BbrnyxxBrowser & computer use

jev-ra

Browser use for coding agents, 3-5x faster than browser-use. MCP server + CLI; TypeSafe Jev decides every step in ~300 ms.

Explore repositoryVisit website

How it uses Jev

Site: brnyxx.github.io/jev-ra replays a real recorded run and explains the pipeline.

Getting started

sh export OPENROUTER API KEY=sk-or-... uvx jev-ra install claude

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

Keep exploring

Similar to jev-ra

Browse all
jev-browser project preview

jev-browser

Browser & computer use
Browser use using Typesafe's Jev model
JMade byjkudish257
jev-browser (Ying-Kai-Liao) project preview

jev-browser (Ying-Kai-Liao)

Browser & computer use
Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.
YMade byYing-Kai-Liao82
ego-jev (jiangkoumo) project preview

ego-jev (jiangkoumo)

Browser & computer use
Drive the ego lite browser with Jev (TypeSafe System One): one indexed element table in, one operation + target out, single process. ~2x faster than a per-step LLM loop in our measurements.
JMade byjiangkoumo4
jev-harness (TypeSafeAI) project preview

jev-harness (TypeSafeAI)

Agent tooling
A custom coding harness for TypeSafe AI's Jev: an LLM proposes, Jev answers narrow questions, code decides, every step leaves a receipt.
TMade byTypeSafeAI8
jev-engineering project preview

jev-engineering

Agent tooling
Decision layer for coding agents: deterministic rules before any model call, then one Jev request, as a Claude Code PreToolUse hook, an MCP server, a loopback service and a team policy that personal overrides can tighten but not loosen. Ships the 300-call injection kit behind its own numbers.
EMade byeugeniughelbur2
jev-mcp (blakestone-x) project preview

jev-mcp (blakestone-x)

Agent tooling
MCP server for TypeSafe Jev: typed classify, score, check, match and screen for any agent, with confidence on every answer
BMade byblakestone-x22
siftr project preview

siftr

Benchmarks & research
Fast, cheap judgment for AI coding agents: semantic search, focused reads and list picking in ~2s. CLI + MCP server on TypeSafe Jev. Benchmarked on SWE-bench.
BMade byBentlybro2
daf-jev project preview

daf-jev

Benchmarks & research
daf-jev: composable Python toolkit for TypeSafe's Jev (System One) decision API — question builders, confidence gates, evaluator, calibration, CLI, MCP server, agent skill
DMade bydocxology6
llama-index-jev project preview

llama-index-jev

Integrations
LlamaIndex reranker + router powered by TypeSafe Jev — typed scores/choices, cheaper than LLM-as-judge.
WMade byWiktorB20044