YYing-Kai-LiaoBrowser & computer use

jev-browser (Ying-Kai-Liao)

Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.

Explore repository

How it uses Jev

Browser automation where an LLM plans and Jev decides.

Getting started

On older Claude Code versions, add the marketplace first:

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to jev-browser (Ying-Kai-Liao)

Browse all
jev-browse (0x7067) project preview

jev-browse (0x7067)

Browser & computer use
Browser automation with Jev (TypeSafe) as decision model
0Made by0x70673
jev-ra project preview

jev-ra

Browser & computer use
Browser use for coding agents, 3-5x faster than browser-use. MCP server + CLI; TypeSafe Jev decides every step in ~300 ms.
BMade bybrnyxx4
jev-browser (tontoko) project preview

jev-browser (tontoko)

Browser & computer use
One grounded Jev/Playwright core: typed SDK, persistent CLI, and MCP server with native browser operations and deterministic assertions.
TMade bytontoko7
jevwire project preview

jevwire

Agent tooling
Jev decision layer for agents: MCP server, embeddable DecisionModel library, and an escalate-only Claude Code plugin (TypeSafe AI's Jev)
BMade byBrainwires18
jev-deepresearch project preview

jev-deepresearch

Benchmarks & research
Deep research crawl where Jev (a System One model) makes every per-page decision and an LLM only plans and writes
TMade bytashfeenahmed2
jev-align project preview

jev-align

Benchmarks & research
Calibrated alignment verifier for LLM responses and agent plans — powered by Jev
CMade bycaiovicentino4
TypeSafe MCP project preview

TypeSafe MCP

Agent tooling
Bring typed Jev judgments to your coding assistant through a single MCP server.
IMade byitsmostafa292
typesafe-oracles project preview

typesafe-oracles

Benchmarks & research
Evaluating TypeSafe's System One primitives (Choice/Score/Noul) — where a typed oracle beats an LLM call
TMade bytrophee-bot0
dsh-jev-adapter project preview

dsh-jev-adapter

Agent tooling
Use the Jev (System One) decision-model paradigm with any OpenAI-compatible LLM — no TypeSafe key required. A jev_decide tool for DeepSeek Harness (dsh).
BMade byBetterZflyee2