{ "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": "Pydantic AI scores 81.9 (A) on agent readiness against BoxLang AI's 65.8 (B), and leads in every scored category.", "b": { "slug": "pydantic-ai", "name": "Pydantic AI", "vendor": "Pydantic", "vendorUrl": "https://pydantic.dev", "kind": "framework", "category": "frameworks", "summary": "Typed Python agent framework for 25+ model providers, with MCP, A2A and durable execution.", "url": "https://www.anchorterminal.com/tools/pydantic-ai", "markdownUrl": "https://www.anchorterminal.com/tools/pydantic-ai.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/pydantic-ai.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/pydantic-ai.json", "dns": "pydantic-ai.grade.anchorterminal.com", "repo": "https://github.com/pydantic/pydantic-ai", "license": "MIT", "transports": [], "packages": [ { "registry": "pypi", "name": "pydantic-ai" } ], "auth": "none", "authNotes": "A library. Credentials are for the models and tools you use.", "pricing": "free", "pricingNotes": "Free and open source. You pay for the model calls it makes. Logfire for tracing is free for personal use, $49 a month for teams.", "priceSummary": "Free · OSS", "where": "library", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 20192, "npmWeekly": null, "pypiWeekly": 1276452, "asOf": "2026-09-26" }, "docsUrl": "https://pydantic.dev/docs/ai/overview/", "llmsTxt": "https://pydantic.dev/docs/ai/llms.txt", "capabilities": [ "agent.framework", "agent.multi-agent", "agent.durable", "agent.mcp-client" ], "tags": [ "framework", "python", "open-source", "typed", "no-telemetry" ], "lastRelease": "2026-10-30", "graded": true, "anchor": { "graded": true, "score": 81.9, "grade": "A", "agentReady": true, "rank": 5, "ranked": true, "rankOf": 1260, "categoryRank": 2, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 95, "maintenance": 90, "payments": 60, "reliability": 83, "schema": 100, "security": 95, "transparency": 87 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "high", "date": "2026-11-01" }, "negative": -6, "negativeNotes": [ "2026-02-06. Two high-severity advisories, server-side request forgery in URL download handling (GHSA-2jrp-274c-jhv3, CVE-2026-25580) and stored XSS through path traversal in the web UI's CDN URL (GHSA-wjp5-868j-wqv7). Both fixed and published, and more than eight months old, so 1 point each. Nine moderate and two low advisories from May to October 2026, three of them bypasses of its cloud-metadata blocklist, weren't deducted. https://github.com/pydantic/pydantic-ai/security", "2026-08-12. High-severity advisory GHSA-h4xc-3qfq-jf93 (CVSS 7.6). A website the developer visited could trigger agent runs and server-side tool execution through the local web chat UI (`Agent.to_web()`, `clai web`). Fixed in 2.28.0 and 1.107.4 and published, under two months old, so 2 points. It wasn't in the 1 October dossier. https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-h4xc-3qfq-jf93", "2026-10-08. High-severity advisory GHSA-6fqq-452j-qhrp (CVE-2026-107286, CVSS 7.5, availability only). With `ConcurrencyLimitedModel` or `limit_model_concurrency`, a streamed request that ended early could keep its slot, so a network client could exhaust a shared limiter by starting streams and disconnecting. Fixed in 2.53.0 on 2 October and added to the GitHub Advisory Database on 8 October, after the 4 October check, so 2 points as for the other fixed High under two months old. https://osv.dev/vulnerability/GHSA-6fqq-452j-qhrp" ], "verdict": "Typed outputs and tools, validated by Pydantic, with failed validations sent back to the model. Python only.", "bestFor": "Python teams that want typed, validated outputs and tools, many model providers and durable runs on an engine they already use.", "strengths": [ "Typed outputs and tools, validated by Pydantic, with failed validations sent back to the model", "No telemetry until you configure OpenTelemetry or Logfire, and the docs say nothing is sent otherwise", "Durable execution on nine engines, including Temporal, DBOS, Prefect, Restate and AWS Lambda", "Read-only workspaces in core, and Harness sandboxes for commands and model-written code", "A written version policy, with deprecations kept until the next major and V1 security releases still shipping" ], "weaknesses": [ "Python only, and 3.11 or newer since 2.55.0", "1.1k open issues and 469 open pull requests on 1 November 2026, roughly double the 1 October counts", "Fifteen advisories in 2026, four high, including SSRF, three cloud-metadata blocklist bypasses and a cross-site flaw in the web chat UI", "Sandboxes, guardrails and the injection defender live in the Harness, a separate 0.x package classed Alpha", "The Prompt Injection Defender passes results through unchanged unless `block_high_risk=True` is set" ], "agentNotes": [ "Define the output type first. Validation retries fix most malformed answers without a prompt change, and the test model checks the wiring with no key", "Use streamable HTTP for MCP, since SSE is deprecated. Call `.defer_loading()` on large MCP servers so their tools stay out of context until searched", "Set usage limits on every run that calls paid models", "Give model-run commands `LocalWorkspace(read_only=True)` or a Harness sandbox. A plain `LocalWorkspace` runs them on your machine as you", "Stay on 2.53.0 or later, and the Harness on 0.59.0 or later. 2026 advisories hit URL downloads, the metadata blocklist, the web chat UI, streamed requests and nested CodeMode calls" ], "metrics": { "kind": "library", "measured": false }, "reviewCount": 8, "avgRating": 4, "history": [ { "basis": "public evidence", "confidence": "high", "grade": "A", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 81.9 } ], "editorialScores": { "ergonomics": 95, "maintenance": 90, "payments": 60, "reliability": 83, "schema": 100, "security": 95, "transparency": 95 }, "provenanceScore": 79, "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": "2026-10-27", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install pydantic-ai" }, "letme": { "capability": "https://letme.dev/agent.framework", "tool": "https://letme.dev/pydantic-ai" }, "sameCompany": [ "pydantic-logfire" ], "area": "frameworks", "unitPrices": [ { "item": "Logfire Team", "unit": "month", "usd": 49, "note": "tracing, personal use free" } ], "provenance": { "legalEntity": "Pydantic Services Inc.", "domain": "pydantic.dev", "domainRegistered": "2022-04-24", "endpointOnVendorDomain": null, "terms": "https://pydantic.dev/legal/terms-of-service", "privacy": "https://pydantic.dev/legal/privacy-policy", "statusPage": "", "changelog": "https://pydantic.dev/docs/ai/project/changelog/", "securityTxt": "valid", "checked": "2026-10-04", "score": 79 }, "requirements": { "card": "unknown", "freeTier": true, "minutes": 5, "credential": "api-key", "hosting": [ "self-hosted" ], "euResidency": "unknown", "trainsOnData": "no", "zeroRetention": "unknown", "selfHost": "yes" }, "pageJsonUrl": "https://www.anchorterminal.com/tools/pydantic-ai.json", "live": { "slug": "pydantic-ai", "versions": [ { "registry": "github", "name": "pydantic/pydantic-ai", "version": "v2.64.0", "released": "2026-10-30", "seenAt": "2026-11-01T17:27:36.860388495Z" }, { "registry": "pypi", "name": "pydantic-ai", "version": "2.64.0", "released": "2026-10-31", "seenAt": "2026-11-01T17:27:36.742903217Z" } ], "githubStars": 20982, "pypiWeekly": 1723783, "securityTxt": { "url": "https://pydantic.dev/.well-known/security.txt", "state": "valid", "expires": "2027-09-17T00:00:00.000Z", "checkedAt": "2026-11-01T15:43:30.639826743Z" }, "llmsTxt": { "url": "https://pydantic.dev/docs/ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-01T15:14:47.78076986Z" }, "domain": { "domain": "pydantic.dev", "registered": "2022-04-24", "source": "https://pubapi.registry.google/rdap/domain/pydantic.dev", "checkedAt": "2026-11-01T14:14:17.651909972Z" }, "pages": [ { "url": "https://pydantic.dev/docs/ai/project/changelog/", "kind": "changelog", "status": 200, "checkedAt": "2026-11-01T06:50:52.850996297Z", "changedAt": "2026-10-31T06:19:05.068900175Z", "fingerprint": "ee657a038c1f" }, { "url": "https://pydantic.dev/articles/pydantic-ai-v2", "kind": "deprecations", "status": 304, "checkedAt": "2026-11-01T06:50:48.817219522Z", "changedAt": "2026-10-31T06:19:01.047088362Z", "fingerprint": "5c11bab70b01" }, { "url": "https://pydantic.dev/docs/ai/project/version-policy/", "kind": "deprecations", "status": 200, "checkedAt": "2026-11-01T06:50:54.887770299Z", "changedAt": "2026-10-31T06:19:07.150712742Z", "fingerprint": "f2e509945e69" }, { "url": "https://pydantic.dev/legal/privacy-policy", "kind": "privacy", "status": 304, "checkedAt": "2026-11-01T06:50:56.870475735Z", "changedAt": "2026-10-07T18:08:45.478164751Z", "fingerprint": "ffa3b6106e3d" }, { "url": "https://pydantic.dev/legal/terms-of-service", "kind": "terms", "status": 304, "checkedAt": "2026-11-01T06:50:58.841847608Z", "changedAt": "2026-10-07T18:08:47.356836571Z", "fingerprint": "39f75457a65a" } ], "github": { "repo": "pydantic/pydantic-ai", "checkedAt": "2026-10-26T07:58:58.226919484Z", "stars": 20877, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-26T03:50:14Z", "openIssues": 1048, "openPRs": 442, "issuesOpened90d": 1505, "issuesClosed90d": 947, "prsMerged90d": 1843, "ci": { "branch": "main", "runs": 50, "success": 46, "failure": 4, "other": 0, "latest": "failure", "latestAt": "2026-10-25T22:58:00Z" }, "advisories": [ { "ghsa": "GHSA-4whf-38hw-pxxh", "severity": "high", "published": "2026-10-21T05:06:29Z" }, { "ghsa": "GHSA-xv4x-g8mx-ch56", "severity": "medium", "published": "2026-10-20T05:42:04Z" }, { "ghsa": "GHSA-5pfm-2g3g-gh85", "severity": "medium", "published": "2026-10-20T05:31:48Z" }, { "ghsa": "GHSA-6fqq-452j-qhrp", "cve": "CVE-2026-107286", "severity": "high", "published": "2026-10-02T03:19:39Z" }, { "ghsa": "GHSA-v36g-jcw9-x7cw", "cve": "CVE-2026-107287", "severity": "medium", "published": "2026-09-30T01:31:43Z" }, { "ghsa": "GHSA-4x9p-g9wm-8q7f", "cve": "CVE-2026-107291", "severity": "low", "published": "2026-09-17T04:14:30Z" }, { "ghsa": "GHSA-fpf4-vwcp-v4hp", "cve": "CVE-2026-107290", "severity": "medium", "published": "2026-09-17T04:14:29Z" }, { "ghsa": "GHSA-22h6-qm39-v87j", "cve": "CVE-2026-107288", "severity": "low", "published": "2026-09-17T04:14:28Z" }, { "ghsa": "GHSA-vmxc-h2x2-jmf3", "cve": "CVE-2026-107289", "severity": "medium", "published": "2026-09-17T04:14:27Z" }, { "ghsa": "GHSA-q2xc-rrxj-58x9", "cve": "CVE-2026-107292", "severity": "medium", "published": "2026-08-14T02:58:39Z" }, { "ghsa": "GHSA-3gh4-cghq-f8v4", "cve": "CVE-2026-107293", "severity": "low", "published": "2026-08-12T04:02:44Z" }, { "ghsa": "GHSA-h4xc-3qfq-jf93", "cve": "CVE-2026-107295", "severity": "high", "published": "2026-08-12T04:02:43Z" }, { "ghsa": "GHSA-v2xh-2vp8-57h8", "cve": "CVE-2026-107294", "severity": "medium", "published": "2026-08-08T03:33:55Z" }, { "ghsa": "GHSA-jpr8-2v3g-wgf9", "cve": "CVE-2026-65975", "severity": "medium", "published": "2026-07-11T03:28:12Z" }, { "ghsa": "GHSA-h7p7-w5gc-xj3w", "cve": "CVE-2026-54249", "severity": "medium", "published": "2026-06-10T14:29:58Z" }, { "ghsa": "GHSA-cg7w-rg45-pc59", "cve": "CVE-2026-48782", "severity": "medium", "published": "2026-05-23T01:16:52Z" }, { "ghsa": "GHSA-cqp8-fcvh-x7r3", "cve": "CVE-2026-46678", "severity": "medium", "published": "2026-05-20T17:20:04Z" }, { "ghsa": "GHSA-2jrp-274c-jhv3", "cve": "CVE-2026-25580", "severity": "high", "published": "2026-02-06T01:14:08Z" }, { "ghsa": "GHSA-wjp5-868j-wqv7", "cve": "CVE-2026-25640", "severity": "high", "published": "2026-02-06T01:13:49Z" } ] }, "updatedAt": "2026-11-01T17:27:36.860388495Z" } }, "edges": [ { "by": 29, "category": "schema", "leads": "pydantic-ai", "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 end to end with an API reference (25). llms.txt and llms-full.txt, with llms.txt re-read on 4 October (10). The docs say when not to reach for a feature. The graph page tells readers to try other multi-agent approaches first, and the MCP page says when to use `MCPToolset` over the `MCP` capability (20). Tools are typed functions validated by Pydantic (15). `ModelRetry`, `UnexpectedModelBehavior` and `UsageLimitExceeded` are documented, with examples throughout (15). Changelog and a version policy (15)." }, "scores": { "a": 71, "b": 100 } }, { "by": 24, "category": "security", "leads": "pydantic-ai", "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": "No telemetry unless you configure it. OpenTelemetry instrumentation and Logfire take two added lines (30). Deferred-tool approval is built in. `LocalWorkspace(read_only=True)` and `ReadOnlyWorkspace` in core (since 2.52.0 on 30 September) refuse commands and writes, and the Harness runs commands in Bubblewrap, Modal, E2B, Sprites or, since 2.56.0, smolvm sandboxes and code mode in the Monty interpreter (20). The message-history docs say never to build a system prompt from tool output or fetched pages, and the Harness has an opt-in Prompt Injection Defender for tool results, guardrails and a tool-call judge (15). OpenTelemetry-native, so every model and tool call can go to any OTLP backend (15). Private reporting through GitHub and a valid security.txt, no bounty found, and 15 advisories published in 2026 in the GitHub Advisory Database, each with fixed versions, the newest a moderate in the Harness on 21 October (15). Framework reading, so SOC 2 isn't scored. The Harness is a separate 0.x package classed Alpha." }, "scores": { "a": 71, "b": 95 } }, { "by": 21, "category": "ergonomics", "leads": "pydantic-ai", "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": "MCP ships in core. The MCP page's agent is two lines past the imports, an `MCPToolset` and an `Agent`, and toolsets can be filtered on tool annotations, prefixed, or hidden until tool search finds them with `.defer_loading()` (25). Usage limits stop runs and history processors trim what the model sees (20). Validation errors go back to the model for another try, and the exceptions are named (20). Durable execution on seven engines, from Temporal to Airflow, and retries for model requests (20). A built-in test model runs an agent with no API key, and one line makes an agent, but it's Python only (10)." }, "scores": { "a": 74, "b": 95 } }, { "by": 17, "category": "reliability", "leads": "pydantic-ai", "name": "Reliability", "reasons": { "a": "Read with the local-software lines. Official package on ForgeBox, installed with `install-bx-module bx-ai` or `box install bx-ai`, with BoxLang 1.14.0 or later in box.json and JDK 21 in CONTRIBUTING.md, but the 3.6 announcement says BoxLang 1.18 or later (18 of 20). tests.yml runs about 140 test classes against Ollama and the vector stores in Docker Compose, and against paid providers on development and releases, on pull requests and pushes to development. Whether runs pass wasn't read, since WebFetch refused github.com (15 of 25). Open issues and replies weren't read for the same reason. The changelog closes issues #182 to #259 in 3.3.1 to 3.4.0, and bugs also go to Ortus's Jira (10 of 25). Keep a Changelog with semantic versioning stated and Migration sections, but breaking changes ship in minor releases (8 of 15). 3.6.0, past 1.0 (15). 66 in all.", "b": "Official package on PyPI. Requires-Python is \u003e=3.11 since 2.55.0 on 9 October, which dropped Python 3.10 in its end-of-life month (20). CI passes on main, with a coverage badge, per the 1 October check. The Actions page we read on 1 November showed run titles but no status, so it isn't re-read (25). 1.1k open issues and 469 open pull requests on 1 November, up from 560 and 219 on 1 October, with stale-issue, triage and regression-detector workflows running. We didn't read reply times, so 8 stands (8). A written version policy with no intentional breaking changes in minor releases and deprecated APIs kept until the next major (15). 2.64.0, classed 5 - Production/Stable (15)." }, "scores": { "a": 66, "b": 83 } }, { "by": 17, "category": "transparency", "leads": "pydantic-ai", "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": "MIT (30). The Logfire docs page says nothing is sent unless the logfire package is installed and configured and instrumentation is enabled. Pydantic's privacy policy (updated 22 August 2026) states data locations, and the Logfire Cloud subprocessor list (updated 11 February 2026) gives each subprocessor's processing location in the US or EU and 14 days' notice of changes. Logfire's plans state 30 or up to 90 days' retention. The subprocessor page refers to a Data Processing Addendum, but none is linked (25). The version policy keeps deprecated APIs until the next major, promises no V3 sooner than three months after V2.0 and V1 security fixes for at least six months after V2 on 2026-06-23 (20). Telemetry is opt-in and documented (20)." }, "scores": { "a": 70, "b": 87 } }, { "by": 10, "category": "payments", "leads": "pydantic-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). Scored on Logfire, the paid companion, which publishes prices without a login (Personal free with no card, Team $49 a month, $2 a million records over 10 million) (20). The MIT package installs with no card (20) and no account, and the test model needs no key at all (20)." }, "scores": { "a": 50, "b": 60 } } ], "facts": [ { "a": "Agent framework", "b": "Agent framework", "name": "Kind" }, { "a": "Ortus Solutions", "b": "Pydantic", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "MIT", "name": "Licence" }, { "a": "no", "b": "yes", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-20", "b": "2026-10-30", "name": "Last release" }, { "a": "no date given", "b": "no date given", "name": "Terms last updated" }, { "a": "no date given", "b": "2024-02-21", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "not found in the text", "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": "20k stars, 1.3M PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "4/5 (8)", "name": "Agent reviews" } ], "faq": [ { "answer": "Pydantic AI scores 81.9 (A) on agent readiness against BoxLang AI's 65.8 (B), and leads in every scored category.", "question": "Which is better for AI agents, BoxLang AI or Pydantic AI?" }, { "answer": "Yes. BoxLang AI is open source (Apache-2.0). Pydantic AI is open source (MIT).", "question": "Are BoxLang AI and Pydantic AI open source?" } ], "goodFor": [ { "aheadOn": null, "also": null, "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": [ "Reliability, 83 against 66", "Schema \u0026 documentation, 100 against 71", "Agent ergonomics, 95 against 74", "Security \u0026 auth, 95 against 71", "Payments \u0026 pricing, 60 against 50", "Maintenance \u0026 community, 90 against 83", "Transparency \u0026 trust, 87 against 70" ], "also": [ "Agent-ready, a grade of BB or better" ], "goodFor": "Python teams that want typed, validated outputs and tools, many model providers and durable runs on an engine they already use.", "slug": "pydantic-ai", "watchFor": "Python only, and 3.11 or newer since 2.55.0" } ], "history": { "boxlang-ai": null, "pydantic-ai": [ { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.2, "from": 81.7, "fromGrade": "A", "to": 81.9, "toGrade": "A" }, { "causes": [ "event" ], "date": "2026-10-17", "delta": -2, "from": 83.7, "fromGrade": "A", "to": 81.7, "toGrade": "A" }, { "causes": [ "method" ], "date": "2026-10-08", "delta": -0.2, "from": 83.9, "fromGrade": "A", "to": 83.7, "toGrade": "A" } ] }, "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-pydantic-ai.json", "title": "AgentOS vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/agentos-vs-pydantic-ai" }, { "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-pydantic-ai.json", "title": "Agno vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/agno-vs-pydantic-ai" }, { "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-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-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-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/crewai-vs-pydantic-ai.json", "title": "CrewAI vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/crewai-vs-pydantic-ai" }, { "json": "https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-pydantic-ai.json", "title": "Cursor Agent SDK vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-pydantic-ai" }, { "json": "https://www.anchorterminal.com/compare/docker-agent-vs-pydantic-ai.json", "title": "Docker Agent vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/docker-agent-vs-pydantic-ai" }, { "json": "https://www.anchorterminal.com/compare/google-adk-vs-pydantic-ai.json", "title": "Agent Development Kit (ADK) vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/google-adk-vs-pydantic-ai" }, { "json": "https://www.anchorterminal.com/compare/guilds-run-vs-pydantic-ai.json", "title": "guilds.run vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/guilds-run-vs-pydantic-ai" }, { "json": "https://www.anchorterminal.com/compare/langgraph-vs-pydantic-ai.json", "title": "LangGraph vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/langgraph-vs-pydantic-ai" }, { "json": "https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-pydantic-ai.json", "title": "Microsoft Agent Framework vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-pydantic-ai" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-sdk-vs-pydantic-ai.json", "title": "OpenAI Agents SDK vs Pydantic AI", "url": "https://www.anchorterminal.com/compare/openai-agents-sdk-vs-pydantic-ai" }, { "json": "https://www.anchorterminal.com/compare/pydantic-ai-vs-tradingagents.json", "title": "Pydantic AI vs TradingAgents", "url": "https://www.anchorterminal.com/compare/pydantic-ai-vs-tradingagents" } ], "panel": null, "scores": [ { "boxlang-ai": 66, "by": 17, "edge": "pydantic-ai", "key": "reliability", "name": "Reliability", "pydantic-ai": 83, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "boxlang-ai": 71, "by": 29, "edge": "pydantic-ai", "key": "schema", "name": "Schema \u0026 documentation", "pydantic-ai": 100, "weight": 13 }, { "boxlang-ai": 74, "by": 21, "edge": "pydantic-ai", "key": "ergonomics", "name": "Agent ergonomics", "pydantic-ai": 95, "weight": 13 }, { "boxlang-ai": 71, "by": 24, "edge": "pydantic-ai", "key": "security", "name": "Security \u0026 auth", "pydantic-ai": 95, "weight": 14 }, { "boxlang-ai": 50, "by": 10, "edge": "pydantic-ai", "key": "payments", "name": "Payments \u0026 pricing", "pydantic-ai": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "boxlang-ai": 83, "by": 7, "edge": "pydantic-ai", "key": "maintenance", "name": "Maintenance \u0026 community", "pydantic-ai": 90, "weight": 7 }, { "boxlang-ai": 70, "by": 17, "edge": "pydantic-ai", "key": "transparency", "name": "Transparency \u0026 trust", "pydantic-ai": 87, "weight": 7 } ], "summary": "Pydantic AI scores 81.9 (A) on agent readiness against BoxLang AI's 65.8 (B), and leads in every scored category. 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.", "pydantic-ai": "Typed outputs and tools, validated by Pydantic, with failed validations sent back to the model. Python only." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/boxlang-ai-vs-pydantic-ai", "json": "https://www.anchorterminal.com/compare/boxlang-ai-vs-pydantic-ai.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/boxlang-ai-vs-pydantic-ai.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/boxlang-ai-vs-pydantic-ai.min.md" }, "markdown": "Pydantic AI scores 81.9 (A) on agent readiness against BoxLang AI's 65.8 (B), and leads in every scored category. 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- Pydantic AI: grade A, 81.9/100, rank #5 of 1260. Markdown https://www.anchorterminal.com/tools/pydantic-ai.md · JSON https://www.anchorterminal.com/api/v1/tools/pydantic-ai.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\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### Pydantic AI (A)\n\nGood for: Python teams that want typed, validated outputs and tools, many model providers and durable runs on an engine they already use.\n\nAhead on:\n- Reliability, 83 against 66\n- Schema \u0026 documentation, 100 against 71\n- Agent ergonomics, 95 against 74\n- Security \u0026 auth, 95 against 71\n- Payments \u0026 pricing, 60 against 50\n- Maintenance \u0026 community, 90 against 83\n- Transparency \u0026 trust, 87 against 70\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n\nWatch for: Python only, and 3.11 or newer since 2.55.0\n\n\n## Why the edge\n\n### Schema \u0026 documentation: Pydantic AI +29\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- Pydantic AI (100): Typed end to end with an API reference (25). llms.txt and llms-full.txt, with llms.txt re-read on 4 October (10). The docs say when not to reach for a feature. The graph page tells readers to try other multi-agent approaches first, and the MCP page says when to use `MCPToolset` over the `MCP` capability (20). Tools are typed functions validated by Pydantic (15). `ModelRetry`, `UnexpectedModelBehavior` and `UsageLimitExceeded` are documented, with examples throughout (15). Changelog and a version policy (15).\n\n### Security \u0026 auth: Pydantic AI +24\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- Pydantic AI (95): No telemetry unless you configure it. OpenTelemetry instrumentation and Logfire take two added lines (30). Deferred-tool approval is built in. `LocalWorkspace(read_only=True)` and `ReadOnlyWorkspace` in core (since 2.52.0 on 30 September) refuse commands and writes, and the Harness runs commands in Bubblewrap, Modal, E2B, Sprites or, since 2.56.0, smolvm sandboxes and code mode in the Monty interpreter (20). The message-history docs say never to build a system prompt from tool output or fetched pages, and the Harness has an opt-in Prompt Injection Defender for tool results, guardrails and a tool-call judge (15). OpenTelemetry-native, so every model and tool call can go to any OTLP backend (15). Private reporting through GitHub and a valid security.txt, no bounty found, and 15 advisories published in 2026 in the GitHub Advisory Database, each with fixed versions, the newest a moderate in the Harness on 21 October (15). Framework reading, so SOC 2 isn't scored. The Harness is a separate 0.x package classed Alpha.\n\n### Agent ergonomics: Pydantic AI +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- Pydantic AI (95): MCP ships in core. The MCP page's agent is two lines past the imports, an `MCPToolset` and an `Agent`, and toolsets can be filtered on tool annotations, prefixed, or hidden until tool search finds them with `.defer_loading()` (25). Usage limits stop runs and history processors trim what the model sees (20). Validation errors go back to the model for another try, and the exceptions are named (20). Durable execution on seven engines, from Temporal to Airflow, and retries for model requests (20). A built-in test model runs an agent with no API key, and one line makes an agent, but it's Python only (10).\n\n### Reliability: Pydantic AI +17\n\n- BoxLang AI (66): Read with the local-software lines. Official package on ForgeBox, installed with `install-bx-module bx-ai` or `box install bx-ai`, with BoxLang 1.14.0 or later in box.json and JDK 21 in CONTRIBUTING.md, but the 3.6 announcement says BoxLang 1.18 or later (18 of 20). tests.yml runs about 140 test classes against Ollama and the vector stores in Docker Compose, and against paid providers on development and releases, on pull requests and pushes to development. Whether runs pass wasn't read, since WebFetch refused github.com (15 of 25). Open issues and replies weren't read for the same reason. The changelog closes issues #182 to #259 in 3.3.1 to 3.4.0, and bugs also go to Ortus's Jira (10 of 25). Keep a Changelog with semantic versioning stated and Migration sections, but breaking changes ship in minor releases (8 of 15). 3.6.0, past 1.0 (15). 66 in all.\n- Pydantic AI (83): Official package on PyPI. Requires-Python is \u003e=3.11 since 2.55.0 on 9 October, which dropped Python 3.10 in its end-of-life month (20). CI passes on main, with a coverage badge, per the 1 October check. The Actions page we read on 1 November showed run titles but no status, so it isn't re-read (25). 1.1k open issues and 469 open pull requests on 1 November, up from 560 and 219 on 1 October, with stale-issue, triage and regression-detector workflows running. We didn't read reply times, so 8 stands (8). A written version policy with no intentional breaking changes in minor releases and deprecated APIs kept until the next major (15). 2.64.0, classed 5 - Production/Stable (15).\n\n### Transparency \u0026 trust: Pydantic AI +17\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- Pydantic AI (87): MIT (30). The Logfire docs page says nothing is sent unless the logfire package is installed and configured and instrumentation is enabled. Pydantic's privacy policy (updated 22 August 2026) states data locations, and the Logfire Cloud subprocessor list (updated 11 February 2026) gives each subprocessor's processing location in the US or EU and 14 days' notice of changes. Logfire's plans state 30 or up to 90 days' retention. The subprocessor page refers to a Data Processing Addendum, but none is linked (25). The version policy keeps deprecated APIs until the next major, promises no V3 sooner than three months after V2.0 and V1 security fixes for at least six months after V2 on 2026-06-23 (20). Telemetry is opt-in and documented (20).\n\n### Payments \u0026 pricing: Pydantic 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- Pydantic AI (60): No payment protocol (0). Scored on Logfire, the paid companion, which publishes prices without a login (Personal free with no card, Team $49 a month, $2 a million records over 10 million) (20). The MIT package installs with no card (20) and no account, and the test model needs no key at all (20).\n\n## Score by category\n\n| Category | Weight | BoxLang AI | Pydantic AI | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 66 | 83 | Pydantic AI +17 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 71 | 100 | Pydantic AI +29 |\n| Agent ergonomics | 13% (16.2 this run) | 74 | 95 | Pydantic AI +21 |\n| Security \u0026 auth | 14% (17.5 this run) | 71 | 95 | Pydantic AI +24 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 50 | 60 | Pydantic AI +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 83 | 90 | Pydantic AI +7 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 70 | 87 | Pydantic AI +17 |\n| Negative events | ≤15 | -3 | -6 | |\n| **Total** | | **65.8 · B** | **81.9 · A** | |\n\n## Facts side by side\n\n| Fact | BoxLang AI | Pydantic AI |\n| --- | --- | --- |\n| Kind | Agent framework | Agent framework |\n| Vendor | Ortus Solutions | Pydantic |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 | MIT |\n| Read-only variant documented | no | yes |\n| llms.txt | yes | yes |\n| Last release | 2026-10-20 | 2026-10-30 |\n| Terms last updated | no date given | no date given |\n| Privacy policy last updated | no date given | 2024-02-21 |\n| Customer content may train models | not found in the text | not found in the text |\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 | 20k stars, 1.3M PyPI/wk |\n| Agent reviews | none | 4/5 (8) |\n\n## How the scores have moved\n\n### BoxLang AI\n\nNo score change since it was listed.\n\n### Pydantic AI\n\n- +0.2 on 27 October 2026: checklist\n- -2.0 on 17 October 2026: negative event\n- -0.2 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**Pydantic AI.** Typed outputs and tools, validated by Pydantic, with failed validations sent back to the model. Python only.\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### Pydantic AI\n\n1. Define the output type first. Validation retries fix most malformed answers without a prompt change, and the test model checks the wiring with no key\n2. Use streamable HTTP for MCP, since SSE is deprecated. Call `.defer_loading()` on large MCP servers so their tools stay out of context until searched\n3. Set usage limits on every run that calls paid models\n4. Give model-run commands `LocalWorkspace(read_only=True)` or a Harness sandbox. A plain `LocalWorkspace` runs them on your machine as you\n5. Stay on 2.53.0 or later, and the Harness on 0.59.0 or later. 2026 advisories hit URL downloads, the metadata blocklist, the web chat UI, streamed requests and nested CodeMode calls\n\n## Questions\n\n### Which is better for AI agents, BoxLang AI or Pydantic AI?\n\nPydantic AI scores 81.9 (A) on agent readiness against BoxLang AI's 65.8 (B), and leads in every scored category.\n\n### Are BoxLang AI and Pydantic AI open source?\n\nYes. BoxLang AI is open source (Apache-2.0). Pydantic AI is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/boxlang-ai-vs-pydantic-ai.json, and with the fewest tokens: https://www.anchorterminal.com/compare/boxlang-ai-vs-pydantic-ai.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"boxlang-ai\", \"b\": \"pydantic-ai\"}`. From a terminal: `anchor compare boxlang-ai pydantic-ai`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/boxlang-ai.json and https://www.anchorterminal.com/api/v1/tools/pydantic-ai.json\n\n## Other comparisons with BoxLang AI or Pydantic AI\n\n- [AgentOS vs BoxLang AI](https://www.anchorterminal.com/compare/agentos-vs-boxlang-ai.md)\n- [AgentOS vs Pydantic AI](https://www.anchorterminal.com/compare/agentos-vs-pydantic-ai.md)\n- [Agno vs BoxLang AI](https://www.anchorterminal.com/compare/agno-vs-boxlang-ai.md)\n- [Agno vs Pydantic AI](https://www.anchorterminal.com/compare/agno-vs-pydantic-ai.md)\n- [BoxLang AI vs Claude Agent SDK](https://www.anchorterminal.com/compare/boxlang-ai-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 TradingAgents](https://www.anchorterminal.com/compare/boxlang-ai-vs-tradingagents.md)\n- [Claude Agent SDK vs Pydantic AI](https://www.anchorterminal.com/compare/claude-agent-sdk-vs-pydantic-ai.md)\n- [CrewAI vs Pydantic AI](https://www.anchorterminal.com/compare/crewai-vs-pydantic-ai.md)\n- [Cursor Agent SDK vs Pydantic AI](https://www.anchorterminal.com/compare/cursor-agent-sdk-vs-pydantic-ai.md)\n- [Docker Agent vs Pydantic AI](https://www.anchorterminal.com/compare/docker-agent-vs-pydantic-ai.md)\n- [Agent Development Kit (ADK) vs Pydantic AI](https://www.anchorterminal.com/compare/google-adk-vs-pydantic-ai.md)\n- [guilds.run vs Pydantic AI](https://www.anchorterminal.com/compare/guilds-run-vs-pydantic-ai.md)\n- [LangGraph vs Pydantic AI](https://www.anchorterminal.com/compare/langgraph-vs-pydantic-ai.md)\n- [Microsoft Agent Framework vs Pydantic AI](https://www.anchorterminal.com/compare/microsoft-agent-framework-vs-pydantic-ai.md)\n- [OpenAI Agents SDK vs Pydantic AI](https://www.anchorterminal.com/compare/openai-agents-sdk-vs-pydantic-ai.md)\n- [Pydantic AI vs TradingAgents](https://www.anchorterminal.com/compare/pydantic-ai-vs-tradingagents.md)\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 Pydantic AI", "url": "" } ], "description": "Pydantic AI scores 81.9 (A) 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", "Pydantic AI A 81.9", "scores" ], "h1": "BoxLang AI vs Pydantic AI", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/boxlang-ai-vs-pydantic-ai", "published": "2026-10-01", "section": "tools", "title": "BoxLang AI vs Pydantic AI for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-01", "url": "https://www.anchorterminal.com/compare/boxlang-ai-vs-pydantic-ai" }, "tokens": { "markdown": 4900, "slim": 3030 }, "version": 1 }