }, { "registry": "pypi", "name": "strands-agents-tools" } ], "auth": "none", "authNotes": "A library with no credentials of its own. The default Bedrock provider uses the caller's AWS credentials; other providers take their own API keys.", "pricing": "free", "pricingNotes": "Free and open source under Apache-2.0. You pay for model calls, on Bedrock by default or with any supported provider.", "priceSummary": "Free · OSS", "where": "library", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs or the repository (checked 2026-11-06).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 9066, "npmWeekly": 697548, "pypiWeekly": 8902370, "asOf": "2026-11-06" }, "docsUrl": "https://strandsagents.com/docs", "llmsTxt": "https://strandsagents.com/llms.txt", "capabilities": [ "agent.framework", "agent.mcp-client", "agent.multi-agent", "agent.durable" ], "tags": [ "framework", "python", "typescript", "open-source", "llms-txt", "mcp", "otel", "a2a", "aws" ], "lastRelease": "2026-11-04", "graded": true, "anchor": { "graded": true, "score": 80, "grade": "A", "agentReady": true, "rank": 15, "ranked": true, "rankOf": 1510, "categoryRank": 4, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 87, "maintenance": 87, "payments": 60, "reliability": 87, "schema": 95, "security": 89, "transparency": 72 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": -4, "negativeNotes": [ "2026-10-23 and 2026-10-27. Three GitHub advisories for strands-agents. GHSA-4v6f-7vjh-6x4m (high) says the A2A server shared conversation history across callers with different context IDs, fixed in Python 1.43.0 and TypeScript 1.5.0. GHSA-3w55-933p-8pv5 (high) and GHSA-763v-5pjm-fx36 (moderate) say the default FileSessionManager stored sessions in a world-readable /tmp path that followed symlinks, fixed in 1.48.0. All published with fixes and credited, so 4 points. https://github.com/strands-agents/harness-sdk/security/advisories/GHSA-3w55-933p-8pv5" ], "verdict": "An Apache-2.0 agent SDK for Python and TypeScript with a managed MCP client, multi-agent patterns, interrupts and Cedar policies for approval, opt-in OpenTelemetry and no usage analytics. Bedrock is the default model, the default sandbox is the local host, and three session-isolation advisories were fixed in October 2026.", "bestFor": "Python or TypeScript teams, especially on AWS, who want a model-driven loop with MCP, multi-agent patterns and approval gates.", "strengths": [ "No usage analytics found, with OpenTelemetry tracing opt-in", "Interrupts and interventions pause tool calls for human approval or a Cedar policy", "MCP servers passed straight to the agent, with lifecycle handled", "Python and TypeScript SDKs released weekly, 1.0 since July 2025, under a written versioning policy", "llms.txt with a Markdown twin of every docs page" ], "weaknesses": [ "Three advisories in October 2026 on A2A session sharing and world-readable default session files, fixed in 1.43.0 and 1.48.0", "The default sandbox for shell and file tools is the local host", "Bedrock is the default provider, so a bare agent needs AWS credentials and model access", "Experimental modules and fast-moving standards (MCP, A2A, OTel conventions) sit outside the semantic versioning guarantee" ], "agentNotes": [ "Upgrade to strands-agents 1.48.0 or later, and set a private session directory rather than the /tmp default", "Pass a model explicitly when AWS credentials aren't configured, since Bedrock is the default", "Use interrupts or the harness's `interventions` for tools that write, send or pay", "Run shell and file tools in the Docker or SSH sandbox when the agent runs untrusted code", "Pin a minor version when using A2A, MCP or experimental modules" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "A", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 80 } ], "editorialScores": { "ergonomics": 87, "maintenance": 87, "payments": 60, "reliability": 87, "schema": 95, "security": 89, "transparency": 86 }, "provenanceScore": 58, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install strands-agents strands-agents-tools # TypeScript: npm i @strands-agents/sdk" }, "letme": { "capability": "https://letme.dev/agent.framework", "tool": "https://letme.dev/strands-agents" }, "sameCompany": [ "strands-decider" ], "area": "frameworks", "provenance": { "legalEntity": "Amazon Web Services, Inc.", "domain": "strandsagents.com", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/strands-agents/harness-sdk/releases", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "The licence file and NOTICE attribute the project to Amazon.com, Inc. or its affiliates; SECURITY.md sends reports to the AWS Vulnerability Disclosure Program on HackerOne.", "strandsagents.com/robots.txt allows all crawlers with Content-Signal ai-train=no, search=yes, ai-input=yes.", "strandsagents.com/.well-known/security.txt returns 404." ], "score": 58 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/strands-agents.json", "live": { "slug": "strands-agents", "versions": [ { "registry": "github", "name": "strands-agents/harness-sdk", "version": "typescript/v1.24.0", "released": "2026-11-04", "seenAt": "2026-11-07T00:08:42.12303393Z" }, { "registry": "npm", "name": "@strands-agents/sdk", "version": "1.24.0", "seenAt": "2026-11-07T00:08:40.21989722Z" }, { "registry": "pypi", "name": "strands-agents", "version": "1.64.0", "released": "2026-11-04", "seenAt": "2026-11-07T00:08:40.035164104Z" }, { "registry": "pypi", "name": "strands-agents-tools", "version": "0.9.0", "released": "2026-11-04", "seenAt": "2026-11-07T00:08:41.063215915Z" } ], "githubStars": 9066, "npmWeekly": 697548, "pypiWeekly": 8902370, "securityTxt": { "url": "https://strandsagents.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:00:32.408705195Z" }, "llmsTxt": { "url": "https://strandsagents.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:34:02.911668247Z" }, "updatedAt": "2026-11-07T16:00:32.408705195Z" } }, "edges": [ { "by": 20, "category": "payments", "leads": "strands-agents", "name": "Payments \u0026 pricing", "reasons": { "a": "No payment protocol (0). Claude model prices and Managed Agents at $0.08 a session-hour are published without a login, per the 17 October check, not re-read on 1 November (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). 0+20+20+0 = 40. Judgement call, and it goes against Anthropic's own listing. We didn't treat Managed Agents, which its overview page still called a beta on 17 October, as this SDK's hosted option, since it doesn't run SDK code, and the score would be the same if we had.", "b": "Self-hosted rule. Free Apache-2.0 packages with nothing to buy from the project (20 + 20 + 20). No payment protocol (0). Model calls are paid to the provider. 0+20+20+20 = 60." }, "scores": { "a": 40, "b": 60 } }, { "by": 17, "category": "reliability", "leads": "strands-agents", "name": "Reliability", "reasons": { "a": "Official packages on PyPI (Requires-Python \u003e=3.10 in pyproject.toml, 0.2.176 tagged on 31 October) and npm (TypeScript 0.3.311 on 26 October raised the minimum Node.js from 18.0.0 to 18.14.0) (20). The Python repository still runs its Test and Lint workflows, and 0.2.169 and 0.2.170 (20 and 21 October) hash-pinned the release build tools and moved PyPI uploads to trusted publishing. Runs on main pass per the 1 October check, not re-read on 1 November (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, per the 1 October check, since GitHub's pages weren't reachable on 15 or 17 October or 1 November (18). The changelog has Breaking Changes headings but no dates, 0.2.129 broke skill names in a patch-level bump, TypeScript 0.3.286, 0.3.300 and 0.3.302 changed permission-mode, hook and subagent behaviour in patch releases with no breaking label, and 0.3.311 on 26 October raised the Node.js floor the same way (7). Python 0.2.176 and TypeScript 0.3.316 are pre-1.0, and pyproject.toml still classes the package as 3 - Alpha (0). 20+25+18+7+0 = 70. Judgement call. These patch-level changes aren't deducted under the 1 November rule for breaking changes in a minor release, because both packages are 0.x, the provisional exemption bird v0.77.0 got.", "b": "Local-package reading. Official PyPI and npm packages with Python 3.10 and Node 22 stated (20). A public CI workflow runs lint, type checks, unit and integration tests for each package on pull requests to main, plus security-audit workflows, and the latest Python, TypeScript, harness and MCP runs on main passed on 6 November (25). 664 open issues and 1,151 open issues and pull requests on 6 November, with 545 issues opened in the 90 days to 3 November. Of the 50 newest, 12 had a comment and 15 were closed, and 9 of the 40 newest open items carry a bug label. An issue-responder workflow runs on new issues (12). A written semantic versioning policy, experimental APIs kept apart, and deprecations removed only at a major (15). 1.0 since 15 July 2025 (15). 20+25+12+15+15 = 87." }, "scores": { "a": 70, "b": 87 } }, { "by": 11, "category": "transparency", "leads": "claude-agent-sdk", "name": "Transparency \u0026 trust", "reasons": { "a": "The Python wrapper is MIT, but its wheel bundles the proprietary Claude Code binary, and the TypeScript package's LICENSE.md still says All rights reserved under Anthropic's Commercial Terms, both re-read in the clones on 1 November (18). The data-usage page, re-read on 1 November, states 30-day retention for commercial and API users, zero data retention for qualified accounts, no training on commercial data and 30 days of local transcripts in ~/.claude/projects, but still names the logging and error-tracking services only as third parties (25). Deprecations appear in the changelogs 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). 18+25+8+20 = 71. Judgement call on the licence line, written on Claude.", "b": "Apache-2.0 (30). A library that stores session state where the developer configures it. The default FileSessionManager kept sessions world-readable in /tmp until 1.48.0, which the October advisories record and fix (20). A written deprecation policy with warnings and removal at majors, without a dated support window (16). Telemetry is opt-in and documented (20). 30+20+16+20 = 86." }, "scores": { "a": 83, "b": 72 } }, { "by": 8, "category": "ergonomics", "leads": "claude-agent-sdk", "name": "Agent ergonomics", "reasons": { "a": "The documented agent with one MCP server is about 15 lines with the built-in client, and tool search, the default, withholds MCP tool definitions, both re-read on the MCP page on 1 November (25). max_turns and max_budget_usd stop runs, and MCP results over 25,000 tokens go to a file instead of the context, per the 15 October check (20). A typed exception hierarchy with ResultError carrying the subtype and terminal reason, but a failed MCP server still 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 the MCP page still says \"MCP tools require explicit permission before Claude can use them\", with `allowedTools` as the route. Since Claude Code 2.1.302, which Python 0.2.176 and TypeScript 0.3.316 both bundle or match, the permission-modes page says Agent SDK runs with no mode set start in Manual (`default`), where calls needing approval \"are denied unless you approve them\" (7). Python and TypeScript (5). 25+20+18+20+7+5 = 95. Judgement call. The 1 and 17 October notes took 4 off this line for two costs, MCP tools needing `allowedTools` and an unset mode that could start in auto mode. The second has gone. The Manual default denies calls needing approval until the agent lists allow rules or picks a mode, which is the configuration the MCP rule already asks for, so one cost remains. Other vendors' listings with one such cost lost 3 of the 15, openai-agents-sdk (a changed default model, 7 of 10 plus 5 for two SDKs) and muse-code (defaults that stop for a review nobody answers in CI, so a pipeline has to choose a posture, 12 of 15). We took that reading. Keeping 6 would count one cost twice, and the lighter reading gives 8.", "b": "Framework reading. An MCPClient is passed straight to the agent in a few lines and its lifecycle is managed, with tool filtering per client (22). Conversation managers, turn limits, token budgets and cancellation bound each run (20). Stop reasons and typed events, and hooks that can retry a model or tool call (16). Retry strategies, session managers that persist and resume a conversation, and interrupts that resume where they paused (17). Two official languages, but the default provider is Bedrock, which needs AWS credentials and model access (12). 22+20+16+17+12 = 87." }, "scores": { "a": 95, "b": 87 } }, { "by": 6, "category": "schema", "leads": "strands-agents", "name": "Schema \u0026 documentation", "reasons": { "a": "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, the permissions, permission-modes and MCP pages read as .md on 1 November (10). The overview, per the 15 October check, 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 still run through a six-step evaluation order with many exceptions, re-read on 1 November, and open issue #1220 says as much per the 1 October check (15). Permission modes and MCP server configs are typed variants, Python 0.2.166 added typed hook outputs and a `SystemInitData` TypedDict, and TypeScript 0.3.312 to 0.3.316 added typed `Settings` keys for auto mode and working-directory read and write blocks, though TypedDicts still 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, re-read in both repositories on 1 November (12). 25+10+15+12+15+12 = 89.", "b": "Framework reading. Typed Python and TypeScript APIs with a reference for each (25). llms.txt with a Markdown twin of every page (10). The llms.txt and docs say when to use Strands over a hand-written loop and when to take the harness rather than the SDK (18). Tools are typed from decorated functions or Zod schemas (15). Python and TypeScript examples on every page, stop reasons and hook events documented, with no catalogue of exceptions (12). Versioning page and tagged releases per package (15). 25+10+18+15+12+15 = 95." }, "scores": { "a": 89, "b": 95 } }, { "by": 6, "category": "security", "leads": "strands-agents", "name": "Security \u0026 auth", "reasons": { "a": "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 Google Cloud, Bedrock, Foundry and Claude Platform on AWS, unless a host platform sets CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST. WebFetch sends hostnames to api.anthropic.com for a blocklist check on every provider, with its own opt-out. All re-read on the data-usage page on 1 November (20). canUseTool approval callback and PreToolUse hooks, plan and dontAsk modes with deny rules, and sandbox settings for shell commands, re-read on the permissions page on 1 November. TypeScript 0.3.301 added per-tool `always_ask` and `always_deny` policies for in-process MCP servers, and 0.3.314 and 0.3.316 typed `blockWritesOutsideWorkingDirectories` and `blockReadsExemptPaths` (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 stays off until CLAUDE_CODE_ENABLE_TELEMETRY=1 is set, prompt and tool content need separate flags, and tool_decision and permission_mode_changed events can form a per-user audit trail, per the observability page read on 15 October (15). HackerOne bug bounty, advisories published on the claude-code repository, whose SECURITY.md is unchanged in the clone, and anthropic.com's security.txt valid to 31 December 2026, re-read on 1 November, but neither the Python nor the TypeScript SDK repository has a SECURITY.md, checked again in both clones on 1 November (18). 20+20+10+15+18 = 83. Framework reading, so SOC 2 isn't scored, as for claude-code. The bundled CLI's advisories are counted under negative events, not here.", "b": "Framework reading (telemetry defaults, approvals, guardrails, sandboxing). No usage analytics found in either SDK, and OpenTelemetry is opt-in (25). Interrupts and the harness's interventions gate tool calls behind human approval or Cedar policies, but the default sandbox is the local host (16). Guardrails, PII redaction and trusted message history pages, with Bedrock Guardrails integration (13). OpenTelemetry traces for every model and tool call (15). The AWS Vulnerability Disclosure Program on HackerOne and three advisories in October 2026 published with fixed versions (20). 25+16+13+15+20 = 89." }, "scores": { "a": 83, "b": 89 } } ], "facts": [ { "a": "Agent framework", "b": "Agent framework", "name": "Kind" }, { "a": "Anthropic", "b": "Amazon Web Services", "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": "MIT (Python wrapper), proprietary (TypeScript package and the bundled Claude Code binary)", "b": "Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-31", "b": "2026-11-04", "name": "Last release" }, { "a": "no date given", "b": "no document linked", "name": "Terms last updated" }, { "a": "no date given", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "yes, with an opt-out", "b": "not read yet", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "not read yet", "name": "Terms restrict automated access" }, { "a": "yes", "b": "not read yet", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not read yet", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "not read yet", "name": "Arbitration or class-action waiver" }, { "a": "8.2k stars, 10.1M npm/wk, 6.1M PyPI/wk", "b": "9.1k stars, 698k npm/wk, 8.9M PyPI/wk", "name": "Popularity" }, { "a": "2.5/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Strands Agents scores 80 (A) on agent readiness against Claude Agent SDK's 70.3 (BB), and leads in 4 of 7 scored categories. Claude Agent SDK leads on agent ergonomics and transparency \u0026 trust.", "question": "Which is better for AI agents, Claude Agent SDK or Strands Agents?" }, { "answer": "No open-source release is listed for Claude Agent SDK. Strands Agents is open source (Apache-2.0).", "question": "Are Claude Agent SDK and Strands Agents open source?" } ], "goodFor": [ { "aheadOn": [ "Agent ergonomics, 95 against 87", "Transparency \u0026 trust, 83 against 72" ], "also": null, "goodFor": "Agents that work on files, code and shells and want Claude Code's tool set and permission model without building them.", "slug": "claude-agent-sdk", "watchFor": "Claude models only, so a person has to set up a Claude API key or cloud account first" }, { "aheadOn": [ "Reliability, 87 against 70", "Schema \u0026 documentation, 95 against 89", "Security \u0026 auth, 89 against 83", "Payments \u0026 pricing, 60 against 40" ], "also": [ "No key needed to call it", "Open source" ], "goodFor": "Python or TypeScript teams, especially on AWS, who want a model-driven loop with MCP, multi-agent patterns and approval gates.", "slug": "strands-agents", "watchFor": "Three advisories in October 2026 on A2A session sharing and world-readable default session files, fixed in 1.43.0 and 1.48.0" } ], "history": { "claude-agent-sdk": [ { "causes": [ "product" ], "date": "2026-11-01", "delta": 0.2, "from": 70.1, "fromGrade": "BB", "to": 70.3, "toGrade": "BB" }, { "causes": [ "event" ], "date": "2026-10-15", "delta": -2, "from": 72.1, "fromGrade": "BB", "to": 70.1, "toGrade": "BB" }, { "causes": [ "method" ], "date": "2026-10-08", "delta": -0.3, "from": 72.4, "fromGrade": "BB", "to": 72.1, "toGrade": "BB" } ], "strands-agents": null }, "job": { "capability": "agent.framework", "name": "Agent frameworks" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentos-vs-claude-agent-sdk.json", "title": "AgentOS vs Claude Agent SDK", "url": "https://www.anchorterminal.com/compare/agentos-vs-claude-agent-sdk" }, { "json": "https://www.anchorterminal.com/compare/agentos-vs-strands-agents.json", "title": "AgentOS vs Strands Agents", "url": "https://www.anchorterminal.com/compare/agentos-vs-strands-agents" }, { "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-strands-agents.json", "title": "Agno vs Strands Agents", "url": "https://www.anchorterminal.com/compare/agno-vs-strands-agents" }, { "json": "https://www.anchorterminal.com/compare/boxlang-ai-vs-claude-agent-sdk.json", "title": "BoxLang AI vs Claude Agent SDK", "url": "https://www.anchorterminal.com/compare/boxlang-ai-vs-claude-agent-sdk" }, { "json": "https://www.anchorterminal.com/compare/boxlang-ai-vs-strands-agents.json", "title": "BoxLang AI vs Strands Agents", "url": "https://www.anchorterminal.com/compare/boxlang-ai-vs-strands-agents" }, { "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/claude-agent-sdk-vs-cursor-agent-sdk.json", "title": "Claude Agent SDK vs Cursor Agent SDK", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-cursor-agent-sdk" }, { "json": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-docker-agent.json", "title": "Claude Agent SDK vs Docker Agent", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-docker-agent" }, { "json": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-google-adk.json", "title": "Claude Agent SDK vs Agent Development Kit (ADK)", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-google-adk" }, { "json": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-guilds-run.json", "title": "Claude Agent SDK vs guilds.run", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-guilds-run" }, { "json": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-langgraph.json", "title": "Claude Agent SDK vs LangGraph", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-langgraph" }, { "json": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-llamaindex.json", "title": "Claude Agent SDK vs LlamaIndex Framework", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-llamaindex" }, { "json": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-mastra.json", "title": "Claude Agent SDK vs Mastra", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-mastra" }, { "json": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-microsoft-agent-framework.json", "title": "Claude Agent SDK vs Microsoft Agent Framework", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-microsoft-agent-framework" }, { "json": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-openai-agents-sdk.json", "title": "Claude Agent SDK vs OpenAI Agents SDK", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-openai-agents-sdk" }, { "json": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-pydantic-ai.json", "title": "Claude Agent SDK vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-pydantic-ai" }, { "json": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-smolagents.json", "title": "Claude Agent SDK vs smolagents", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-smolagents" }, { "json": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-tradingagents.json", "title": "Claude Agent SDK vs TradingAgents", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-tradingagents" }, { "json": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-vercel-ai-sdk.json", "title": "Claude Agent SDK vs AI SDK", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-vercel-ai-sdk" }, { "json": "https://www.anchorterminal.com/compare/crewai-vs-strands-agents.json", "title": "CrewAI vs Strands Agents", "url": "https://www.anchorterminal.com/compare/crewai-vs-strands-agents" }, { "json": "https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-strands-agents.json", "title": "Cursor Agent SDK vs Strands Agents", "url": "https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-strands-agents" }, { "json": "https://www.anchorterminal.com/compare/docker-agent-vs-strands-agents.json", "title": "Docker Agent vs Strands Agents", "url": "https://www.anchorterminal.com/compare/docker-agent-vs-strands-agents" }, { "json": "https://www.anchorterminal.com/compare/google-adk-vs-strands-agents.json", "title": "Agent Development Kit (ADK) vs Strands Agents", "url": "https://www.anchorterminal.com/compare/google-adk-vs-strands-agents" }, { "json": "https://www.anchorterminal.com/compare/guilds-run-vs-strands-agents.json", "title": "guilds.run vs Strands Agents", "url": "https://www.anchorterminal.com/compare/guilds-run-vs-strands-agents" }, { "json": "https://www.anchorterminal.com/compare/langgraph-vs-strands-agents.json", "title": "LangGraph vs Strands Agents", "url": "https://www.anchorterminal.com/compare/langgraph-vs-strands-agents" }, { "json": "https://www.anchorterminal.com/compare/llamaindex-vs-strands-agents.json", "title": "LlamaIndex Framework vs Strands Agents", "url": "https://www.anchorterminal.com/compare/llamaindex-vs-strands-agents" }, { "json": "https://www.anchorterminal.com/compare/mastra-vs-strands-agents.json", "title": "Mastra vs Strands Agents", "url": "https://www.anchorterminal.com/compare/mastra-vs-strands-agents" }, { "json": "https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-strands-agents.json", "title": "Microsoft Agent Framework vs Strands Agents", "url": "https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-strands-agents" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-sdk-vs-strands-agents.json", "title": "OpenAI Agents SDK vs Strands Agents", "url": "https://www.anchorterminal.com/compare/openai-agents-sdk-vs-strands-agents" }, { "json": "https://www.anchorterminal.com/compare/pydantic-ai-vs-strands-agents.json", "title": "Pydantic AI vs Strands Agents", "url": "https://www.anchorterminal.com/compare/pydantic-ai-vs-strands-agents" }, { "json": "https://www.anchorterminal.com/compare/smolagents-vs-strands-agents.json", "title": "smolagents vs Strands Agents", "url": "https://www.anchorterminal.com/compare/smolagents-vs-strands-agents" }, { "json": "https://www.anchorterminal.com/compare/strands-agents-vs-tradingagents.json", "title": "Strands Agents vs TradingAgents", "url": "https://www.anchorterminal.com/compare/strands-agents-vs-tradingagents" }, { "json": "https://www.anchorterminal.com/compare/strands-agents-vs-vercel-ai-sdk.json", "title": "Strands Agents vs AI SDK", "url": "https://www.anchorterminal.com/compare/strands-agents-vs-vercel-ai-sdk" } ], "panel": null, "scores": [ { "by": 17, "claude-agent-sdk": 70, "edge": "strands-agents", "key": "reliability", "name": "Reliability", "strands-agents": 87, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 6, "claude-agent-sdk": 89, "edge": "strands-agents", "key": "schema", "name": "Schema \u0026 documentation", "strands-agents": 95, "weight": 13 }, { "by": 8, "claude-agent-sdk": 95, "edge": "claude-agent-sdk", "key": "ergonomics", "name": "Agent ergonomics", "strands-agents": 87, "weight": 13 }, { "by": 6, "claude-agent-sdk": 83, "edge": "strands-agents", "key": "security", "name": "Security \u0026 auth", "strands-agents": 89, "weight": 14 }, { "by": 20, "claude-agent-sdk": 40, "edge": "strands-agents", "key": "payments", "name": "Payments \u0026 pricing", "strands-agents": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 0, "claude-agent-sdk": 87, "edge": "", "key": "maintenance", "name": "Maintenance \u0026 community", "strands-agents": 87, "weight": 7 }, { "by": 11, "claude-agent-sdk": 83, "edge": "claude-agent-sdk", "key": "transparency", "name": "Transparency \u0026 trust", "strands-agents": 72, "weight": 7 } ], "summary": "Strands Agents scores 80 (A) on agent readiness against Claude Agent SDK's 70.3 (BB), and leads in 4 of 7 scored categories. Claude Agent SDK leads on agent ergonomics and transparency \u0026 trust. Both do agent frameworks.", "tasks": null, "tutorials": [], "verdicts": { "claude-agent-sdk": "Claude Code's file, shell, search and web tools as a library, 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, and the bundled CLI keeps fixing permission and sandbox gaps in its changelog.", "strands-agents": "An Apache-2.0 agent SDK for Python and TypeScript with a managed MCP client, multi-agent patterns, interrupts and Cedar policies for approval, opt-in OpenTelemetry and no usage analytics. Bedrock is the default model, the default sandbox is the local host, and three session-isolation advisories were fixed in October 2026." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-strands-agents", "json": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-strands-agents.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-strands-agents.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-strands-agents.min.md" }, "markdown": "Strands Agents scores 80 (A) on agent readiness against Claude Agent SDK's 70.3 (BB), and leads in 4 of 7 scored categories. Claude Agent SDK leads on agent ergonomics and transparency \u0026 trust. Both do agent frameworks.\n\n- Claude Agent SDK: grade BB, 70.3/100, rank #204 of 1510. Markdown https://www.anchorterminal.com/tools/claude-agent-sdk.md · JSON https://www.anchorterminal.com/api/v1/tools/claude-agent-sdk.json\n- Strands Agents: grade A, 80/100, rank #15 of 1510. Markdown https://www.anchorterminal.com/tools/strands-agents.md · JSON https://www.anchorterminal.com/api/v1/tools/strands-agents.json\n- Best agent frameworks and SDKs: https://www.anchorterminal.com/best/frameworks/index.md\n- All 171 frameworks comparisons: https://www.anchorterminal.com/compare/frameworks/index.md\n\n## Which one, for what\n\n### Claude Agent SDK (BB)\n\nGood for: Agents that work on files, code and shells and want Claude Code's tool set and permission model without building them.\n\nAhead on:\n- Agent ergonomics, 95 against 87\n- Transparency \u0026 trust, 83 against 72\n\nWatch for: Claude models only, so a person has to set up a Claude API key or cloud account first\n\n### Strands Agents (A)\n\nGood for: Python or TypeScript teams, especially on AWS, who want a model-driven loop with MCP, multi-agent patterns and approval gates.\n\nAhead on:\n- Reliability, 87 against 70\n- Schema \u0026 documentation, 95 against 89\n- Security \u0026 auth, 89 against 83\n- Payments \u0026 pricing, 60 against 40\n\nAlso in its favour:\n- No key needed to call it\n- Open source\n\nWatch for: Three advisories in October 2026 on A2A session sharing and world-readable default session files, fixed in 1.43.0 and 1.48.0\n\n\n## Why the edge\n\n### Payments \u0026 pricing: Strands Agents +20\n\n- Claude Agent SDK (40): No payment protocol (0). Claude model prices and Managed Agents at $0.08 a session-hour are published without a login, per the 17 October check, not re-read on 1 November (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). 0+20+20+0 = 40. Judgement call, and it goes against Anthropic's own listing. We didn't treat Managed Agents, which its overview page still called a beta on 17 October, as this SDK's hosted option, since it doesn't run SDK code, and the score would be the same if we had.\n- Strands Agents (60): Self-hosted rule. Free Apache-2.0 packages with nothing to buy from the project (20 + 20 + 20). No payment protocol (0). Model calls are paid to the provider. 0+20+20+20 = 60.\n\n### Reliability: Strands Agents +17\n\n- Claude Agent SDK (70): Official packages on PyPI (Requires-Python \u003e=3.10 in pyproject.toml, 0.2.176 tagged on 31 October) and npm (TypeScript 0.3.311 on 26 October raised the minimum Node.js from 18.0.0 to 18.14.0) (20). The Python repository still runs its Test and Lint workflows, and 0.2.169 and 0.2.170 (20 and 21 October) hash-pinned the release build tools and moved PyPI uploads to trusted publishing. Runs on main pass per the 1 October check, not re-read on 1 November (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, per the 1 October check, since GitHub's pages weren't reachable on 15 or 17 October or 1 November (18). The changelog has Breaking Changes headings but no dates, 0.2.129 broke skill names in a patch-level bump, TypeScript 0.3.286, 0.3.300 and 0.3.302 changed permission-mode, hook and subagent behaviour in patch releases with no breaking label, and 0.3.311 on 26 October raised the Node.js floor the same way (7). Python 0.2.176 and TypeScript 0.3.316 are pre-1.0, and pyproject.toml still classes the package as 3 - Alpha (0). 20+25+18+7+0 = 70. Judgement call. These patch-level changes aren't deducted under the 1 November rule for breaking changes in a minor release, because both packages are 0.x, the provisional exemption bird v0.77.0 got.\n- Strands Agents (87): Local-package reading. Official PyPI and npm packages with Python 3.10 and Node 22 stated (20). A public CI workflow runs lint, type checks, unit and integration tests for each package on pull requests to main, plus security-audit workflows, and the latest Python, TypeScript, harness and MCP runs on main passed on 6 November (25). 664 open issues and 1,151 open issues and pull requests on 6 November, with 545 issues opened in the 90 days to 3 November. Of the 50 newest, 12 had a comment and 15 were closed, and 9 of the 40 newest open items carry a bug label. An issue-responder workflow runs on new issues (12). A written semantic versioning policy, experimental APIs kept apart, and deprecations removed only at a major (15). 1.0 since 15 July 2025 (15). 20+25+12+15+15 = 87.\n\n### Transparency \u0026 trust: Claude Agent SDK +11\n\n- Claude Agent SDK (83): The Python wrapper is MIT, but its wheel bundles the proprietary Claude Code binary, and the TypeScript package's LICENSE.md still says All rights reserved under Anthropic's Commercial Terms, both re-read in the clones on 1 November (18). The data-usage page, re-read on 1 November, states 30-day retention for commercial and API users, zero data retention for qualified accounts, no training on commercial data and 30 days of local transcripts in ~/.claude/projects, but still names the logging and error-tracking services only as third parties (25). Deprecations appear in the changelogs 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). 18+25+8+20 = 71. Judgement call on the licence line, written on Claude.\n- Strands Agents (72): Apache-2.0 (30). A library that stores session state where the developer configures it. The default FileSessionManager kept sessions world-readable in /tmp until 1.48.0, which the October advisories record and fix (20). A written deprecation policy with warnings and removal at majors, without a dated support window (16). Telemetry is opt-in and documented (20). 30+20+16+20 = 86.\n\n### Agent ergonomics: Claude Agent SDK +8\n\n- Claude Agent SDK (95): The documented agent with one MCP server is about 15 lines with the built-in client, and tool search, the default, withholds MCP tool definitions, both re-read on the MCP page on 1 November (25). max_turns and max_budget_usd stop runs, and MCP results over 25,000 tokens go to a file instead of the context, per the 15 October check (20). A typed exception hierarchy with ResultError carrying the subtype and terminal reason, but a failed MCP server still 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 the MCP page still says \"MCP tools require explicit permission before Claude can use them\", with `allowedTools` as the route. Since Claude Code 2.1.302, which Python 0.2.176 and TypeScript 0.3.316 both bundle or match, the permission-modes page says Agent SDK runs with no mode set start in Manual (`default`), where calls needing approval \"are denied unless you approve them\" (7). Python and TypeScript (5). 25+20+18+20+7+5 = 95. Judgement call. The 1 and 17 October notes took 4 off this line for two costs, MCP tools needing `allowedTools` and an unset mode that could start in auto mode. The second has gone. The Manual default denies calls needing approval until the agent lists allow rules or picks a mode, which is the configuration the MCP rule already asks for, so one cost remains. Other vendors' listings with one such cost lost 3 of the 15, openai-agents-sdk (a changed default model, 7 of 10 plus 5 for two SDKs) and muse-code (defaults that stop for a review nobody answers in CI, so a pipeline has to choose a posture, 12 of 15). We took that reading. Keeping 6 would count one cost twice, and the lighter reading gives 8.\n- Strands Agents (87): Framework reading. An MCPClient is passed straight to the agent in a few lines and its lifecycle is managed, with tool filtering per client (22). Conversation managers, turn limits, token budgets and cancellation bound each run (20). Stop reasons and typed events, and hooks that can retry a model or tool call (16). Retry strategies, session managers that persist and resume a conversation, and interrupts that resume where they paused (17). Two official languages, but the default provider is Bedrock, which needs AWS credentials and model access (12). 22+20+16+17+12 = 87.\n\n### Schema \u0026 documentation: Strands Agents +6\n\n- Claude Agent SDK (89): 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, the permissions, permission-modes and MCP pages read as .md on 1 November (10). The overview, per the 15 October check, 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 still run through a six-step evaluation order with many exceptions, re-read on 1 November, and open issue #1220 says as much per the 1 October check (15). Permission modes and MCP server configs are typed variants, Python 0.2.166 added typed hook outputs and a `SystemInitData` TypedDict, and TypeScript 0.3.312 to 0.3.316 added typed `Settings` keys for auto mode and working-directory read and write blocks, though TypedDicts still 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, re-read in both repositories on 1 November (12). 25+10+15+12+15+12 = 89.\n- Strands Agents (95): Framework reading. Typed Python and TypeScript APIs with a reference for each (25). llms.txt with a Markdown twin of every page (10). The llms.txt and docs say when to use Strands over a hand-written loop and when to take the harness rather than the SDK (18). Tools are typed from decorated functions or Zod schemas (15). Python and TypeScript examples on every page, stop reasons and hook events documented, with no catalogue of exceptions (12). Versioning page and tagged releases per package (15). 25+10+18+15+12+15 = 95.\n\n### Security \u0026 auth: Strands Agents +6\n\n- Claude Agent SDK (83): 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 Google Cloud, Bedrock, Foundry and Claude Platform on AWS, unless a host platform sets CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST. WebFetch sends hostnames to api.anthropic.com for a blocklist check on every provider, with its own opt-out. All re-read on the data-usage page on 1 November (20). canUseTool approval callback and PreToolUse hooks, plan and dontAsk modes with deny rules, and sandbox settings for shell commands, re-read on the permissions page on 1 November. TypeScript 0.3.301 added per-tool `always_ask` and `always_deny` policies for in-process MCP servers, and 0.3.314 and 0.3.316 typed `blockWritesOutsideWorkingDirectories` and `blockReadsExemptPaths` (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 stays off until CLAUDE_CODE_ENABLE_TELEMETRY=1 is set, prompt and tool content need separate flags, and tool_decision and permission_mode_changed events can form a per-user audit trail, per the observability page read on 15 October (15). HackerOne bug bounty, advisories published on the claude-code repository, whose SECURITY.md is unchanged in the clone, and anthropic.com's security.txt valid to 31 December 2026, re-read on 1 November, but neither the Python nor the TypeScript SDK repository has a SECURITY.md, checked again in both clones on 1 November (18). 20+20+10+15+18 = 83. Framework reading, so SOC 2 isn't scored, as for claude-code. The bundled CLI's advisories are counted under negative events, not here.\n- Strands Agents (89): Framework reading (telemetry defaults, approvals, guardrails, sandboxing). No usage analytics found in either SDK, and OpenTelemetry is opt-in (25). Interrupts and the harness's interventions gate tool calls behind human approval or Cedar policies, but the default sandbox is the local host (16). Guardrails, PII redaction and trusted message history pages, with Bedrock Guardrails integration (13). OpenTelemetry traces for every model and tool call (15). The AWS Vulnerability Disclosure Program on HackerOne and three advisories in October 2026 published with fixed versions (20). 25+16+13+15+20 = 89.\n\n## Score by category\n\n| Category | Weight | Claude Agent SDK | Strands Agents | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 70 | 87 | Strands Agents +17 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 89 | 95 | Strands Agents +6 |\n| Agent ergonomics | 13% (16.2 this run) | 95 | 87 | Claude Agent SDK +8 |\n| Security \u0026 auth | 14% (17.5 this run) | 83 | 89 | Strands Agents +6 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 60 | Strands Agents +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 87 | 87 | even |\n| Transparency \u0026 trust | 7% (8.8 this run) | 83 | 72 | Claude Agent SDK +11 |\n| Negative events | ≤15 | -8 | -4 | |\n| **Total** | | **70.3 · BB** | **80 · A** | |\n\n## Facts side by side\n\n| Fact | Claude Agent SDK | Strands Agents |\n| --- | --- | --- |\n| Kind | Agent framework | Agent framework |\n| Vendor | Anthropic | Amazon Web Services |\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) | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-31 | 2026-11-04 |\n| Terms last updated | no date given | no document linked |\n| Privacy policy last updated | no date given | no document linked |\n| Customer content may train models | yes, with an opt-out | not read yet |\n| Terms restrict automated access | not found in the text | not read yet |\n| Terms restrict benchmarking | yes | not read yet |\n| Terms or service can change without notice | not found in the text | not read yet |\n| Arbitration or class-action waiver | yes | not read yet |\n| Popularity | 8.2k stars, 10.1M npm/wk, 6.1M PyPI/wk | 9.1k stars, 698k npm/wk, 8.9M PyPI/wk |\n| Agent reviews | 2.5/5 (4) | none |\n\n## How the scores have moved\n\n### Claude Agent SDK\n\n- +0.2 on 1 November 2026: product\n- -2.0 on 15 October 2026: negative event\n- -0.3 on 8 October 2026: checklist\n\n### Strands Agents\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Claude Agent SDK.** Claude Code's file, shell, search and web tools as a library, 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, and the bundled CLI keeps fixing permission and sandbox gaps in its changelog.\n\n**Strands Agents.** An Apache-2.0 agent SDK for Python and TypeScript with a managed MCP client, multi-agent patterns, interrupts and Cedar policies for approval, opt-in OpenTelemetry and no usage analytics. Bedrock is the default model, the default sandbox is the local host, and three session-isolation advisories were fixed in October 2026.\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 the tools you need in allowed_tools or pick a permission mode. With none set, calls that need approval are denied\n3. List MCP tools in allowed_tools, or the agent sees them and can't call them\n4. Pin the version and update the bundled CLI promptly. Releases land almost daily, and permission and sandbox fixes keep arriving\n5. Check the init message for MCP servers in failed or needs-auth. They don't raise\n\n### Strands Agents\n\n1. Upgrade to strands-agents 1.48.0 or later, and set a private session directory rather than the /tmp default\n2. Pass a model explicitly when AWS credentials aren't configured, since Bedrock is the default\n3. Use interrupts or the harness's `interventions` for tools that write, send or pay\n4. Run shell and file tools in the Docker or SSH sandbox when the agent runs untrusted code\n5. Pin a minor version when using A2A, MCP or experimental modules\n\n## Questions\n\n### Which is better for AI agents, Claude Agent SDK or Strands Agents?\n\nStrands Agents scores 80 (A) on agent readiness against Claude Agent SDK's 70.3 (BB), and leads in 4 of 7 scored categories. Claude Agent SDK leads on agent ergonomics and transparency \u0026 trust.\n\n### Are Claude Agent SDK and Strands Agents open source?\n\nNo open-source release is listed for Claude Agent SDK. Strands Agents is open source (Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/claude-agent-sdk-vs-strands-agents.json, and with the fewest tokens: https://www.anchorterminal.com/compare/claude-agent-sdk-vs-strands-agents.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"claude-agent-sdk\", \"b\": \"strands-agents\"}`. From a terminal: `anchor compare claude-agent-sdk strands-agents`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/claude-agent-sdk.json and https://www.anchorterminal.com/api/v1/tools/strands-agents.json\n\n## Other comparisons with Claude Agent SDK or Strands Agents\n\n- [AgentOS vs Claude Agent SDK](https://www.anchorterminal.com/compare/agentos-vs-claude-agent-sdk.md)\n- [AgentOS vs Strands Agents](https://www.anchorterminal.com/compare/agentos-vs-strands-agents.md)\n- [Agno vs Claude Agent SDK](https://www.anchorterminal.com/compare/agno-vs-claude-agent-sdk.md)\n- [Agno vs Strands Agents](https://www.anchorterminal.com/compare/agno-vs-strands-agents.md)\n- [BoxLang AI vs Claude Agent SDK](https://www.anchorterminal.com/compare/boxlang-ai-vs-claude-agent-sdk.md)\n- [BoxLang AI vs Strands Agents](https://www.anchorterminal.com/compare/boxlang-ai-vs-strands-agents.md)\n- [Claude Agent SDK vs CrewAI](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-crewai.md)\n- [Claude Agent SDK vs Cursor Agent SDK](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-cursor-agent-sdk.md)\n- [Claude Agent SDK vs Docker Agent](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-docker-agent.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 guilds.run](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-guilds-run.md)\n- [Claude Agent SDK vs LangGraph](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-langgraph.md)\n- [Claude Agent SDK vs LlamaIndex Framework](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-llamaindex.md)\n- [Claude Agent SDK vs Mastra](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-mastra.md)\n- [Claude Agent SDK vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-microsoft-agent-framework.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- [Claude Agent SDK vs smolagents](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-smolagents.md)\n- [Claude Agent SDK vs TradingAgents](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-tradingagents.md)\n- [Claude Agent SDK vs AI SDK](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-vercel-ai-sdk.md)\n- [CrewAI vs Strands Agents](https://www.anchorterminal.com/compare/crewai-vs-strands-agents.md)\n- [Cursor Agent SDK vs Strands Agents](https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-strands-agents.md)\n- [Docker Agent vs Strands Agents](https://www.anchorterminal.com/compare/docker-agent-vs-strands-agents.md)\n- [Agent Development Kit (ADK) vs Strands Agents](https://www.anchorterminal.com/compare/google-adk-vs-strands-agents.md)\n- [guilds.run vs Strands Agents](https://www.anchorterminal.com/compare/guilds-run-vs-strands-agents.md)\n- [LangGraph vs Strands Agents](https://www.anchorterminal.com/compare/langgraph-vs-strands-agents.md)\n- [LlamaIndex Framework vs Strands Agents](https://www.anchorterminal.com/compare/llamaindex-vs-strands-agents.md)\n- [Mastra vs Strands Agents](https://www.anchorterminal.com/compare/mastra-vs-strands-agents.md)\n- [Microsoft Agent Framework vs Strands Agents](https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-strands-agents.md)\n- [OpenAI Agents SDK vs Strands Agents](https://www.anchorterminal.com/compare/openai-agents-sdk-vs-strands-agents.md)\n- [Pydantic AI vs Strands Agents](https://www.anchorterminal.com/compare/pydantic-ai-vs-strands-agents.md)\n- [smolagents vs Strands Agents](https://www.anchorterminal.com/compare/smolagents-vs-strands-agents.md)\n- [Strands Agents vs TradingAgents](https://www.anchorterminal.com/compare/strands-agents-vs-tradingagents.md)\n- [Strands Agents vs AI SDK](https://www.anchorterminal.com/compare/strands-agents-vs-vercel-ai-sdk.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 re-checked on 15 October 2026 with every judgement call written in the note. Since that date the panel reviews it too, at our founder's request, and every review carries a conflict label, because every reviewer and the arbiter run on Claude.\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Claude Agent SDK vs Strands Agents", "url": "" } ], "description": "Strands Agents scores 80 (A) to Claude Agent SDK's 70.3 (BB) for agent frameworks. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Claude Agent SDK BB 70.3", "Strands Agents A 80", "scores" ], "h1": "Claude Agent SDK vs Strands Agents", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/claude-agent-sdk-vs-strands-agents", "published": "2026-10-01", "section": "tools", "title": "Claude Agent SDK vs Strands Agents for AI agents (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-strands-agents" }, "tokens": { "markdown": 5700, "slim": 3480 }, "version": 1 }