AgentOS vs BoxLang AI

AgentOS 92

Typed TypeScript API with a TypeDoc reference (25). llms.txt on agentos.sh and docs.agentos.sh (10). The guides say which surface to reach for, for example agency-level approval for most apps and workflow nodes for an explicit graph, and the tool-forging docs state what each executor does not isolate (16). Tools take Zod schemas (15). 22 runnable examples and a cookbook, with CLI error codes documented but no single page for the library's error classes found (11). Release notes are generated for every release and published as GitHub releases under written version rules. The CHANGELOG.md on master still stops at 0.13.150 of 15 October, and the GitHub releases page couldn't be read on 1 November, so release notes were read from the tagged commits (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.

AgentOS 77

Official npm package with Node 22 or newer stated in package.json on 1 November (20). A public CI workflow builds, lints, type-checks and runs the tests with coverage, and the 12 most recent runs on master on 8 October 2026 passed, per the 8 October check, not re-read on 1 November (25). 16 open issues and pull requests in total, most filed by the maintainer, with one outside suggestion from 12 September unanswered, per the 8 October check, not re-read on 1 November (20). Written release rules give a breaking change a minor version, and a workflow fails a pull request with a breaking-change marker unless a maintainer approves it, but feature commits ship as patches and breaking minors 0.11.0 and 0.12.0 (7 October), 0.13.0 (8 October), 0.14.0 (17 October) and 0.15.0 (21 October, two persona changes marked BREAKING CHANGE) landed within two weeks (12). Version 0.15.69, not declared stable (0). 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.

AgentOS 81

No analytics or telemetry code found in the source, and the privacy and security pages say the runtime sends nothing to the vendor. OpenTelemetry is off by default and the host installs the exporter (30). Approval gates on five triggers, five security tiers and a rule that composed tools chain a side-effecting step only when the host lists it. Agent-written code runs by default in an in-process node:vm context with a 5-second limit and no memory cap, off unless the host enables it. An optional QuickJS executor runs each call in its own WebAssembly instance with a memory cap. No gate is on unless configured (17). SECURITY.md names model output, tool results and retrieved content as untrusted input, and injection detection is an opt-in extension pack. The security page says that pack's default ONNX model has no prompt-injection label, so injection is scored only when that model can't load, and points to a phrase-list guard (11). OpenTelemetry spans, a usage ledger, a reasoning trace and an opt-in signed audit log (15). SECURITY.md with a private advisory form, acknowledgement in 5 business days and disclosure at 90 days, and the site's security page now gives the same times. No security.txt, no bounty and no published advisory found (8). 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.

AgentOS 60

No payment protocol (0). Self-hosted rule. The package is free under Apache 2.0 with nothing to buy (20), installs with no card (20) and needs no account (20). No paid tier of AgentOS was found.

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.