BrowserAct vs jevcrawl

BrowserAct 23

Hosted reading. No status page found (0) and no readable incident history (5). The docs say there are no rate limits, and give concurrency by plan (2 free, up to 20 for paid API users) and a 7-hour task cap (8). No 429 or retry guidance, and no idempotency keys on task creation (0). No SLA (0). No beta label on the API or MCP server (10). 0 + 5 + 8 + 0 + 0 + 10 = 23.

jevcrawl 68

Read as local software, though crawl and map also depend on TypeSafe's hosted Jev API. Installs from PyPI with Python 3.11 or later stated (20). CI runs ruff, mypy strict and the offline tests on Python 3.11 and 3.13, and every CI run on main from 11 to 15 October 2026 passed, per the 15 October check; the workflow is unchanged, and run results couldn't be read on 2 November (25). Eight issues, all opened by the maintainer as a roadmap, two closed, per the 15 October check. No outside bug reports were found then, and the project is three weeks old, so there is little record to read (15). Semver tags with GitHub release notes, no CHANGELOG file, v0.1.0's notes only a commit link, and breaking changes not marked (8). Version 0.2.0, still classified Development Status 3 Alpha (0). 20 + 25 + 15 + 8 + 0 = 68.

BrowserAct 49

Graded on the API, since the MCP tool list isn't published. Task results come back whole, with no field selection found (10). Lists of bots, templates and tasks are paginated (15). Errors carry numeric codes with documented meanings for a few cases (12). No idempotency key on task creation; webhooks and a status endpoint avoid polling loops (5). No official SDK in two languages; the CLI is Python (7). 10 + 15 + 12 + 5 + 7 = 49.

jevcrawl 80

Three compact tools (25). max_pages, max_seconds, return_tokens and limit bound every call, and scrape can return a whole page or only the passages for a goal. No pagination is needed (18). Expected failures come back as {error, message} with a message that says what to do, and stopped_because, degraded and needs_js_urls tell the agent why a result is thin (19). All tools read only and repeats are answered from a local cache at no cost, but there are no readOnlyHint or idempotentHint annotations (10). Only goal and start_url are required, with measured defaults. The Python library is usable but undocumented (an open issue), and there is one language (8).

BrowserAct 41

One account-wide API key type, revocable and listed with last-used time, but without scopes or expiry (18). Confirmation Required mode holds purchases and asset creation or deletion for approval in the BrowserAct page (14). Scraped pages are untrusted, and no prompt-injection guidance was found (3). Keys show last use and runs keep logs (6). No security page, disclosure policy, certification or bug bounty found (0). 18 + 14 + 3 + 6 + 0 = 41.

jevcrawl 59

Read with the API and MCP lines, since the server runs locally but sends data to a hosted API. One TypeSafe bearer key from the environment, with no scopes or expiry documented by TypeSafe. The README says the key is never written to disk or logs (20). Every tool only reads, a crawl stays on the start host, and robots.txt is followed by default. There is still no check against private, loopback or link-local addresses in the source on 2 November, so an agent can be steered to internal hosts. The unreleased 26 October change skips redirects off the crawl's hosts (12). Pages are untrusted content. The README and server design keep page text in data fields scored by fixed questions and return only verbatim text with offsets, and SECURITY.md names a change in fetch behaviour through page content as in scope. These are the author's claims, untested by us (12). Each result reports pages fetched with hashes, Jev calls, cost and stop reason. No persistent call log (7). SECURITY.md with GitHub private reporting and a one-week answer. No bounty, no advisories yet, and TypeSafe publishes no security.txt (8).

BrowserAct 61

browser-act-cli 1.6.2 on 5 November 2026, read from PyPI's release feed (30). Six CLI releases from 15 October to 5 November (20). A closed service with a support address, but no public changelog or issue tracker found (8). No official SDKs and no entry in the official MCP registry (0). The CLI package carries no licence or repository in its metadata (3). 30 + 20 + 8 + 0 + 3 = 61.

jevcrawl 68

v0.2.0 on 15 October 2026, 18 days before 2 November (30). Three releases between 13 and 15 October 2026 (20). One later change, the merged audit-fixes pull request of 26 October (redirect scope, per-step time limits, a 50 MB cap on gzip sitemaps), is in no release yet. No outside issues or pull requests were found on 15 October, and GitHub's issue pages couldn't be read on 2 November (8 of 25). Not in the official MCP registry, which returned no server for jevcrawl on 2 November (0). Current dependencies, a uv.lock, CI and PyPI trusted publishing in the workflows (10). 30 + 20 + 8 + 0 + 10 = 68.

BrowserAct 44

Closed service with published terms naming the operating company and governing law (15). The privacy policy of 15 May 2025 states retention by category and that crawled data is kept per plan and deletable by the user (15). No deprecation policy or notices found (0). No sub-processors or data locations named (3). 15 + 15 + 0 + 3 = 33.

jevcrawl 51

Apache-2.0 in LICENSE, pyproject.toml and as detected by GitHub (30). The README says plainly that page text, link labels and URLs go to TypeSafe and that answers are cached locally. TypeSafe's policies agree on no training but give no retention period, and jevcrawl has no privacy statement of its own (15). No deprecation policy. The model version is pinned and changes are in release notes (3). No telemetry or analytics found in the source. Outbound traffic is the target site and api.typesafe.ai, both stated in the README, so there is nothing hidden to opt out of, though no explicit telemetry statement exists (15).

BrowserAct 76

An OpenAPI 3.0.3 document behind the API reference (25). llms.txt on both the site and the docs, with Markdown pages (10). Endpoint descriptions explain the run flow (find a bot, read its input_schema, then run) and when to use the lighter status endpoint (14). Inputs are typed, but a run's input is an object shaped by each bot's own schema (10). Examples per endpoint and named error codes such as 10879 and 10127; no full error table found (10). The path carries v3, but no changelog was found (7). 25 + 10 + 14 + 10 + 10 + 7 = 76.

jevcrawl 81

Typed JSON Schema inputs on all three tools, generated from the Python signatures, with required parameters marked (25). No llms.txt. The repository ships an agent skill, skills/jevcrawl/SKILL.md, as Markdown for agents (5). Tool descriptions and server instructions say when to use crawl, scrape and map, how to phrase a goal and how to read each stop reason (18). Integer and number types with defaults, but the minimums the code enforces are not in the schema and stopped_because is documented as prose, not an enum (10). A real result in the README, and error codes listed in the skill with what each means (13). Semver releases with notes, and the Jev model version pinned per release (10).