Will this spam candidates or send connection requests?

No. It navigates and scrolls under your signed-in Chrome session but never messages, connects, likes, or comments. Profile visits follow your LinkedIn visibility settings.

Can I trust a potential match?

Only as a shortlist lead. It means every required criterion was marked met with observed quotations, but the README warns a real quotation can still be misread — verify dates, overlapping roles, and location yourself.

Do I have to use TypeSafe, or does it work with Morph?

Either, but exactly one. TypeSafe Jev is the default and Morph is an explicit alternative for the same choice contract — no secondary text model and no silent fallback.

What is the default search actually looking for?

Forward-deployed or solutions engineers in the San Francisco Bay Area with 3-5 years experience. The search, the brief, and up to 20 one-per-line criteria are all editable before you run.

How do I run the recruiter locally?

You need Python 3.12 or newer, uv, Chrome with a signed-in LinkedIn session, and a TypeSafe or Morph API key. Clone the repo, run uv sync, copy .env.example to .env and set the provider key, then uv run browser-harness --doctor and uv run jev, and open http://127.0.0.1:8766.

Does the model generate browser selectors or executable code?

No. Jev selects an operation and a compatible target in one request, and the executor consumes only the selected target, maps it to an observed element and checks freshness before acting. Model output never becomes a selector or executable code.

What are the retry rules for model calls?

Model timeouts and temporary HTTP 429, 503 or 529 responses share a limit of three attempts with short backoff, and each attempt sends the same model input. Browser actions are never retried, and stale page guards still apply before execution.

CommunityJev Agents & MCP

Jev Recruiter

Local LinkedIn recruiting workspace on Browser Use's Jev Ultrafast: Jev screens titles, drives navigation, and assesses profile excerpts against your brief while a live browser stays visible; matches and evidence export as JSON.

See highlights

Open github.com

Stars: 51
Language: Python
License: MIT
Published by: Community
Author: skeptrunedev
Last verified: Oct 2026

skeptrunedev/jev-recruiter

User repository on GitHub

View on GitHub

A Jev powered LinkedIn recruiting agent. Watch it browse relevant profiles, save links, and review evidence against your hiring brief.

Forks: 13
Last pushed: Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

About this project

▶ Watch the 45 second demo · Accelerated footage of Jev browsing profiles and saving potential matches. Give Jev a role. Watch it explore LinkedIn. Keep the profiles and the evidence. A local recruiting workspace built on Browser Use’s Jev Ultrafast and Browser Harness. Jev chooses where to go, screens professional titles, and assesses visible profile excerpts against your brief. The live browser sits at the top, open by default, inside a Craigslist inspired interface.

Quoted from the project's README. Read the full README.

Tagscommunity jevbest catalog-import awesomejev

Works forJev for Classification Jev for Tool calling

Used inJev for Software & DevTools

Languages: Python

Highlights

One provider handles every decision with no text model and no fallback: TypeSafe Jev by default, Morph as an explicit alternative.
The default brief targets forward-deployed or solutions engineers in the Bay Area with 3-5 years experience; search and criteria are editable.
A potential match needs every required criterion met with observed quotations; the README warns a real quotation can still be misread.
Needs Python 3.12+, uv, Chrome with a signed-in LinkedIn session, and a TypeSafe or Morph key; runs and data stay local.

Watch out

Browses LinkedIn under your own session and visibility settings; it navigates and scrolls but never messages. Copy reviewed against the repo README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

jev-skill-suggester

Codex Skill plus stdlib-only Python CLI that recommends which installed skill to read next for a task, allowing no-skill or uncertain answers and never executing candidates.