{ "data": { "a": { "slug": "boxlang-ai", "name": "BoxLang AI", "vendor": "Ortus Solutions", "vendorUrl": "https://ai.boxlang.io", "kind": "framework", "category": "frameworks", "summary": "BoxLang AI (bx-ai) is Ortus Solutions' Apache-2.0 agent framework for BoxLang on the JVM, with agents, tools, memory, RAG, human approval, and an MCP client and server across more than 15 model providers.", "url": "https://www.anchorterminal.com/tools/boxlang-ai", "markdownUrl": "https://www.anchorterminal.com/tools/boxlang-ai.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/boxlang-ai.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/boxlang-ai.json", "dns": "boxlang-ai.grade.anchorterminal.com", "repo": "https://github.com/ortus-boxlang/bx-ai", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "forgebox", "name": "bx-ai" } ], "auth": "none", "authNotes": "A library with no account of its own. Model providers need their own keys, set in boxlang.json or read from each provider's environment variable (OPENAI_API_KEY, CLAUDE_API_KEY and so on). Ollama, Docker Model Runner and the mock provider need no key.", "pricing": "free", "pricingNotes": "Free under Apache-2.0. Model calls are billed by the provider. Ortus sells optional BoxLang runtime plans from $749 a year (Starter, one server) to $4,999 a node a year (BoxLang++), which the readme says add more vector memories and an Agent Dashboard.", "priceSummary": "Free · OSS", "where": "library", "x402": { "level": "no", "evidence": "Local library. No x402, MPP or L402 in the repository, the docs or the plans page, checked 1 November 2026.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-01" }, "docsUrl": "https://ai.ortusbooks.com", "llmsTxt": "https://ai.ortusbooks.com/llms.txt", "capabilities": [ "agent.framework", "agent.multi-agent", "agent.mcp-client" ], "tags": [ "framework", "boxlang", "jvm", "open-source", "apache-2.0", "mcp", "llms-txt", "free" ], "lastRelease": "2026-10-20", "graded": true, "anchor": { "graded": true, "score": 65.8, "grade": "B", "agentReady": false, "rank": 328, "ranked": true, "rankOf": 1260, "categoryRank": 10, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 74, "maintenance": 83, "payments": 50, "reliability": 66, "schema": 71, "security": 71, "transparency": 70 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": -3, "negativeNotes": [ "2026-10-20. -3, a breaking change in a minor release without advance notice. 3.6.0 renamed the `MCPClient` class to `MCPHttpClient` with no alias, so code that created the class directly must move to `MCP( url )`. The changelog's Migration section says so on release day. 3.5.0 (11 September) likewise raised the minimum BoxLang runtime from 1.8.0 to 1.14.0. One term at the floor, as google-adk's minor-release breaking changes took. https://github.com/ortus-boxlang/bx-ai/blob/main/changelog.md" ], "verdict": "A JVM agent framework with human approval, guardrail middleware and an MCP client over HTTP and stdio, all enforced in code, with three releases in the 90 days to 1 November 2026. It runs only on BoxLang, the stronger guards are opt-in, and minor releases have renamed public classes without a deprecation period.", "bestFor": "Teams already running BoxLang or modernising CFML on the JVM who want agents, RAG and MCP with approval and guardrails in the same language", "strengths": [ "Human approval enforced in code, with suspended runs that resume without replaying the model call, five approval policies and durable grants", "Untrusted context is fenced and inbound text Unicode-normalised by default, with opt-in sanitiser, LLM-judge and output-redaction middleware", "stdio MCP servers start without a shell, with an allowedCommands setting, per-server tool filters and prefixes, and restart limits", "Three releases in the 90 days to 1 November 2026 (3.4.0, 3.5.0, 3.6.0), with a Keep a Changelog file and migration notes", "llms.txt and a Markdown copy of every docs page, plus about 100 runnable example scripts in the repository" ], "weaknesses": [ "Runs only on BoxLang, a JVM language, so it suits teams already on BoxLang or CFML rather than Python or TypeScript stacks", "Minor releases carry breaking changes. 3.6.0 renamed MCPClient to MCPHttpClient with no alias, noted on release day", "The stdio command allow-list, filesystem tool paths and MCP server authentication are all open by default", "Docs lag the code. On 1 November the 3.6.0 release page still read unreleased and didn't mention the stdio MCP client", "No OpenTelemetry export found. Tracing is through BoxLang interception points, logging and flight-recorder middleware" ], "agentNotes": [ "Set `mcp.stdio.allowedCommands` to the executables you need. The default empty list lets any command start as a stdio MCP server.", "Pass `allowedPaths` when you create FileSystemTools. With none, its tools can read, write and delete anywhere the JVM user can.", "Attach HumanInTheLoopMiddleware with a checkpointer for tools that write or spend. Approval is opt-in.", "Create MCP clients with `MCP()` rather than the class, since 3.6.0 renamed MCPClient to MCPHttpClient without an alias.", "Use the `mock` provider to test agent wiring and guardrails with no API key or network." ], "metrics": { "kind": "library", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 65.8 } ], "editorialScores": { "ergonomics": 74, "maintenance": 83, "payments": 50, "reliability": 66, "schema": 71, "security": 71, "transparency": 65 }, "provenanceScore": 74, "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", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "install-bx-module bx-ai # in a web app: box install bx-ai" }, "letme": { "capability": "https://letme.dev/agent.framework", "tool": "https://letme.dev/boxlang-ai" }, "sameCompany": [ "bx-playwright" ], "area": "frameworks", "provenance": { "legalEntity": "Ortus Solutions, Corp.", "domain": "ortussolutions.com", "domainRegistered": "2006-04-12", "endpointOnVendorDomain": null, "terms": "https://github.com/ortus-boxlang/bx-ai/blob/main/src/main/resources/LICENSE", "privacy": "https://www.ortussolutions.com/about-us/ortus-privacy-policy", "statusPage": "", "changelog": "https://github.com/ortus-boxlang/bx-ai/blob/main/changelog.md", "securityTxt": "none", "checked": "2026-11-01", "notes": [ "The readme names Ortus Solutions, Corp as copyright holder, and box.json names Ortus Solutions as author.", "domainRegistered is from Verisign's RDAP record for ortussolutions.com. rdap.org has no record for boxlang.io, so the product domain's date wasn't read.", "security.txt answers 410 on www.ortussolutions.com and boxlang.io. CONTRIBUTING.md asks for vulnerability reports to security@ortussolutions.com.", "The Apache 2.0 licence stands in for terms. The privacy policy covers Ortus's website and customers, not the module.", "Local software, so there is no endpoint or status page." ], "score": 74 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/boxlang-ai.json" }, "answer": "Claude Agent SDK scores 70.3 (BB) on agent readiness against BoxLang AI's 65.8 (B), and leads in 6 of 7 scored categories. BoxLang AI leads on payments \u0026 pricing.", "b": { "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": 171, "ranked": true, "rankOf": 1260, "categoryRank": 7, "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": "2026-11-02T01:00:23.873635961Z" }, "versions": [ { "registry": "github", "name": "anthropics/claude-agent-sdk-python", "version": "v0.2.176", "released": "2026-10-31", "seenAt": "2026-11-01T16:49:14.978814403Z" }, { "registry": "npm", "name": "@anthropic-ai/claude-agent-sdk", "version": "0.3.316", "seenAt": "2026-11-01T16:49:14.118384155Z" }, { "registry": "pypi", "name": "claude-agent-sdk", "version": "0.2.176", "released": "2026-10-31", "seenAt": "2026-11-01T16:49:13.987149905Z" } ], "githubStars": 8402, "npmWeekly": 17096839, "pypiWeekly": 8093087, "securityTxt": { "url": "https://claude.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-01T15:43:31.144074216Z" }, "llmsTxt": { "url": "https://code.claude.com/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-01T15:13:08.04150338Z" }, "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": "2026-11-01T06:52:27.008115645Z", "changedAt": "2026-10-31T06:20:39.249963894Z", "fingerprint": "2517087302b6" }, { "url": "https://raw.githubusercontent.com/anthropics/claude-agent-sdk-typescript/main/CHANGELOG.md", "kind": "deprecations", "status": 304, "checkedAt": "2026-11-01T06:52:30.129180152Z", "changedAt": "2026-10-31T06:20:41.22431806Z", "fingerprint": "88953aad3425" } ], "github": { "repo": "anthropics/claude-agent-sdk-python", "checkedAt": "2026-10-26T07:10:10.432678925Z", "stars": 8349, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-25T22:38:58Z", "openIssues": 232, "openPRs": 360, "issuesOpened90d": 87, "issuesClosed90d": 15, "prsMerged90d": 31, "ci": { "branch": "main", "runs": 50, "success": 50, "failure": 0, "other": 0, "latest": "success", "latestAt": "2026-10-24T00:24:20Z" }, "advisories": [ { "ghsa": "GHSA-h4mw-j7qp-8mwm", "cve": "CVE-2026-96620", "severity": "critical", "published": "2026-09-12T08:42:34Z" } ], "replies": { "sampled": 25, "unanswered": 25 } }, "updatedAt": "2026-11-02T01:00:23.873635961Z" } }, "edges": [ { "by": 21, "category": "ergonomics", "leads": "claude-agent-sdk", "name": "Agent ergonomics", "reasons": { "a": "Framework reading, scored on what a tool-calling agent with MCP takes. An agent with an MCP server is one `aiAgent()` call with `mcpServers`, and `toolFilter` and `prefix` limit what each server adds. Skills can load lazily, but `autoLoadSkills` is on by default and injects every SKILL.md under /.agents/skills into every agent (20 of 25). MaxToolCallsMiddleware caps tool calls, window and summary memory bound history by messages or tokens, `withMaxResponseBytes` caps MCP answers and `listTools( cursor )` pages tools (17 of 20). Named exceptions (ProviderError, UnsupportedCapability, InvalidArgument, MCPCommandRefused, BXAI.SecurityViolation) but no reference page, and the changelog says a timed-out call still surfaces as a JSON parse error (12 of 20). RetryMiddleware with exponential backoff, approval resumes that don't replay the model call or rerun executed tools, and a stdio client that never repeats an in-flight call. MCP tool annotations such as readOnlyHint aren't read (15 of 20). An agent needs a name and works with defaults, and a mock provider runs with no key, but it is one language (10 of 15). 74 in all.", "b": "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." }, "scores": { "a": 74, "b": 95 } }, { "by": 18, "category": "schema", "leads": "claude-agent-sdk", "name": "Schema \u0026 documentation", "reasons": { "a": "Framework reading. A reference page for each built-in function with its arguments, and tool schemas generated from typed function arguments with required fields since 3.3.1. BoxLang is dynamically typed and no published API reference was found, though the repository builds DocBox API docs (15 of 25). llms.txt with about 150 entries and a Markdown copy of every page (10). The FAQ says when to use aiChat() or aiAgent() and the security guide says which guards to use when, though some FAQ links still say coming soon for pages that exist (14 of 20). Tool arguments are typed with required lists, and stdio options a server doesn't have throw InvalidArgument (11 of 15). About 100 example scripts in the repository and a gallery on ai.boxlang.io, but the production guide catches RateLimitException, TimeoutException and AuthenticationException, which the module's source never throws, and there is no exception reference (9 of 15). Keep a Changelog and a release-history page per version, but the 3.6.0 page still read unreleased on 1 November and two old versions appear twice in the changelog (12 of 15). 71 in all.", "b": "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." }, "scores": { "a": 71, "b": 89 } }, { "by": 13, "category": "transparency", "leads": "claude-agent-sdk", "name": "Transparency \u0026 trust", "reasons": { "a": "Apache-2.0, OSI approved, though the licence file sits in src/main/resources rather than the repository root (30). The FAQ says prompts and history go to the chosen cloud provider and that Ollama keeps data local, and we found no telemetry in the source, but there's no statement for the module of what, if anything, Ortus receives. Ortus's privacy policy covers its website and customers and says data is collected when you use its products without naming which (15 of 30). Migration notes are dated in the changelog, and default models were moved off a Groq model on its removal date, but there's no written deprecation policy or support window (10 of 20). No telemetry statement either way in the docs (10 of 20). 65 in all.", "b": "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." }, "scores": { "a": 70, "b": 83 } }, { "by": 12, "category": "security", "leads": "claude-agent-sdk", "name": "Security \u0026 auth", "reasons": { "a": "Framework reading. 30 for what leaves the machine and credentials, 20 for approvals and sandboxing, 15 for prompt injection, 15 for audit and 20 for the security programme. No telemetry in the module's source, requests go only to configured providers, keys come from settings or environment variables, and request logging is off by default. 3.4.0 fixed a Gemini key leaking into logs through the request URL (27 of 30). Approval is enforced in code by HumanInTheLoopMiddleware with five policies, GuardrailMiddleware blocks tools by name and argument pattern, and stdio commands never use a shell. All of it is opt-in. `allowedCommands` allows any executable by default, FileSystemTools allows any path without `allowedPaths`, and the MCP server has no authentication unless configured (12 of 20). Unicode hygiene and fencing of `${context}` are on by default, with opt-in input sanitiser, LLM judge and output guard. Streaming guards detect after the fact, which the changelog says (14 of 15). About 70 interception points, LoggingMiddleware, FlightRecorderMiddleware and MCP server statistics, with no OpenTelemetry export (11 of 15). CONTRIBUTING.md asks for reports to security@ortussolutions.com and the Slack #security channel. No security.txt (410), no bounty, and no published advisory found, while 3.6.0 lists a SQL injection fix in MySQL vector memory under Fixed (7 of 20). 71 in all.", "b": "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." }, "scores": { "a": 71, "b": 83 } }, { "by": 10, "category": "payments", "leads": "boxlang-ai", "name": "Payments \u0026 pricing", "reasons": { "a": "Self-hosted rule, scored on the paid option. No payment protocol (0). BoxLang runtime plans are public without a login, Starter $749 a year and BoxLang+ and BoxLang++ from $1,999 to $4,999 a server or node a year, plan pricing rather than per unit (10). The Apache-2.0 module installs with no card (20) and no account or sign-up (20). 50 in all.", "b": "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." }, "scores": { "a": 50, "b": 40 } } ], "facts": [ { "a": "Agent framework", "b": "Agent framework", "name": "Kind" }, { "a": "Ortus Solutions", "b": "Anthropic", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "None", "b": "API key", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "MIT (Python wrapper), proprietary (TypeScript package and the bundled Claude Code binary)", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-20", "b": "2026-10-31", "name": "Last release" }, { "a": "no date given", "b": "no date given", "name": "Terms last updated" }, { "a": "no date given", "b": "no date given", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "yes, with an opt-out", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "8.2k stars, 10.1M npm/wk, 6.1M PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "2.5/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Claude Agent SDK scores 70.3 (BB) on agent readiness against BoxLang AI's 65.8 (B), and leads in 6 of 7 scored categories. BoxLang AI leads on payments \u0026 pricing.", "question": "Which is better for AI agents, BoxLang AI or Claude Agent SDK?" }, { "answer": "BoxLang AI is open source (Apache-2.0). No open-source release is listed for Claude Agent SDK.", "question": "Are BoxLang AI and Claude Agent SDK open source?" } ], "goodFor": [ { "aheadOn": [ "Payments \u0026 pricing, 50 against 40" ], "also": [ "No key needed to call it", "Open source" ], "goodFor": "Teams already running BoxLang or modernising CFML on the JVM who want agents, RAG and MCP with approval and guardrails in the same language", "slug": "boxlang-ai", "watchFor": "Runs only on BoxLang, a JVM language, so it suits teams already on BoxLang or CFML rather than Python or TypeScript stacks" }, { "aheadOn": [ "Schema \u0026 documentation, 89 against 71", "Agent ergonomics, 95 against 74", "Security \u0026 auth, 83 against 71", "Transparency \u0026 trust, 83 against 70" ], "also": [ "Agent-ready, a grade of BB or better" ], "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" } ], "history": { "boxlang-ai": null, "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" } ] }, "job": { "capability": "agent.framework", "name": "Agent frameworks" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentos-vs-boxlang-ai.json", "title": "AgentOS vs BoxLang AI", "url": "https://www.anchorterminal.com/compare/agentos-vs-boxlang-ai" }, { "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/agno-vs-boxlang-ai.json", "title": "Agno vs BoxLang AI", "url": "https://www.anchorterminal.com/compare/agno-vs-boxlang-ai" }, { "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/boxlang-ai-vs-crewai.json", "title": "BoxLang AI vs CrewAI", "url": "https://www.anchorterminal.com/compare/boxlang-ai-vs-crewai" }, { "json": "https://www.anchorterminal.com/compare/boxlang-ai-vs-cursor-agent-sdk.json", "title": "BoxLang AI vs Cursor Agent SDK", "url": "https://www.anchorterminal.com/compare/boxlang-ai-vs-cursor-agent-sdk" }, { "json": "https://www.anchorterminal.com/compare/boxlang-ai-vs-docker-agent.json", "title": "BoxLang AI vs Docker Agent", "url": "https://www.anchorterminal.com/compare/boxlang-ai-vs-docker-agent" }, { "json": "https://www.anchorterminal.com/compare/boxlang-ai-vs-google-adk.json", "title": "BoxLang AI vs Agent Development Kit (ADK)", "url": "https://www.anchorterminal.com/compare/boxlang-ai-vs-google-adk" }, { "json": "https://www.anchorterminal.com/compare/boxlang-ai-vs-guilds-run.json", "title": "BoxLang AI vs guilds.run", "url": "https://www.anchorterminal.com/compare/boxlang-ai-vs-guilds-run" }, { "json": "https://www.anchorterminal.com/compare/boxlang-ai-vs-langgraph.json", "title": "BoxLang AI vs LangGraph", "url": "https://www.anchorterminal.com/compare/boxlang-ai-vs-langgraph" }, { "json": "https://www.anchorterminal.com/compare/boxlang-ai-vs-microsoft-agent-framework.json", "title": "BoxLang AI vs Microsoft Agent Framework", "url": "https://www.anchorterminal.com/compare/boxlang-ai-vs-microsoft-agent-framework" }, { "json": "https://www.anchorterminal.com/compare/boxlang-ai-vs-openai-agents-sdk.json", "title": "BoxLang AI vs OpenAI Agents SDK", "url": "https://www.anchorterminal.com/compare/boxlang-ai-vs-openai-agents-sdk" }, { "json": "https://www.anchorterminal.com/compare/boxlang-ai-vs-pydantic-ai.json", "title": "BoxLang AI vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/boxlang-ai-vs-pydantic-ai" }, { "json": "https://www.anchorterminal.com/compare/boxlang-ai-vs-tradingagents.json", "title": "BoxLang AI vs TradingAgents", "url": "https://www.anchorterminal.com/compare/boxlang-ai-vs-tradingagents" }, { "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-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-tradingagents.json", "title": "Claude Agent SDK vs TradingAgents", "url": "https://www.anchorterminal.com/compare/claude-agent-sdk-vs-tradingagents" } ], "panel": null, "scores": [ { "boxlang-ai": 66, "by": 4, "claude-agent-sdk": 70, "edge": "claude-agent-sdk", "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "boxlang-ai": 71, "by": 18, "claude-agent-sdk": 89, "edge": "claude-agent-sdk", "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "boxlang-ai": 74, "by": 21, "claude-agent-sdk": 95, "edge": "claude-agent-sdk", "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "boxlang-ai": 71, "by": 12, "claude-agent-sdk": 83, "edge": "claude-agent-sdk", "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "boxlang-ai": 50, "by": 10, "claude-agent-sdk": 40, "edge": "boxlang-ai", "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "boxlang-ai": 83, "by": 4, "claude-agent-sdk": 87, "edge": "claude-agent-sdk", "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "boxlang-ai": 70, "by": 13, "claude-agent-sdk": 83, "edge": "claude-agent-sdk", "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Claude Agent SDK scores 70.3 (BB) on agent readiness against BoxLang AI's 65.8 (B), and leads in 6 of 7 scored categories. BoxLang AI leads on payments \u0026 pricing. Both do agent frameworks.", "tasks": null, "tutorials": [], "verdicts": { "boxlang-ai": "A JVM agent framework with human approval, guardrail middleware and an MCP client over HTTP and stdio, all enforced in code, with three releases in the 90 days to 1 November 2026. It runs only on BoxLang, the stronger guards are opt-in, and minor releases have renamed public classes without a deprecation period.", "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." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/boxlang-ai-vs-claude-agent-sdk", "json": "https://www.anchorterminal.com/compare/boxlang-ai-vs-claude-agent-sdk.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/boxlang-ai-vs-claude-agent-sdk.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/boxlang-ai-vs-claude-agent-sdk.min.md" }, "markdown": "Claude Agent SDK scores 70.3 (BB) on agent readiness against BoxLang AI's 65.8 (B), and leads in 6 of 7 scored categories. BoxLang AI leads on payments \u0026 pricing. Both do agent frameworks.\n\n- BoxLang AI: grade B, 65.8/100, rank #328 of 1260. Markdown https://www.anchorterminal.com/tools/boxlang-ai.md · JSON https://www.anchorterminal.com/api/v1/tools/boxlang-ai.json\n- Claude Agent SDK: grade BB, 70.3/100, rank #171 of 1260. Markdown https://www.anchorterminal.com/tools/claude-agent-sdk.md · JSON https://www.anchorterminal.com/api/v1/tools/claude-agent-sdk.json\n- Best agent frameworks and SDKs: https://www.anchorterminal.com/best/frameworks/index.md\n- All 91 frameworks comparisons: https://www.anchorterminal.com/compare/frameworks/index.md\n\n## Which one, for what\n\n### BoxLang AI (B)\n\nGood for: Teams already running BoxLang or modernising CFML on the JVM who want agents, RAG and MCP with approval and guardrails in the same language\n\nAhead on:\n- Payments \u0026 pricing, 50 against 40\n\nAlso in its favour:\n- No key needed to call it\n- Open source\n\nWatch for: Runs only on BoxLang, a JVM language, so it suits teams already on BoxLang or CFML rather than Python or TypeScript stacks\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- Schema \u0026 documentation, 89 against 71\n- Agent ergonomics, 95 against 74\n- Security \u0026 auth, 83 against 71\n- Transparency \u0026 trust, 83 against 70\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n\nWatch for: Claude models only, so a person has to set up a Claude API key or cloud account first\n\n\n## Why the edge\n\n### Agent ergonomics: Claude Agent SDK +21\n\n- BoxLang AI (74): Framework reading, scored on what a tool-calling agent with MCP takes. An agent with an MCP server is one `aiAgent()` call with `mcpServers`, and `toolFilter` and `prefix` limit what each server adds. Skills can load lazily, but `autoLoadSkills` is on by default and injects every SKILL.md under /.agents/skills into every agent (20 of 25). MaxToolCallsMiddleware caps tool calls, window and summary memory bound history by messages or tokens, `withMaxResponseBytes` caps MCP answers and `listTools( cursor )` pages tools (17 of 20). Named exceptions (ProviderError, UnsupportedCapability, InvalidArgument, MCPCommandRefused, BXAI.SecurityViolation) but no reference page, and the changelog says a timed-out call still surfaces as a JSON parse error (12 of 20). RetryMiddleware with exponential backoff, approval resumes that don't replay the model call or rerun executed tools, and a stdio client that never repeats an in-flight call. MCP tool annotations such as readOnlyHint aren't read (15 of 20). An agent needs a name and works with defaults, and a mock provider runs with no key, but it is one language (10 of 15). 74 in all.\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\n### Schema \u0026 documentation: Claude Agent SDK +18\n\n- BoxLang AI (71): Framework reading. A reference page for each built-in function with its arguments, and tool schemas generated from typed function arguments with required fields since 3.3.1. BoxLang is dynamically typed and no published API reference was found, though the repository builds DocBox API docs (15 of 25). llms.txt with about 150 entries and a Markdown copy of every page (10). The FAQ says when to use aiChat() or aiAgent() and the security guide says which guards to use when, though some FAQ links still say coming soon for pages that exist (14 of 20). Tool arguments are typed with required lists, and stdio options a server doesn't have throw InvalidArgument (11 of 15). About 100 example scripts in the repository and a gallery on ai.boxlang.io, but the production guide catches RateLimitException, TimeoutException and AuthenticationException, which the module's source never throws, and there is no exception reference (9 of 15). Keep a Changelog and a release-history page per version, but the 3.6.0 page still read unreleased on 1 November and two old versions appear twice in the changelog (12 of 15). 71 in all.\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\n### Transparency \u0026 trust: Claude Agent SDK +13\n\n- BoxLang AI (70): Apache-2.0, OSI approved, though the licence file sits in src/main/resources rather than the repository root (30). The FAQ says prompts and history go to the chosen cloud provider and that Ollama keeps data local, and we found no telemetry in the source, but there's no statement for the module of what, if anything, Ortus receives. Ortus's privacy policy covers its website and customers and says data is collected when you use its products without naming which (15 of 30). Migration notes are dated in the changelog, and default models were moved off a Groq model on its removal date, but there's no written deprecation policy or support window (10 of 20). No telemetry statement either way in the docs (10 of 20). 65 in all.\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\n### Security \u0026 auth: Claude Agent SDK +12\n\n- BoxLang AI (71): Framework reading. 30 for what leaves the machine and credentials, 20 for approvals and sandboxing, 15 for prompt injection, 15 for audit and 20 for the security programme. No telemetry in the module's source, requests go only to configured providers, keys come from settings or environment variables, and request logging is off by default. 3.4.0 fixed a Gemini key leaking into logs through the request URL (27 of 30). Approval is enforced in code by HumanInTheLoopMiddleware with five policies, GuardrailMiddleware blocks tools by name and argument pattern, and stdio commands never use a shell. All of it is opt-in. `allowedCommands` allows any executable by default, FileSystemTools allows any path without `allowedPaths`, and the MCP server has no authentication unless configured (12 of 20). Unicode hygiene and fencing of `${context}` are on by default, with opt-in input sanitiser, LLM judge and output guard. Streaming guards detect after the fact, which the changelog says (14 of 15). About 70 interception points, LoggingMiddleware, FlightRecorderMiddleware and MCP server statistics, with no OpenTelemetry export (11 of 15). CONTRIBUTING.md asks for reports to security@ortussolutions.com and the Slack #security channel. No security.txt (410), no bounty, and no published advisory found, while 3.6.0 lists a SQL injection fix in MySQL vector memory under Fixed (7 of 20). 71 in all.\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\n### Payments \u0026 pricing: BoxLang AI +10\n\n- BoxLang AI (50): Self-hosted rule, scored on the paid option. No payment protocol (0). BoxLang runtime plans are public without a login, Starter $749 a year and BoxLang+ and BoxLang++ from $1,999 to $4,999 a server or node a year, plan pricing rather than per unit (10). The Apache-2.0 module installs with no card (20) and no account or sign-up (20). 50 in all.\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\n## Score by category\n\n| Category | Weight | BoxLang AI | Claude Agent SDK | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 66 | 70 | Claude Agent SDK +4 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 71 | 89 | Claude Agent SDK +18 |\n| Agent ergonomics | 13% (16.2 this run) | 74 | 95 | Claude Agent SDK +21 |\n| Security \u0026 auth | 14% (17.5 this run) | 71 | 83 | Claude Agent SDK +12 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 50 | 40 | BoxLang AI +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 83 | 87 | Claude Agent SDK +4 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 70 | 83 | Claude Agent SDK +13 |\n| Negative events | ≤15 | -3 | -8 | |\n| **Total** | | **65.8 · B** | **70.3 · BB** | |\n\n## Facts side by side\n\n| Fact | BoxLang AI | Claude Agent SDK |\n| --- | --- | --- |\n| Kind | Agent framework | Agent framework |\n| Vendor | Ortus Solutions | Anthropic |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | None | API key |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 | MIT (Python wrapper), proprietary (TypeScript package and the bundled Claude Code binary) |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-20 | 2026-10-31 |\n| Terms last updated | no date given | no date given |\n| Privacy policy last updated | no date given | no date given |\n| Customer content may train models | not found in the text | yes, with an opt-out |\n| Terms restrict automated access | not found in the text | not found in the text |\n| Terms restrict benchmarking | not found in the text | yes |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | not found in the text | yes |\n| Popularity | none | 8.2k stars, 10.1M npm/wk, 6.1M PyPI/wk |\n| Agent reviews | none | 2.5/5 (4) |\n\n## How the scores have moved\n\n### BoxLang AI\n\nNo score change since it was listed.\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## Verdicts\n\n**BoxLang AI.** A JVM agent framework with human approval, guardrail middleware and an MCP client over HTTP and stdio, all enforced in code, with three releases in the 90 days to 1 November 2026. It runs only on BoxLang, the stronger guards are opt-in, and minor releases have renamed public classes without a deprecation period.\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## Before you call either\n\n### BoxLang AI\n\n1. Set `mcp.stdio.allowedCommands` to the executables you need. The default empty list lets any command start as a stdio MCP server.\n2. Pass `allowedPaths` when you create FileSystemTools. With none, its tools can read, write and delete anywhere the JVM user can.\n3. Attach HumanInTheLoopMiddleware with a checkpointer for tools that write or spend. Approval is opt-in.\n4. Create MCP clients with `MCP()` rather than the class, since 3.6.0 renamed MCPClient to MCPHttpClient without an alias.\n5. Use the `mock` provider to test agent wiring and guardrails with no API key or network.\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## Questions\n\n### Which is better for AI agents, BoxLang AI or Claude Agent SDK?\n\nClaude Agent SDK scores 70.3 (BB) on agent readiness against BoxLang AI's 65.8 (B), and leads in 6 of 7 scored categories. BoxLang AI leads on payments \u0026 pricing.\n\n### Are BoxLang AI and Claude Agent SDK open source?\n\nBoxLang AI is open source (Apache-2.0). No open-source release is listed for Claude Agent SDK.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/boxlang-ai-vs-claude-agent-sdk.json, and with the fewest tokens: https://www.anchorterminal.com/compare/boxlang-ai-vs-claude-agent-sdk.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"boxlang-ai\", \"b\": \"claude-agent-sdk\"}`. From a terminal: `anchor compare boxlang-ai claude-agent-sdk`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/boxlang-ai.json and https://www.anchorterminal.com/api/v1/tools/claude-agent-sdk.json\n\n## Other comparisons with BoxLang AI or Claude Agent SDK\n\n- [AgentOS vs BoxLang AI](https://www.anchorterminal.com/compare/agentos-vs-boxlang-ai.md)\n- [AgentOS vs Claude Agent SDK](https://www.anchorterminal.com/compare/agentos-vs-claude-agent-sdk.md)\n- [Agno vs BoxLang AI](https://www.anchorterminal.com/compare/agno-vs-boxlang-ai.md)\n- [Agno vs Claude Agent SDK](https://www.anchorterminal.com/compare/agno-vs-claude-agent-sdk.md)\n- [BoxLang AI vs CrewAI](https://www.anchorterminal.com/compare/boxlang-ai-vs-crewai.md)\n- [BoxLang AI vs Cursor Agent SDK](https://www.anchorterminal.com/compare/boxlang-ai-vs-cursor-agent-sdk.md)\n- [BoxLang AI vs Docker Agent](https://www.anchorterminal.com/compare/boxlang-ai-vs-docker-agent.md)\n- [BoxLang AI vs Agent Development Kit (ADK)](https://www.anchorterminal.com/compare/boxlang-ai-vs-google-adk.md)\n- [BoxLang AI vs guilds.run](https://www.anchorterminal.com/compare/boxlang-ai-vs-guilds-run.md)\n- [BoxLang AI vs LangGraph](https://www.anchorterminal.com/compare/boxlang-ai-vs-langgraph.md)\n- [BoxLang AI vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/boxlang-ai-vs-microsoft-agent-framework.md)\n- [BoxLang AI vs OpenAI Agents SDK](https://www.anchorterminal.com/compare/boxlang-ai-vs-openai-agents-sdk.md)\n- [BoxLang AI vs Pydantic AI](https://www.anchorterminal.com/compare/boxlang-ai-vs-pydantic-ai.md)\n- [BoxLang AI vs TradingAgents](https://www.anchorterminal.com/compare/boxlang-ai-vs-tradingagents.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 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 TradingAgents](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-tradingagents.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": "2026-11-02", "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": "BoxLang AI vs Claude Agent SDK", "url": "" } ], "description": "Claude Agent SDK scores 70.3 (BB) to BoxLang AI's 65.8 (B) for agent frameworks. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "BoxLang AI B 65.8", "Claude Agent SDK BB 70.3", "scores" ], "h1": "BoxLang AI vs Claude Agent SDK", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/boxlang-ai-vs-claude-agent-sdk", "published": "2026-10-01", "section": "tools", "title": "BoxLang AI vs Claude Agent SDK for AI agents (2026) | Anchor Terminal", "toc": null, "updated": "2026-11-01", "url": "https://www.anchorterminal.com/compare/boxlang-ai-vs-claude-agent-sdk" }, "tokens": { "markdown": 5450, "slim": 3430 }, "version": 1 }