Agno vs BoxLang AI

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.

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.

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.

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.

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).

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.

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.

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.