jev-recruiter
Local recruiting workspace where Jev browses LinkedIn, screens titles and checks profile excerpts against a hiring brief.
Overview
Jev Recruiter is a local recruiting workspace built on Browser Use's Jev Ultrafast and Browser Harness. You give it a role, and Jev chooses where to go on LinkedIn, screens professional titles and assesses visible profile excerpts against your brief, while the live browser is shown inside a Craigslist-inspired interface. One decision provider handles navigation, title screening and evidence choices with no secondary text model; the default is TypeSafe's Jev, and Morph's decision endpoint can be selected instead, with no automatic fallback.
It starts from a relevant people search, follows recommendations from the sidebar, saves discovered profile URLs with their source and screening result, and shows criterion findings beside quotations from the profile. You can run toward a target number of matches, pause, step through decisions, export JSON and shortlist or pass candidates yourself. The default brief looks for forward-deployed or solutions engineers in the Bay Area with three to five years of experience, and is editable.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Where should the browser go next? | — |
| Yes / no | Does this professional title fit the brief? | yes · no |
| Choice | Does this profile excerpt meet, miss or not show this criterion?(inferred) | — |
How it works
- Start from a people search for the brief
- Jev chooses navigation steps and screens titles
- Save matching profile URLs immediately
- Assess visible excerpts against each criterion
- A human shortlists or passes candidates
Strengths
- Evidence quotes shown beside each finding
- Human makes final shortlist decisions
- Single provider with no hidden fallback
Caveats
- Uses a signed-in LinkedIn session, which may conflict with site terms
- Screening on partial profiles can be biased or incomplete
- Requires a TypeSafe or Morph key
Getting started
git clone https://github.com/skeptrunedev/jev-recruiter.git && cd jev-recruiter && uv sync && cp .env.example .env (set TYPESAFE_API_KEY)At a glance
- Type
- Project
- Status
- prototype
- Language
- Python
- Runtime
- Local web app driving Chrome
- Has code
- yes
- License
- MIT
Use cases and integrations
How curated lists describe it
A Jev powered LinkedIn recruiting agent. Watch it browse relevant profiles, save links, and review evidence against your hiring brief.
hellogumbo/awesome-jev
Frequently asked questions
What does Jev decide?
Where to navigate, whether titles fit, and how profile excerpts match each criterion.
Who makes the final call?
You do; the app only saves potential matches and evidence.
Can I use another provider?
Yes, Morph's decision endpoint, selected explicitly.
Related projects
Claude Code job-application tool that finds roles, fills forms in Chrome, reads every answer back and sends only those you approve.
ProjectbetaTypeScriptCoding-agent skill that drives Chrome over CDP to hunt for jobs on company sites, with Jev scoring every link and job posting.
Agent skillprototypePythonRAM-efficient Rust coding-agent harness, listed as using Jev decisions for memory pruning, browser navigation and voice routing.
ServiceproductionRustMCP server and libraries that drive Chrome over CDP and hand a decision model like Jev a bounded menu of page actions.
ProjectproductionTypeScript- Jev Browser★ 335
Headless browser automation via MCP server, CLI or library: Jev picks one action per step and scores goal-met and stuck probabilities.
MCP serverbetaTypeScript Local browser agent that picks each step's operation and element with a Jev-shaped model such as a fine-tuned Laya, no cloud needed.
MCP serverbetaPython