shipwithjev

Catalog / Agents & browsers

0243GitHub

JevScout

Coding-agent skill that drives Chrome over CDP to look for jobs on company sites, with Jev scoring pages and links.

hqman/JevScoutREADME ↗
# Jev AI Job Hunter

Demo MVP: a coding-agent **skill** that hunts AI/software jobs on real company sites.

**Chrome sees and acts. Jev decides.** The host CLI runs one command. `jjh` drives Chrome over CDP and calls [Jev](https://docs.typesafe.ai) (TypeSafe System One) to score every link and job. The host LLM never picks what to click.

Skill: [`skills/jev-job-hunter`](skills/jev-job-hunter/SKILL.md).

<video src="assets/jev_job.mp4" controls playsinline preload="metadata" width="100%">
  <a href="assets/jev_job.mp4">Watch the demo</a>
</video>

## Setup

```bash
cp .env.example .env   # then set TYPESAFE_API_KEY (optional for --mock)
uv sync
```

Visible Chrome (not headless). Chrome DevTools MCP is optional; `jjh run` talks to Chrome over CDP directly.

## One-command hunt

```bash
uv run jjh run --url https://openai.com --query "Applied AI Engineer, Codex"
uv run jjh run --url https://typesafe.ai --query "backend / AI engineer"
uv run jjh log
```

Any company homepage works. `--companies openai` is only a shortcut. Add `--mock` with no API key, `--max-pages N`, `--tab reuse`. Tests: `uv run pytest -q`.

## Slow-motion (fixtures / narrated demos)

```bash
uv run jjh start --mock
uv run jjh step --page tests/fixtures/openai_home.page.json --mock
uv run jjh step --page tests/fixtures/openai_careers.page.json --mock
uv run jjh step --page tests/fixtures/openai_job.page.json --mock
uv run jjh report
```

If CDP is down: `evaluate_script` (no `filePath`) then `uv run jjh step --page - <<'EOF' ... EOF`.

Also filed under Agents & browsers

  1. 0226

    Flight search with Browser Use★

    Breaking: Browser Use + Jev = Ultrafast ⚡ Findings flights took 7s and cost only $0.0039 🤯 > new action space every step > DOM state space > small LLM fallback to type (this video is at 1x speed btw) Built a tiny open source browser agent. try it below ↓

    @gregpr07 · Agents & browsers · ~$0.004 · ~7 s

  2. 0619

    jevmem: automatic project memory for Claude Code

    After every Claude Code message, Jev decides in ~0.3 s whether it holds a decision, rule or bug worth keeping, and jevmem saves it as one line in JEVMEM.md.

    @jetwaniavinash · Agents & browsers · ~0.3 s

  3. 0618

    Playwright + Jev: tests in plain language

    Write Playwright steps like "add the most expensive item to the cart". Jev finds the right buttons and fields, fills forms and checks the result.

    Andrey Popov · Agents & browsers

  4. 0617

    toolgate: a tool-call firewall for agents

    A Claude Code and MCP hook where Jev answers seven yes/no risk questions per tool call to allow, ask or deny. Usage and benchmark numbers are in the repo.

    Jaz · Agents & browsers