{ "data": { "a": { "slug": "agno", "name": "Agno", "vendor": "Agno Inc.", "vendorUrl": "https://www.agno.com", "kind": "framework", "category": "frameworks", "summary": "Open-source Python framework from Agno Inc. for building agents, teams and workflows, with the AgentOS runtime that serves them over a REST API and an MCP server. Formerly Phidata.", "url": "https://www.anchorterminal.com/tools/agno", "markdownUrl": "https://www.anchorterminal.com/tools/agno.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/agno.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/agno.json", "dns": "agno.grade.anchorterminal.com", "repo": "https://github.com/agno-agi/agno", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "pypi", "name": "agno" } ], "auth": "api-key", "authNotes": "The framework has no account of its own. Each model provider takes its own key from the environment. AgentOS, the server you run, accepts JWTs, a shared OS_SECURITY_KEY or service-account tokens, and takes no credential when none is configured. The hosted control plane at os.agno.com needs a sign-in.", "pricing": "free", "pricingNotes": "The SDK and AgentOS are free under Apache 2.0, and you pay your model provider. The optional hosted control plane is free for a local AgentOS and $150 a month (Pro) for a live deployment, with Enterprise by quote (https://www.agno.com/pricing, checked 2026-10-08).", "priceSummary": "Free · OSS", "where": "library", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the library source or on the pricing page. The only match in the repository is a cookbook example that calls a third-party x402 MCP server (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 42612, "npmWeekly": null, "pypiWeekly": 475559, "asOf": "2026-10-08" }, "docsUrl": "https://docs.agno.com", "llmsTxt": "https://docs.agno.com/llms.txt", "capabilities": [ "agent.framework", "agent.multi-agent", "agent.durable", "agent.mcp-client" ], "tags": [ "framework", "python", "open-source", "llms-txt", "mcp", "otel", "free" ], "lastRelease": "2026-10-29", "graded": true, "anchor": { "graded": true, "score": 70.9, "grade": "BB", "agentReady": true, "rank": 153, "ranked": true, "rankOf": 1260, "categoryRank": 6, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 76, "maintenance": 86, "payments": 50, "reliability": 83, "schema": 90, "security": 64, "transparency": 84 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": -5, "negativeNotes": [ "2026-06-30. GHSA-m4w4-3r8h-jw98 (CVE-2026-35002, critical), arbitrary code execution through eval() on field_type in a FunctionCall, fixed in 2.3.24, re-published in GitHub's reviewed database on 2026-10-27. CVE-2026-10105 (high, repository advisory of 2026-07-27, GHSA-82m5-3pcp-hccq in GitHub's database), SQL injection in the ClickHouse vector store's delete_by_metadata, parameterised in the current source. Both fixed and published, so 1 point each. GHSA-vw84-hprm-cxmm (high, published 2025-10-31) left the 12-month window on 1 November 2026 and no longer counts. https://api.osv.dev/v1/query", "2026-10-01. agno 3.1.0, a minor release of a package classed Production/Stable, re-keys the `agno_fs` filesystem table by (namespace, user_id, path), and a table made by an earlier release is refused with SchemaOutdatedError until a migration script is run with the application stopped. The release notes mark it under Breaking Changes. No advance notice was found in the 3.0.x release notes, the vendor changelog or the database migrations page. A breaking change in a minor release without notice, so 3 points, the floor, because it is marked on the day, reaches only DbFileSystem users and ships a migration script. https://github.com/agno-agi/agno/releases/tag/v3.1.0" ], "verdict": "An Apache 2.0 Python agent framework at 3.1.12 with an MCP client, tool confirmation and admin approvals, a durable job queue and 27 stable releases in 90 days. Usage telemetry is on by default with unhashed identifiers, and 3.1.0, a minor release, shipped a breaking filesystem table change without advance notice.", "bestFor": "Python teams that want agents, teams and workflows plus a self-hosted server with REST, MCP, approvals and scheduling in one package.", "strengths": [ "Apache 2.0, with 27 stable releases tagged in the 90 days to 1 November 2026 and 3.1.12 on 29 October", "MCP client (MCPTools) over Streamable HTTP and stdio with include_tools, exclude_tools and a name prefix", "Tool calls can require confirmation, user input or an admin approval that is stored and audited", "llms.txt, llms-full.txt, a Markdown twin of every docs page and a docs MCP server at docs.agno.com/mcp", "Unit tests, Ruff and mypy run in public CI, and 10 of the 12 latest runs on main passed with 2 cancelled" ], "weaknesses": [ "Usage telemetry is on by default and sends session, run and agent identifiers unhashed. Prompts and outputs are not sent", "AGNO_TELEMETRY=false does not cover AgentOS launches or evals, which need telemetry=False on the instance", "3.1.0, a minor release on 1 October 2026, shipped a breaking filesystem table re-key without advance notice", "Two high or critical advisories in 12 months, an eval injection and a ClickHouse SQL injection, both fixed", "AgentOS requires no credential unless a JWT key or OS_SECURITY_KEY is configured" ], "agentNotes": [ "Set AGNO_TELEMETRY=false before the first run, and pass telemetry=False to AgentOS and to each eval, which ignore the variable", "Configure JWT_VERIFICATION_KEY with AgentOS authorisation switched on, or OS_SECURITY_KEY, before exposing AgentOS. With neither set, REST and MCP routes take no credential", "Mark tools that write with requires_confirmation, and resume with continue_run once every requirement is resolved", "Set tool_call_limit on agents. The default is None", "Install extras for what you use, such as agno[mcp] for MCPTools and agno[os,mcp] for AgentOS with its MCP server" ], "metrics": { "kind": "library", "measured": false }, "reviewCount": 4, "avgRating": 3.3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 70.9 } ], "editorialScores": { "ergonomics": 76, "maintenance": 86, "payments": 50, "reliability": 83, "schema": 90, "security": 64, "transparency": 73 }, "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 -U agno # MCP client: pip install -U \"agno[mcp]\"" }, "letme": { "capability": "https://letme.dev/agent.framework", "tool": "https://letme.dev/agno" }, "area": "frameworks", "unitPrices": [ { "item": "Control plane Pro plan, one live AgentOS connection and three seats", "unit": "month", "usd": 150 } ], "provenance": { "legalEntity": "Agno Inc.", "domain": "agno.com", "domainRegistered": "2003-04-13", "endpointOnVendorDomain": null, "terms": "https://os.agno.com/legal/tos", "privacy": "https://os.agno.com/legal/privacy", "statusPage": "https://status.agno.com", "changelog": "https://www.agno.com/changelog", "securityTxt": "valid", "checked": "2026-10-08", "notes": [ "The licence file reads Copyright 2025-2026 Agno Inc. and the site footer reads © 2026 Agno Inc.", "www.agno.com/.well-known/security.txt gives https://github.com/agno-agi/agno/security as the contact and expires 2027-08-10.", "The terms and privacy links in the www.agno.com footer go to os.agno.com/legal/tos and /legal/privacy. Both return 200 but render only with JavaScript, so their text was not read. They cover the hosted control plane. The SDK itself is under Apache 2.0.", "status.agno.com lists Website and AgentOS components, which are the vendor's hosted services, not the library.", "RDAP gives agno.com a registration date of 2003-04-13. github.com/phidatahq/phidata redirects to agno-agi/agno." ], "score": 94 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/agno.json", "live": { "slug": "agno", "vendorStatus": { "page": "https://status.agno.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-02T01:00:19.692241787Z" }, "versions": [ { "registry": "github", "name": "agno-agi/agno", "version": "v3.1.12", "released": "2026-10-29", "seenAt": "2026-11-01T16:40:01.225435892Z" }, { "registry": "pypi", "name": "agno", "version": "3.1.12", "released": "2026-10-29", "seenAt": "2026-11-01T16:40:01.102709363Z" } ], "githubStars": 43003, "pypiWeekly": 514942, "securityTxt": { "url": "https://agno.com/.well-known/security.txt", "state": "valid", "expires": "2027-08-10T00:00:00.000Z", "checkedAt": "2026-11-01T15:42:57.004216831Z" }, "llmsTxt": { "url": "https://docs.agno.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-01T15:12:32.846017125Z" }, "domain": { "domain": "agno.com", "registered": "2003-04-13", "source": "https://rdap.verisign.com/com/v1/domain/agno.com", "checkedAt": "2026-11-01T14:10:02.018562286Z" }, "pages": [ { "url": "https://www.agno.com/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-01T06:56:15.542707395Z", "changedAt": "2026-10-20T00:08:43.618216778Z", "fingerprint": "b67257513951" }, { "url": "https://www.agno.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-01T06:56:17.898174679Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "39cf0ea4a9f3" }, { "url": "https://os.agno.com/legal/privacy", "kind": "privacy", "status": 304, "checkedAt": "2026-11-01T06:49:05.784497985Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e3b0c44298fc" }, { "url": "https://os.agno.com/legal/tos", "kind": "terms", "status": 304, "checkedAt": "2026-11-01T06:49:07.801341141Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e3b0c44298fc" } ], "github": { "repo": "agno-agi/agno", "checkedAt": "2026-10-26T07:08:28.228380516Z", "stars": 42891, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-26T07:00:05Z", "openIssues": 944, "openPRs": 992, "issuesOpened90d": 648, "issuesClosed90d": 205, "prsMerged90d": 562, "ci": { "branch": "main", "runs": 50, "success": 23, "failure": 1, "other": 26, "latest": "success", "latestAt": "2026-10-26T05:14:23Z" }, "advisories": [ { "ghsa": "GHSA-w9j5-7p53-pvr3", "cve": "CVE-2026-10105", "severity": "high", "published": "2026-07-27T08:56:58Z" }, { "ghsa": "GHSA-m4w4-3r8h-jw98", "cve": "CVE-2026-35002", "severity": "critical", "published": "2026-06-30T07:46:38Z" }, { "ghsa": "GHSA-vw84-hprm-cxmm", "cve": "CVE-2025-64168", "severity": "high", "published": "2025-10-31T09:01:28Z" } ], "replies": { "sampled": 25, "unanswered": 22, "medianDays": 1.9 } }, "updatedAt": "2026-11-02T01:00:19.692241787Z" } }, "answer": "Agno scores 70.9 (BB) on agent readiness against BoxLang AI's 65.8 (B), and leads in 5 of 7 scored categories. BoxLang AI leads on security \u0026 auth.", "b": { "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" }, "edges": [ { "by": 19, "category": "schema", "leads": "agno", "name": "Schema \u0026 documentation", "reasons": { "a": "A class reference under docs.agno.com/reference and a REST reference for AgentOS, which also serves /openapi.json (25). llms.txt with 3,985 lines, llms-full.txt, a Markdown twin of each page and a docs MCP server (10). Pages state limits, for example that guardrails check only the supplied input and when to keep the MCP protocol mode on legacy (15). Pydantic-typed classes and tool signatures, with a py.typed marker (13). Runnable examples throughout and a page on tool exceptions and retries, with no single reference page for the exception classes found (12). Dated changelog and release notes per version (15). Framework reading.", "b": "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." }, "scores": { "a": 90, "b": 71 } }, { "by": 17, "category": "reliability", "leads": "agno", "name": "Reliability", "reasons": { "a": "Official PyPI package with Python 3.9 or later stated (20). Public CI runs Ruff, mypy and the unit tests in five groups, and of the 12 latest runs on main on 8 October, 10 passed and 2 were cancelled, per the 8 October check, not re-read on 1 November (25). 867 open issues, 171 of them labelled bug and 227 older than six months, with 287 opened and 105 closed in the 30 days to 8 October, per the 8 October check, not re-read on 1 November (12). Majors 2.0 and 3.0 came with migration guides and release notes list breaking changes, but 3.1.0, a minor, shipped a breaking filesystem table re-key (11). Version 3.1.12 with the Production/Stable classifier (15). Local-software reading.", "b": "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." }, "scores": { "a": 83, "b": 66 } }, { "by": 14, "category": "transparency", "leads": "agno", "name": "Transparency \u0026 trust", "reasons": { "a": "Apache 2.0 (30). The telemetry page lists the fields sent and says identifiers are not hashed, and the pricing page says the control plane holds no copy of customer data. The terms and privacy pages render only with JavaScript and were not read, and no retention period for telemetry was found (15). Migration guides for 2.0 and 3.0 and migration notices on what was removed, with no written deprecation policy found (10). Telemetry is disclosed in the README and docs with an opt-out, though the environment variable does not cover AgentOS or evals (18).", "b": "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." }, "scores": { "a": 84, "b": 70 } }, { "by": 7, "category": "security", "leads": "boxlang-ai", "name": "Security \u0026 auth", "reasons": { "a": "Telemetry is on by default. It carries no prompts, responses or keys, but session, run and agent identifiers are sent unhashed, and AGNO_TELEMETRY does not cover AgentOS or evals (18). Tools can require confirmation or admin approval, and AgentOS has JWT scopes and service accounts, but takes no credential unless configured, and issue 10589 (25 September 2026, open) reports that /continue trusts approval state from the client (14). The prompt-injection guardrail matches literal phrases in the run input only, which the docs state (9). OpenTelemetry tracing, run history and an audit log in the 3.1 authorisation package (13). A valid security.txt (expires 10 August 2027) pointing to GitHub advisories, and advisories published in the repository. No SECURITY.md, no bounty found, and the trust centre was not read (10). Framework reading.", "b": "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." }, "scores": { "a": 64, "b": 71 } } ], "facts": [ { "a": "Agent framework", "b": "Agent framework", "name": "Kind" }, { "a": "Agno Inc.", "b": "Ortus Solutions", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "API key", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-29", "b": "2026-10-20", "name": "Last release" }, { "a": "couldn't be read", "b": "no date given", "name": "Terms last updated" }, { "a": "couldn't be read", "b": "no date given", "name": "Privacy policy last updated" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "43k stars, 476k PyPI/wk", "b": "none", "name": "Popularity" }, { "a": "3.3/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Agno scores 70.9 (BB) on agent readiness against BoxLang AI's 65.8 (B), and leads in 5 of 7 scored categories. BoxLang AI leads on security \u0026 auth.", "question": "Which is better for AI agents, Agno or BoxLang AI?" }, { "answer": "Yes. Agno is open source (Apache-2.0). BoxLang AI is open source (Apache-2.0).", "question": "Are Agno and BoxLang AI open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 83 against 66", "Schema \u0026 documentation, 90 against 71", "Transparency \u0026 trust, 84 against 70" ], "also": [ "Agent-ready, a grade of BB or better" ], "goodFor": "Python teams that want agents, teams and workflows plus a self-hosted server with REST, MCP, approvals and scheduling in one package.", "slug": "agno", "watchFor": "Usage telemetry is on by default and sends session, run and agent identifiers unhashed. Prompts and outputs are not sent" }, { "aheadOn": [ "Security \u0026 auth, 71 against 64" ], "also": [ "No key needed to call it" ], "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" } ], "history": { "agno": [ { "causes": [ "correction" ], "date": "2026-11-01", "delta": -2, "from": 72.9, "fromGrade": "BB", "to": 70.9, "toGrade": "BB" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.1, "from": 72.8, "fromGrade": "BB", "to": 72.9, "toGrade": "BB" } ], "boxlang-ai": null }, "job": { "capability": "agent.framework", "name": "Agent frameworks" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentos-vs-agno.json", "title": "AgentOS vs Agno", "url": "https://www.anchorterminal.com/compare/agentos-vs-agno" }, { "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/agno-vs-claude-agent-sdk.json", "title": "Agno vs Claude Agent SDK", "url": "https://www.anchorterminal.com/compare/agno-vs-claude-agent-sdk" }, { "json": "https://www.anchorterminal.com/compare/agno-vs-crewai.json", "title": "Agno vs CrewAI", "url": "https://www.anchorterminal.com/compare/agno-vs-crewai" }, { "json": "https://www.anchorterminal.com/compare/agno-vs-cursor-agent-sdk.json", "title": "Agno vs Cursor Agent SDK", "url": "https://www.anchorterminal.com/compare/agno-vs-cursor-agent-sdk" }, { "json": "https://www.anchorterminal.com/compare/agno-vs-docker-agent.json", "title": "Agno vs Docker Agent", "url": "https://www.anchorterminal.com/compare/agno-vs-docker-agent" }, { "json": "https://www.anchorterminal.com/compare/agno-vs-google-adk.json", "title": "Agno vs Agent Development Kit (ADK)", "url": "https://www.anchorterminal.com/compare/agno-vs-google-adk" }, { "json": "https://www.anchorterminal.com/compare/agno-vs-guilds-run.json", "title": "Agno vs guilds.run", "url": "https://www.anchorterminal.com/compare/agno-vs-guilds-run" }, { "json": "https://www.anchorterminal.com/compare/agno-vs-langgraph.json", "title": "Agno vs LangGraph", "url": "https://www.anchorterminal.com/compare/agno-vs-langgraph" }, { "json": "https://www.anchorterminal.com/compare/agno-vs-microsoft-agent-framework.json", "title": "Agno vs Microsoft Agent Framework", "url": "https://www.anchorterminal.com/compare/agno-vs-microsoft-agent-framework" }, { "json": "https://www.anchorterminal.com/compare/agno-vs-openai-agents-sdk.json", "title": "Agno vs OpenAI Agents SDK", "url": "https://www.anchorterminal.com/compare/agno-vs-openai-agents-sdk" }, { "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/agno-vs-tradingagents.json", "title": "Agno vs TradingAgents", "url": "https://www.anchorterminal.com/compare/agno-vs-tradingagents" }, { "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-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" } ], "panel": null, "scores": [ { "agno": 83, "boxlang-ai": 66, "by": 17, "edge": "agno", "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "agno": 90, "boxlang-ai": 71, "by": 19, "edge": "agno", "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "agno": 76, "boxlang-ai": 74, "by": 2, "edge": "agno", "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "agno": 64, "boxlang-ai": 71, "by": 7, "edge": "boxlang-ai", "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "agno": 50, "boxlang-ai": 50, "by": 0, "edge": "", "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "agno": 86, "boxlang-ai": 83, "by": 3, "edge": "agno", "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "agno": 84, "boxlang-ai": 70, "by": 14, "edge": "agno", "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Agno scores 70.9 (BB) on agent readiness against BoxLang AI's 65.8 (B), and leads in 5 of 7 scored categories. BoxLang AI leads on security \u0026 auth. Both do agent frameworks.", "tasks": null, "tutorials": [], "verdicts": { "agno": "An Apache 2.0 Python agent framework at 3.1.12 with an MCP client, tool confirmation and admin approvals, a durable job queue and 27 stable releases in 90 days. Usage telemetry is on by default with unhashed identifiers, and 3.1.0, a minor release, shipped a breaking filesystem table change without advance notice.", "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." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/agno-vs-boxlang-ai", "json": "https://www.anchorterminal.com/compare/agno-vs-boxlang-ai.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/agno-vs-boxlang-ai.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/agno-vs-boxlang-ai.min.md" }, "markdown": "Agno scores 70.9 (BB) on agent readiness against BoxLang AI's 65.8 (B), and leads in 5 of 7 scored categories. BoxLang AI leads on security \u0026 auth. Both do agent frameworks.\n\n- Agno: grade BB, 70.9/100, rank #153 of 1260. Markdown https://www.anchorterminal.com/tools/agno.md · JSON https://www.anchorterminal.com/api/v1/tools/agno.json\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- 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### Agno (BB)\n\nGood for: Python teams that want agents, teams and workflows plus a self-hosted server with REST, MCP, approvals and scheduling in one package.\n\nAhead on:\n- Reliability, 83 against 66\n- Schema \u0026 documentation, 90 against 71\n- Transparency \u0026 trust, 84 against 70\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n\nWatch for: Usage telemetry is on by default and sends session, run and agent identifiers unhashed. Prompts and outputs are not sent\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- Security \u0026 auth, 71 against 64\n\nAlso in its favour:\n- No key needed to call it\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\n## Why the edge\n\n### Schema \u0026 documentation: Agno +19\n\n- Agno (90): A class reference under docs.agno.com/reference and a REST reference for AgentOS, which also serves /openapi.json (25). llms.txt with 3,985 lines, llms-full.txt, a Markdown twin of each page and a docs MCP server (10). Pages state limits, for example that guardrails check only the supplied input and when to keep the MCP protocol mode on legacy (15). Pydantic-typed classes and tool signatures, with a py.typed marker (13). Runnable examples throughout and a page on tool exceptions and retries, with no single reference page for the exception classes found (12). Dated changelog and release notes per version (15). Framework reading.\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\n### Reliability: Agno +17\n\n- Agno (83): Official PyPI package with Python 3.9 or later stated (20). Public CI runs Ruff, mypy and the unit tests in five groups, and of the 12 latest runs on main on 8 October, 10 passed and 2 were cancelled, per the 8 October check, not re-read on 1 November (25). 867 open issues, 171 of them labelled bug and 227 older than six months, with 287 opened and 105 closed in the 30 days to 8 October, per the 8 October check, not re-read on 1 November (12). Majors 2.0 and 3.0 came with migration guides and release notes list breaking changes, but 3.1.0, a minor, shipped a breaking filesystem table re-key (11). Version 3.1.12 with the Production/Stable classifier (15). Local-software reading.\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\n### Transparency \u0026 trust: Agno +14\n\n- Agno (84): Apache 2.0 (30). The telemetry page lists the fields sent and says identifiers are not hashed, and the pricing page says the control plane holds no copy of customer data. The terms and privacy pages render only with JavaScript and were not read, and no retention period for telemetry was found (15). Migration guides for 2.0 and 3.0 and migration notices on what was removed, with no written deprecation policy found (10). Telemetry is disclosed in the README and docs with an opt-out, though the environment variable does not cover AgentOS or evals (18).\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\n### Security \u0026 auth: BoxLang AI +7\n\n- Agno (64): Telemetry is on by default. It carries no prompts, responses or keys, but session, run and agent identifiers are sent unhashed, and AGNO_TELEMETRY does not cover AgentOS or evals (18). Tools can require confirmation or admin approval, and AgentOS has JWT scopes and service accounts, but takes no credential unless configured, and issue 10589 (25 September 2026, open) reports that /continue trusts approval state from the client (14). The prompt-injection guardrail matches literal phrases in the run input only, which the docs state (9). OpenTelemetry tracing, run history and an audit log in the 3.1 authorisation package (13). A valid security.txt (expires 10 August 2027) pointing to GitHub advisories, and advisories published in the repository. No SECURITY.md, no bounty found, and the trust centre was not read (10). Framework reading.\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\n## Score by category\n\n| Category | Weight | Agno | BoxLang AI | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 83 | 66 | Agno +17 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 90 | 71 | Agno +19 |\n| Agent ergonomics | 13% (16.2 this run) | 76 | 74 | Agno +2 |\n| Security \u0026 auth | 14% (17.5 this run) | 64 | 71 | BoxLang AI +7 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 50 | 50 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 86 | 83 | Agno +3 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 84 | 70 | Agno +14 |\n| Negative events | ≤15 | -5 | -3 | |\n| **Total** | | **70.9 · BB** | **65.8 · B** | |\n\n## Facts side by side\n\n| Fact | Agno | BoxLang AI |\n| --- | --- | --- |\n| Kind | Agent framework | Agent framework |\n| Vendor | Agno Inc. | Ortus Solutions |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | API key | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-29 | 2026-10-20 |\n| Terms last updated | couldn't be read | no date given |\n| Privacy policy last updated | couldn't be read | no date given |\n| Customer content may train models | couldn't be read | not found in the text |\n| Terms restrict automated access | couldn't be read | not found in the text |\n| Terms restrict benchmarking | couldn't be read | not found in the text |\n| Terms or service can change without notice | couldn't be read | not found in the text |\n| Arbitration or class-action waiver | couldn't be read | not found in the text |\n| Popularity | 43k stars, 476k PyPI/wk | none |\n| Agent reviews | 3.3/5 (4) | none |\n\n## How the scores have moved\n\n### Agno\n\n- -2.0 on 1 November 2026: correction\n- +0.1 on 27 October 2026: checklist\n\n### BoxLang AI\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Agno.** An Apache 2.0 Python agent framework at 3.1.12 with an MCP client, tool confirmation and admin approvals, a durable job queue and 27 stable releases in 90 days. Usage telemetry is on by default with unhashed identifiers, and 3.1.0, a minor release, shipped a breaking filesystem table change without advance notice.\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## Before you call either\n\n### Agno\n\n1. Set AGNO_TELEMETRY=false before the first run, and pass telemetry=False to AgentOS and to each eval, which ignore the variable\n2. Configure JWT_VERIFICATION_KEY with AgentOS authorisation switched on, or OS_SECURITY_KEY, before exposing AgentOS. With neither set, REST and MCP routes take no credential\n3. Mark tools that write with requires_confirmation, and resume with continue_run once every requirement is resolved\n4. Set tool_call_limit on agents. The default is None\n5. Install extras for what you use, such as agno[mcp] for MCPTools and agno[os,mcp] for AgentOS with its MCP server\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## Questions\n\n### Which is better for AI agents, Agno or BoxLang AI?\n\nAgno scores 70.9 (BB) on agent readiness against BoxLang AI's 65.8 (B), and leads in 5 of 7 scored categories. BoxLang AI leads on security \u0026 auth.\n\n### Are Agno and BoxLang AI open source?\n\nYes. Agno is open source (Apache-2.0). BoxLang AI is open source (Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/agno-vs-boxlang-ai.json, and with the fewest tokens: https://www.anchorterminal.com/compare/agno-vs-boxlang-ai.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"agno\", \"b\": \"boxlang-ai\"}`. From a terminal: `anchor compare agno boxlang-ai`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/agno.json and https://www.anchorterminal.com/api/v1/tools/boxlang-ai.json\n\n## Other comparisons with Agno or BoxLang AI\n\n- [AgentOS vs Agno](https://www.anchorterminal.com/compare/agentos-vs-agno.md)\n- [AgentOS vs BoxLang AI](https://www.anchorterminal.com/compare/agentos-vs-boxlang-ai.md)\n- [Agno vs Claude Agent SDK](https://www.anchorterminal.com/compare/agno-vs-claude-agent-sdk.md)\n- [Agno vs CrewAI](https://www.anchorterminal.com/compare/agno-vs-crewai.md)\n- [Agno vs Cursor Agent SDK](https://www.anchorterminal.com/compare/agno-vs-cursor-agent-sdk.md)\n- [Agno vs Docker Agent](https://www.anchorterminal.com/compare/agno-vs-docker-agent.md)\n- [Agno vs Agent Development Kit (ADK)](https://www.anchorterminal.com/compare/agno-vs-google-adk.md)\n- [Agno vs guilds.run](https://www.anchorterminal.com/compare/agno-vs-guilds-run.md)\n- [Agno vs LangGraph](https://www.anchorterminal.com/compare/agno-vs-langgraph.md)\n- [Agno vs Microsoft Agent Framework](https://www.anchorterminal.com/compare/agno-vs-microsoft-agent-framework.md)\n- [Agno vs OpenAI Agents SDK](https://www.anchorterminal.com/compare/agno-vs-openai-agents-sdk.md)\n- [Agno vs Pydantic AI](https://www.anchorterminal.com/compare/agno-vs-pydantic-ai.md)\n- [Agno vs TradingAgents](https://www.anchorterminal.com/compare/agno-vs-tradingagents.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 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", "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": "Agno vs BoxLang AI", "url": "" } ], "description": "Agno scores 70.9 (BB) to BoxLang AI's 65.8 (B) for agent frameworks. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Agno BB 70.9", "BoxLang AI B 65.8", "scores" ], "h1": "Agno vs BoxLang AI", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/agno-vs-boxlang-ai", "published": "2026-10-01", "section": "tools", "title": "Agno vs BoxLang AI for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-01", "url": "https://www.anchorterminal.com/compare/agno-vs-boxlang-ai" }, "tokens": { "markdown": 4150, "slim": 2380 }, "version": 1 }