User repository on GitHub
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
jev-apply (browser form filler)
Fills job applications page by page in a browser from a JSON profile, with plain rules answering common fields, a local decision model choosing among your own facts, and submit gated until you opt in.
- Stars
- 0
- Language
- Python
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- Noface07
- Last verified
- Oct 2026
This is one of several Jev listings for the same project. The canonical entry is Jev Apply — theadaply.
- Languages
- Python
- Platforms
- BrowserPlaywright
- Capabilities
- Open sourceRuns locally
Highlights
- Works through each page: text fields, dropdowns, Yes/No questions, dates, skill tags, resume upload and Next, stopping at Submit by default.
- Every value comes from a JSON file describing you, never from a model's imagination, per the README.
- Laya runs locally by default and only picks which of your facts or options answers a question; one .env line switches it to TypeSafe's Jev.
- Safety is code: sensitive fields, declarations, logins and the final submit are gated by readable rules; auto_submit is opt-in for batches.
- Status: a personal project used on LinkedIn Easy Apply, simple company forms and Workday up to Review; MIT licensed, pushed 2026-10-14.
Watch out
README reviewed 2026-10-17; the excerpt cuts off inside the status note, so the limits, privacy and metrics sections are not captured. The README itself warns that job boards generally prohibit automation, so use is the operator's responsibility.
Questions about this entry
Short answers drawn from the linked project or page.
A tool that fills job applications from your own data: it opens an application in a browser and works page by page through text fields, dropdowns, Yes/No questions, dates, skill tags, resume upload and Next.
Rules first: common fields like notice period, experience, contact details and education are answered by plain code from your profile. Laya, an open-weights decision model running locally, handles other choices but only picks which of your own facts or options answers a question.
Yes. One line in .env switches the decision-model role to TypeSafe's Jev instead of the local Laya model, according to the README's choosing-the-decision-model section.
Only if you enable it. By default it stops at the final Submit button so you can check everything; turning on auto_submit lets it submit complete applications one at a time or in batches.
No. Every value comes from a JSON file describing you, never from a model's imagination, and code checks the Claude-drafted text answers against your profile. Open questions are drafted through the Claude Code CLI on your own login.
Safety is code, not prompts: sensitive fields, declarations, logins and the final submit are gated by rules in jev_apply/policy.py and jev_apply/agent.py. The README warns job boards generally prohibit automation, so use is your responsibility.
A personal project, actively used on LinkedIn Easy Apply, simple company forms and Workday up to the Review step, tested on several companies. It is MIT licensed; the repository was created 2026-09-29 and last pushed 2026-10-14.
More Jev resources like this
A local deep-research tool that turns your own PDF, DOCX, PPTX, image, TXT, or Markdown files into a structured report, using TypeSafe's Jev to rerank Qdrant chunks and verify evidence coverage while an LLM plans and writes.
Jev Tools & CLIs#community#github#python
Community
oqura-ai/deepdocPython
oqura-ai/deepdocPythonA 32M-parameter typed-decision model plus a Chrome extension that runs entirely on-device with WebGPU/WASM and Moonshine speech recognition. Its local server speaks POST /v1/systemone, so existing Jev clients work by changing the base URL; a benchmark table claims zero option-order flips.
Jev Tools & CLIs#community#github#chrome-extension
Community
MeharPro/GenClassPython
MeharPro/GenClassPythonAn Omarchy launcher where you describe what you need and JEV routes it to a reviewed safe operation, settings panel or keyboard shortcut from a live command catalogue. Clear matches run; Preview only shows the plan.
Jev Tools & CLIs#community#github#python
Community
Cozidian/omarchy-jevPython
Cozidian/omarchy-jevPythonA local experiment bench that uploads PDFs, extracts and chunks their text, then generates Full, Jev and RAG comparison records for consecutive questions, storing workspaces, chunk rules and answer history in a SQLite file at .runtime/jev_context.sqlite3.
Jev Tools & CLIs#community#github#python
Community
wdwd200/jevPython
wdwd200/jevPythonA local workbench that pairs OpenCV vision with Laya or Jev decision models: images are segmented and measured, hard rules settle the numbers, and the model gives the verdict — with one-click installers and an "open-source JEV" training path served at /v1/systemone.
Jev Tools & CLIs#community#github#python
Community
uu889/laya-opencvPython
uu889/laya-opencvPythonA proof-of-concept HTTP service for constrained decisions with a local MLX model: send text or JSON plus typed choice, score, or noul questions and it returns probabilities over the answers you declared — no generated text, no parsed model JSON.
Jev Tools & CLIs#community#github#python
Community
snellingio/system-onePython
snellingio/system-onePythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.