StackMap
Subscribe

jev-ultrafast vs typesafe-computer-use

Browser Use's speed experiment: Jev picks the operation and the target element from an indexed action space in one request, and a small LLM writes text only when typing is needed. — versus — macOS computer-use loop at ~$0.0002/step: OCR + accessibility tree read the screen, a TypeSafe classifier picks the next action, code clicks; an LLM writes only free text.

The curated verdict

Same pattern for the browser: a Jev decision picks the operation and target from an indexed action space instead of a frontier-model plan.

jev-ultrafasttypesafe-computer-use
Stars24k1.3k
Forks1.9k123
LanguagePythonPython
LicenseMITMIT
Last activity3 days ago1 months ago
Topicsweb, agentsagents, decision-models
Curated connections56

jev-ultrafast — the curator's take

Read this one for the architecture even if you never run it: the page becomes a numbered element table, Jev answers operation and target as speculative parallel heads in a single round trip, and a small LLM is called only for TYPE_TEXT. That is why Zurich-to-London on Google Flights lands in ~7s with no screenshots in the loop. The safety properties are the interesting part - model output never becomes selectors, coordinates, shell or JS; every target resolves to an observed DOM node and is rechecked for occlusion before input. Use it when latency is the product. Don't reach for it as a general agent: the action space is eight fixed operations, it needs a hosted TypeSafe key plus a text-model key, and browser-use proper is what you want for long, tool-rich, recoverable workflows.

typesafe-computer-use — the curator's take

Use it when per-step cost and latency matter more than raw capability: cheap, gated, replayable desktop automation with a confidence number per action. Skip it when tasks need real visual reasoning — anything the frontier model infers from pixels must be rebuilt as deterministic state — and remember it drives your real mouse, needs a paid TypeSafe key, and Windows is experimental.