ego-jev

Jev (TypeSafe System One) inner loop for ego-browser — one ~0.4s typed decision per DOM step instead of an LLM turn. Agent skill for ego lite.

ego lite skill — each DOM step decided in ~0.4s, no LLM turn

How it uses Jev

When I drive multi-step tasks in ego lite — filling a form, setting filters, clicking through menus — the agent pauses before every step: read the snapshot, reason, then act. A ten-step task means ten LLM turns. Then I saw jev-ultrafast run the same kind of loop standalone — Zürich → London on Google Flights in 7.1 s — and ported that inner loop into ego lite, so the agent keeps your real browser, your sessions and…

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 ego-jev

Browse all
jev-browser-skill (ChenYCL) project preview
Browser & computer use
Browser use & computer use for coding agents, powered by TypeSafe Jev: calibrated judgments from a System One model, control loop in code. ego lite / Chrome / Safari · CLI + MCP
ego-jev (jiangkoumo) project preview
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.
jev-ego project preview
Browser & computer use
TypeScript browser agent for ego lite: Jev Ultrafast indexed actions, TypeSafe Jev decisions, persistent observe/act CLI. No Chrome or Playwright.
ego-jev-ultrafast project preview
Benchmarks & research
Jev drives your Ego Lite browser: one typed-choice request per step. Single-file, zero-dependency port of browser-use/jev-ultrafast with multi-model benchmarks and extra guardrails. Unofficial.
jev-agent-hooks project preview
Agent tooling
TypeSafe Jev hooks for Claude Code, Codex and pi: per-turn skill suggestion and subagent model routing
jev-use project preview
Agent tooling
Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM
jev-codex-router project preview
Agent tooling
Per-turn model & reasoning routing for Codex, driven by Jev (TypeSafe System One): picks the model, thinking depth and speed mode for every turn.
systemone-lite project preview
Applications
Toy local System One–style decision API (Jev-shaped). Not affiliated with TypeSafe.
AnyJev project preview
Jev alternatives & open source
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating)