{ "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": "Claude Agent SDK and LlamaIndex Framework score within a point of each other on agent readiness, 70.3 (BB) and 70 (BB). LlamaIndex Framework leads on payments \u0026 pricing.", "b": { "slug": "llamaindex", "name": "LlamaIndex Framework", "vendor": "LlamaIndex", "vendorUrl": "https://developers.llamaindex.ai/python/framework/", "kind": "framework", "category": "frameworks", "summary": "The LlamaIndex Framework is LlamaIndex's open-source Python toolkit for retrieval and agents, with FunctionAgent, ReActAgent and CodeActAgent, multi-agent AgentWorkflow, event-driven Workflows, MCP tools and hundreds of integration packages.", "url": "https://www.anchorterminal.com/tools/llamaindex", "markdownUrl": "https://www.anchorterminal.com/tools/llamaindex.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/llamaindex.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/llamaindex.json", "dns": "llamaindex.grade.anchorterminal.com", "repo": "https://github.com/run-llama/llama_index", "license": "MIT", "transports": [], "packages": [ { "registry": "pypi", "name": "llama-index" }, { "registry": "pypi", "name": "llama-index-core" }, { "registry": "pypi", "name": "llama-index-workflows" }, { "registry": "pypi", "name": "llama-index-tools-mcp" } ], "auth": "none", "authNotes": "A library with no credentials of its own. The default LLM and embeddings are OpenAI's and read an OpenAI key; integrations take their own keys.", "pricing": "free", "pricingNotes": "Free and open source under MIT. You pay for model calls. LlamaParse and LlamaCloud are separate paid services with their own Anchor Terminal listing.", "priceSummary": "Free · OSS", "where": "library", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the framework docs or the repository (checked 2026-11-06).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 52833, "npmWeekly": null, "pypiWeekly": 1260039, "asOf": "2026-11-06" }, "docsUrl": "https://developers.llamaindex.ai/python/framework/", "llmsTxt": "https://developers.llamaindex.ai/llms.txt", "capabilities": [ "agent.framework", "agent.multi-agent", "agent.durable", "agent.mcp-client" ], "tags": [ "framework", "python", "open-source", "llms-txt", "mcp", "rag", "workflows" ], "lastRelease": "2026-09-21", "graded": true, "anchor": { "graded": true, "score": 70, "grade": "BB", "agentReady": true, "rank": 217, "ranked": true, "rankOf": 1510, "categoryRank": 11, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 73, "maintenance": 69, "payments": 60, "reliability": 70, "schema": 85, "security": 74, "transparency": 67 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": -2, "negativeNotes": [ "2025-11 to 2026-11. Advisories for llama-index-core first published in the last 12 months are GHSA-488g-hw5f-x29p (uncontrolled resource consumption, 2 February 2026, moderate, fixed in 0.12.41) and the PYSEC re-publications in 2026 of 2025 path-traversal, denial-of-service and temporary-file issues fixed by 0.13.0. Fixed and documented, so 2 points. https://osv.dev/vulnerability/GHSA-488g-hw5f-x29p" ], "verdict": "An MIT Python framework for retrieval and agents, with three agent types, multi-agent AgentWorkflow, resumable event-driven Workflows, MCP tools and a huntr bug bounty, and no telemetry found. Core is still 0.14 with breaking minors, OpenAI is the silent default, and approval and injection handling are left to the application.", "bestFor": "Python teams building retrieval-heavy agents over their own data, with many connectors.", "strengths": [ "FunctionAgent, ReActAgent, CodeActAgent and multi-agent AgentWorkflow over one Workflows engine", "Workflow context serialises and resumes, with a DBOS package for durable runs", "Hundreds of integration packages for models, vector stores and data loaders", "No telemetry found in llama-index-core", "huntr bug bounty and public advisories with fixed versions" ], "weaknesses": [ "Core is 0.14.x, and minor versions such as 0.13 and 0.14 carried breaking changes", "OpenAI is the default LLM and embedding provider unless Settings is changed", "No per-tool approval primitive; the threat model leaves input validation to the application", "Several 2025 path-traversal and denial-of-service advisories in core and readers" ], "agentNotes": [ "Set Settings.llm and Settings.embed_model explicitly so calls don't go to OpenAI by default", "Install llama-index-tools-mcp for MCP tools and pass only the allowed tools the task needs", "Use Workflow human-in-the-loop events before tools that write or send", "Pin llama-index-core to a minor version, since minors have broken APIs", "Upgrade llama-index-core to 0.13.0 or later to clear the 2025 advisories" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "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 } ], "editorialScores": { "ergonomics": 73, "maintenance": 69, "payments": 60, "reliability": 70, "schema": 85, "security": 74, "transparency": 72 }, "provenanceScore": 61, "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 llama-index # MCP tools: pip install llama-index-tools-mcp" }, "letme": { "capability": "https://letme.dev/agent.framework", "tool": "https://letme.dev/llamaindex" }, "sameCompany": [ "llamaparse" ], "area": "frameworks", "provenance": { "legalEntity": "LlamaIndex, Inc.", "domain": "llamaindex.ai", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "https://www.llamaindex.ai/privacy-policy", "statusPage": "", "changelog": "https://github.com/run-llama/llama_index/blob/main/CHANGELOG.md", "securityTxt": "unknown", "checked": "2026-11-06", "notes": [ "The framework is MIT-licensed; the company facts follow the LlamaParse listing.", "developers.llamaindex.ai/robots.txt allows all crawlers.", "The privacy policy link is the company's; the library collects nothing itself. Neither the terms nor the privacy policy was re-read for this listing." ], "score": 61 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/llamaindex.json", "live": { "slug": "llamaindex", "versions": [ { "registry": "github", "name": "run-llama/llama_index", "version": "v0.14.25", "released": "2026-09-21", "seenAt": "2026-11-06T23:41:01.613169751Z" }, { "registry": "pypi", "name": "llama-index", "version": "0.14.25", "released": "2026-09-21", "seenAt": "2026-11-06T23:40:55.516520624Z" }, { "registry": "pypi", "name": "llama-index-core", "version": "0.14.25", "released": "2026-09-21", "seenAt": "2026-11-06T23:40:55.720658841Z" }, { "registry": "pypi", "name": "llama-index-tools-mcp", "version": "0.6.0", "released": "2026-08-31", "seenAt": "2026-11-06T23:41:00.102033357Z" }, { "registry": "pypi", "name": "llama-index-workflows", "version": "2.26.1", "released": "2026-10-21", "seenAt": "2026-11-06T23:40:57.534551463Z" } ], "githubStars": 52835, "pypiWeekly": 409969, "securityTxt": { "url": "https://llamaindex.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:24.67649536Z" }, "llmsTxt": { "url": "https://developers.llamaindex.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:53.290758373Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/run-llama/llama_index/main/CHANGELOG.md", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:23:19.050779794Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "51de27bb70e4" }, { "url": "https://www.llamaindex.ai/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:30:58.312656283Z", "changedAt": "2026-11-06T13:51:36.031111139Z", "fingerprint": "22f247245013" } ], "updatedAt": "2026-11-07T16:01:24.67649536Z" } }, "edges": [ { "by": 22, "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. MCP tools through a separate llama-index-tools-mcp package, with allowed tools selectable (18). Memory token limits, iteration caps and streaming events (16). Tool errors returned to the agent, with few typed errors (12). Workflow context serialises and resumes, and the DBOS package makes runs durable (16). Few required parameters, but OpenAI is the silent default for LLM and embeddings, Python here with a separate TypeScript edition (11). 18+16+12+16+11 = 73." }, "scores": { "a": 95, "b": 73 } }, { "by": 20, "category": "payments", "leads": "llamaindex", "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 MIT packages with nothing to buy for the framework itself (20 + 20 + 20). No payment protocol (0). LlamaCloud is graded on its own listing. 0+20+20+20 = 60." }, "scores": { "a": 40, "b": 60 } }, { "by": 18, "category": "maintenance", "leads": "claude-agent-sdk", "name": "Maintenance \u0026 community", "reasons": { "a": "Python 0.2.176 and TypeScript 0.3.316, both tagged on 31 October, PyPI and npm unreadable from here on 1 November (30). 47 Python release tags (0.2.129 to 0.2.176) and 81 TypeScript tags (0.3.221 to 0.3.316) between 4 August and 31 October, inside the 90 days from 3 August (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. Per the 1 October check, not re-read on 1 November (15). Python and TypeScript packages both current, each bundling or matching Claude Code 2.1.316 (15). CI and a dependency-graph workflow pass per the 1 October check. Releases have run without a gap since 6 October, 0.2.165 added an alert for blocked releases, 0.2.169 hash-pinned the build tools and 0.2.170 moved to trusted publishing, but no Python release shipped from 30 September to 6 October, and earlier yanks and the partial publish in #1234 still stand (7). 30+20+15+15+7 = 87.", "b": "llama-index-core 0.14.25 on 21 September 2026, 46 days before this check (20). Two core changelog entries in the 90 days (19 August and 21 September), with integration packages and Workflows (2.24.1 to 2.26.1) publishing in between, so partial (12). 379 open issues and 1,291 open issues and pull requests on 6 November, with 241 issues opened in the 90 days to 3 November. Of the 50 newest, 28 had a comment and 3 were closed; a stale bot and an issue classifier run on the repository (12). Core, Workflows and integrations are current (15). CI and CodeQL passing on main and a stale-package policy that moves unmaintained integrations out of main (10). 20+12+12+15+10 = 69." }, "scores": { "a": 87, "b": 69 } }, { "by": 16, "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": "MIT (30). The library stores nothing itself; OpenAI is the default provider unless changed, which the docs show (20). A stale-package policy and removals noted in the changelog, such as deprecated IPEX integrations removed in 0.14.25, without dated notice (10). No telemetry, though no page states it (12). 30+20+10+12 = 72." }, "scores": { "a": 83, "b": 67 } }, { "by": 9, "category": "security", "leads": "claude-agent-sdk", "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 telemetry found in llama-index-core (25). Human-in-the-loop events in Workflows and agents can wait for a person, but there's no per-tool approval primitive and CodeActAgent's executor is the developer's to supply (12). The threat model puts input validation on the application, with no prompt-injection guidance in the agent pages (5). Instrumentation events and callback handlers for tracing (14). A huntr bug bounty, GitHub private reporting and public advisories with fixed versions (18). 25+12+5+14+18 = 74." }, "scores": { "a": 83, "b": 74 } } ], "facts": [ { "a": "Agent framework", "b": "Agent framework", "name": "Kind" }, { "a": "Anthropic", "b": "LlamaIndex", "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": "MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-31", "b": "2026-09-21", "name": "Last release" }, { "a": "no date given", "b": "no document linked", "name": "Terms last updated" }, { "a": "no date given", "b": "2026-08-24", "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": "53k stars, 1.3M PyPI/wk", "name": "Popularity" }, { "a": "2.5/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Claude Agent SDK and LlamaIndex Framework score within a point of each other on agent readiness, 70.3 (BB) and 70 (BB). LlamaIndex Framework leads on payments \u0026 pricing.", "question": "Which is better for AI agents, Claude Agent SDK or LlamaIndex Framework?" }, { "answer": "No open-source release is listed for Claude Agent SDK. LlamaIndex Framework is open source (MIT).", "question": "Are Claude Agent SDK and LlamaIndex Framework open source?" } ], "goodFor": [ { "aheadOn": [ "Agent ergonomics, 95 against 73", "Security \u0026 auth, 83 against 74", "Maintenance \u0026 community, 87 against 69", "Transparency \u0026 trust, 83 against 67" ], "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": [ "Payments \u0026 pricing, 60 against 40" ], "also": [ "No key needed to call it", "Open source" ], "goodFor": "Python teams building retrieval-heavy agents over their own data, with many connectors.", "slug": "llamaindex", "watchFor": "Core is 0.14.x, and minor versions such as 0.13 and 0.14 carried breaking changes" } ], "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" } ], "llamaindex": 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-llamaindex.json", "title": "AgentOS vs LlamaIndex Framework", "url": "https://www.anchorterminal.com/compare/agentos-vs-llamaindex" }, { "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-llamaindex.json", "title": "Agno vs LlamaIndex Framework", "url": "https://www.anchorterminal.com/compare/agno-vs-llamaindex" }, { "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-llamaindex.json", "title": "BoxLang AI vs LlamaIndex Framework", "url": "https://www.anchorterminal.com/compare/boxlang-ai-vs-llamaindex" }, { "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-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-strands-agents.json", "title": "Claude Agent SDK vs Strands Agents", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-strands-agents" }, { "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-llamaindex.json", "title": "CrewAI vs LlamaIndex Framework", "url": "https://www.anchorterminal.com/compare/crewai-vs-llamaindex" }, { "json": "https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-llamaindex.json", "title": "Cursor Agent SDK vs LlamaIndex Framework", "url": "https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-llamaindex" }, { "json": "https://www.anchorterminal.com/compare/docker-agent-vs-llamaindex.json", "title": "Docker Agent vs LlamaIndex Framework", "url": "https://www.anchorterminal.com/compare/docker-agent-vs-llamaindex" }, { "json": "https://www.anchorterminal.com/compare/google-adk-vs-llamaindex.json", "title": "Agent Development Kit (ADK) vs LlamaIndex Framework", "url": "https://www.anchorterminal.com/compare/google-adk-vs-llamaindex" }, { "json": "https://www.anchorterminal.com/compare/guilds-run-vs-llamaindex.json", "title": "guilds.run vs LlamaIndex Framework", "url": "https://www.anchorterminal.com/compare/guilds-run-vs-llamaindex" }, { "json": "https://www.anchorterminal.com/compare/langgraph-vs-llamaindex.json", "title": "LangGraph vs LlamaIndex Framework", "url": "https://www.anchorterminal.com/compare/langgraph-vs-llamaindex" }, { "json": "https://www.anchorterminal.com/compare/llamaindex-vs-mastra.json", "title": "LlamaIndex Framework vs Mastra", "url": "https://www.anchorterminal.com/compare/llamaindex-vs-mastra" }, { "json": "https://www.anchorterminal.com/compare/llamaindex-vs-microsoft-agent-framework.json", "title": "LlamaIndex Framework vs Microsoft Agent Framework", "url": "https://www.anchorterminal.com/compare/llamaindex-vs-microsoft-agent-framework" }, { "json": "https://www.anchorterminal.com/compare/llamaindex-vs-openai-agents-sdk.json", "title": "LlamaIndex Framework vs OpenAI Agents SDK", "url": "https://www.anchorterminal.com/compare/llamaindex-vs-openai-agents-sdk" }, { "json": "https://www.anchorterminal.com/compare/llamaindex-vs-pydantic-ai.json", "title": "LlamaIndex Framework vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/llamaindex-vs-pydantic-ai" }, { "json": "https://www.anchorterminal.com/compare/llamaindex-vs-smolagents.json", "title": "LlamaIndex Framework vs smolagents", "url": "https://www.anchorterminal.com/compare/llamaindex-vs-smolagents" }, { "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/llamaindex-vs-tradingagents.json", "title": "LlamaIndex Framework vs TradingAgents", "url": "https://www.anchorterminal.com/compare/llamaindex-vs-tradingagents" }, { "json": "https://www.anchorterminal.com/compare/llamaindex-vs-vercel-ai-sdk.json", "title": "LlamaIndex Framework vs AI SDK", "url": "https://www.anchorterminal.com/compare/llamaindex-vs-vercel-ai-sdk" } ], "panel": null, "scores": [ { "by": 0, "claude-agent-sdk": 70, "edge": "", "key": "reliability", "llamaindex": 70, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 4, "claude-agent-sdk": 89, "edge": "claude-agent-sdk", "key": "schema", "llamaindex": 85, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 22, "claude-agent-sdk": 95, "edge": "claude-agent-sdk", "key": "ergonomics", "llamaindex": 73, "name": "Agent ergonomics", "weight": 13 }, { "by": 9, "claude-agent-sdk": 83, "edge": "claude-agent-sdk", "key": "security", "llamaindex": 74, "name": "Security \u0026 auth", "weight": 14 }, { "by": 20, "claude-agent-sdk": 40, "edge": "llamaindex", "key": "payments", "llamaindex": 60, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 18, "claude-agent-sdk": 87, "edge": "claude-agent-sdk", "key": "maintenance", "llamaindex": 69, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 16, "claude-agent-sdk": 83, "edge": "claude-agent-sdk", "key": "transparency", "llamaindex": 67, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Claude Agent SDK and LlamaIndex Framework score within a point of each other on agent readiness, 70.3 (BB) and 70 (BB). LlamaIndex Framework leads on payments \u0026 pricing. 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.", "llamaindex": "An MIT Python framework for retrieval and agents, with three agent types, multi-agent AgentWorkflow, resumable event-driven Workflows, MCP tools and a huntr bug bounty, and no telemetry found. Core is still 0.14 with breaking minors, OpenAI is the silent default, and approval and injection handling are left to the application." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-llamaindex", "json": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-llamaindex.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-llamaindex.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-llamaindex.min.md" }, "markdown": "Claude Agent SDK and LlamaIndex Framework score within a point of each other on agent readiness, 70.3 (BB) and 70 (BB). LlamaIndex Framework leads on payments \u0026 pricing. 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- LlamaIndex Framework: grade BB, 70/100, rank #217 of 1510. Markdown https://www.anchorterminal.com/tools/llamaindex.md · JSON https://www.anchorterminal.com/api/v1/tools/llamaindex.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 73\n- Security \u0026 auth, 83 against 74\n- Maintenance \u0026 community, 87 against 69\n- Transparency \u0026 trust, 83 against 67\n\nWatch for: Claude models only, so a person has to set up a Claude API key or cloud account first\n\n### LlamaIndex Framework (BB)\n\nGood for: Python teams building retrieval-heavy agents over their own data, with many connectors.\n\nAhead on:\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: Core is 0.14.x, and minor versions such as 0.13 and 0.14 carried breaking changes\n\n\n## Why the edge\n\n### Agent ergonomics: Claude Agent SDK +22\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- LlamaIndex Framework (73): Framework reading. MCP tools through a separate llama-index-tools-mcp package, with allowed tools selectable (18). Memory token limits, iteration caps and streaming events (16). Tool errors returned to the agent, with few typed errors (12). Workflow context serialises and resumes, and the DBOS package makes runs durable (16). Few required parameters, but OpenAI is the silent default for LLM and embeddings, Python here with a separate TypeScript edition (11). 18+16+12+16+11 = 73.\n\n### Payments \u0026 pricing: LlamaIndex Framework +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- LlamaIndex Framework (60): Self-hosted rule. Free MIT packages with nothing to buy for the framework itself (20 + 20 + 20). No payment protocol (0). LlamaCloud is graded on its own listing. 0+20+20+20 = 60.\n\n### Maintenance \u0026 community: Claude Agent SDK +18\n\n- Claude Agent SDK (87): Python 0.2.176 and TypeScript 0.3.316, both tagged on 31 October, PyPI and npm unreadable from here on 1 November (30). 47 Python release tags (0.2.129 to 0.2.176) and 81 TypeScript tags (0.3.221 to 0.3.316) between 4 August and 31 October, inside the 90 days from 3 August (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. Per the 1 October check, not re-read on 1 November (15). Python and TypeScript packages both current, each bundling or matching Claude Code 2.1.316 (15). CI and a dependency-graph workflow pass per the 1 October check. Releases have run without a gap since 6 October, 0.2.165 added an alert for blocked releases, 0.2.169 hash-pinned the build tools and 0.2.170 moved to trusted publishing, but no Python release shipped from 30 September to 6 October, and earlier yanks and the partial publish in #1234 still stand (7). 30+20+15+15+7 = 87.\n- LlamaIndex Framework (69): llama-index-core 0.14.25 on 21 September 2026, 46 days before this check (20). Two core changelog entries in the 90 days (19 August and 21 September), with integration packages and Workflows (2.24.1 to 2.26.1) publishing in between, so partial (12). 379 open issues and 1,291 open issues and pull requests on 6 November, with 241 issues opened in the 90 days to 3 November. Of the 50 newest, 28 had a comment and 3 were closed; a stale bot and an issue classifier run on the repository (12). Core, Workflows and integrations are current (15). CI and CodeQL passing on main and a stale-package policy that moves unmaintained integrations out of main (10). 20+12+12+15+10 = 69.\n\n### Transparency \u0026 trust: Claude Agent SDK +16\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- LlamaIndex Framework (67): MIT (30). The library stores nothing itself; OpenAI is the default provider unless changed, which the docs show (20). A stale-package policy and removals noted in the changelog, such as deprecated IPEX integrations removed in 0.14.25, without dated notice (10). No telemetry, though no page states it (12). 30+20+10+12 = 72.\n\n### Security \u0026 auth: Claude Agent SDK +9\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- LlamaIndex Framework (74): Framework reading (telemetry defaults, approvals, guardrails, sandboxing). No telemetry found in llama-index-core (25). Human-in-the-loop events in Workflows and agents can wait for a person, but there's no per-tool approval primitive and CodeActAgent's executor is the developer's to supply (12). The threat model puts input validation on the application, with no prompt-injection guidance in the agent pages (5). Instrumentation events and callback handlers for tracing (14). A huntr bug bounty, GitHub private reporting and public advisories with fixed versions (18). 25+12+5+14+18 = 74.\n\n## Score by category\n\n| Category | Weight | Claude Agent SDK | LlamaIndex Framework | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 70 | 70 | even |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 89 | 85 | Claude Agent SDK +4 |\n| Agent ergonomics | 13% (16.2 this run) | 95 | 73 | Claude Agent SDK +22 |\n| Security \u0026 auth | 14% (17.5 this run) | 83 | 74 | Claude Agent SDK +9 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 60 | LlamaIndex Framework +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 87 | 69 | Claude Agent SDK +18 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 83 | 67 | Claude Agent SDK +16 |\n| Negative events | ≤15 | -8 | -2 | |\n| **Total** | | **70.3 · BB** | **70 · BB** | |\n\n## Facts side by side\n\n| Fact | Claude Agent SDK | LlamaIndex Framework |\n| --- | --- | --- |\n| Kind | Agent framework | Agent framework |\n| Vendor | Anthropic | LlamaIndex |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | API key | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | MIT (Python wrapper), proprietary (TypeScript package and the bundled Claude Code binary) | MIT |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-31 | 2026-09-21 |\n| Terms last updated | no date given | no document linked |\n| Privacy policy last updated | no date given | 2026-08-24 |\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 | 53k stars, 1.3M 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### LlamaIndex Framework\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**LlamaIndex Framework.** An MIT Python framework for retrieval and agents, with three agent types, multi-agent AgentWorkflow, resumable event-driven Workflows, MCP tools and a huntr bug bounty, and no telemetry found. Core is still 0.14 with breaking minors, OpenAI is the silent default, and approval and injection handling are left to the application.\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### LlamaIndex Framework\n\n1. Set Settings.llm and Settings.embed_model explicitly so calls don't go to OpenAI by default\n2. Install llama-index-tools-mcp for MCP tools and pass only the allowed tools the task needs\n3. Use Workflow human-in-the-loop events before tools that write or send\n4. Pin llama-index-core to a minor version, since minors have broken APIs\n5. Upgrade llama-index-core to 0.13.0 or later to clear the 2025 advisories\n\n## Questions\n\n### Which is better for AI agents, Claude Agent SDK or LlamaIndex Framework?\n\nClaude Agent SDK and LlamaIndex Framework score within a point of each other on agent readiness, 70.3 (BB) and 70 (BB). LlamaIndex Framework leads on payments \u0026 pricing.\n\n### Are Claude Agent SDK and LlamaIndex Framework open source?\n\nNo open-source release is listed for Claude Agent SDK. LlamaIndex Framework is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/claude-agent-sdk-vs-llamaindex.json, and with the fewest tokens: https://www.anchorterminal.com/compare/claude-agent-sdk-vs-llamaindex.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"claude-agent-sdk\", \"b\": \"llamaindex\"}`. From a terminal: `anchor compare claude-agent-sdk llamaindex`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/claude-agent-sdk.json and https://www.anchorterminal.com/api/v1/tools/llamaindex.json\n\n## Other comparisons with Claude Agent SDK or LlamaIndex Framework\n\n- [AgentOS vs Claude Agent SDK](https://www.anchorterminal.com/compare/agentos-vs-claude-agent-sdk.md)\n- [AgentOS vs LlamaIndex Framework](https://www.anchorterminal.com/compare/agentos-vs-llamaindex.md)\n- [Agno vs Claude Agent SDK](https://www.anchorterminal.com/compare/agno-vs-claude-agent-sdk.md)\n- [Agno vs LlamaIndex Framework](https://www.anchorterminal.com/compare/agno-vs-llamaindex.md)\n- [BoxLang AI vs Claude Agent SDK](https://www.anchorterminal.com/compare/boxlang-ai-vs-claude-agent-sdk.md)\n- [BoxLang AI vs LlamaIndex Framework](https://www.anchorterminal.com/compare/boxlang-ai-vs-llamaindex.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 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 Strands Agents](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-strands-agents.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 LlamaIndex Framework](https://www.anchorterminal.com/compare/crewai-vs-llamaindex.md)\n- [Cursor Agent SDK vs LlamaIndex Framework](https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-llamaindex.md)\n- [Docker Agent vs LlamaIndex Framework](https://www.anchorterminal.com/compare/docker-agent-vs-llamaindex.md)\n- [Agent Development Kit (ADK) vs LlamaIndex Framework](https://www.anchorterminal.com/compare/google-adk-vs-llamaindex.md)\n- [guilds.run vs LlamaIndex Framework](https://www.anchorterminal.com/compare/guilds-run-vs-llamaindex.md)\n- [LangGraph vs LlamaIndex Framework](https://www.anchorterminal.com/compare/langgraph-vs-llamaindex.md)\n- [LlamaIndex Framework vs Mastra](https://www.anchorterminal.com/compare/llamaindex-vs-mastra.md)\n- [LlamaIndex Framework vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/llamaindex-vs-microsoft-agent-framework.md)\n- [LlamaIndex Framework vs OpenAI Agents SDK](https://www.anchorterminal.com/compare/llamaindex-vs-openai-agents-sdk.md)\n- [LlamaIndex Framework vs Pydantic AI](https://www.anchorterminal.com/compare/llamaindex-vs-pydantic-ai.md)\n- [LlamaIndex Framework vs smolagents](https://www.anchorterminal.com/compare/llamaindex-vs-smolagents.md)\n- [LlamaIndex Framework vs Strands Agents](https://www.anchorterminal.com/compare/llamaindex-vs-strands-agents.md)\n- [LlamaIndex Framework vs TradingAgents](https://www.anchorterminal.com/compare/llamaindex-vs-tradingagents.md)\n- [LlamaIndex Framework vs AI SDK](https://www.anchorterminal.com/compare/llamaindex-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 LlamaIndex Framework", "url": "" } ], "description": "Claude Agent SDK and LlamaIndex Framework score within a point of each other for agent frameworks, 70.3 and 70 out of 100. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Claude Agent SDK BB 70.3", "LlamaIndex Framework BB 70", "scores" ], "h1": "Claude Agent SDK vs LlamaIndex Framework", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/claude-agent-sdk-vs-llamaindex", "published": "2026-10-01", "section": "tools", "title": "Claude Agent SDK vs LlamaIndex Framework for AI agents (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-llamaindex" }, "tokens": { "markdown": 5050, "slim": 2880 }, "version": 1 }