Organization repository on GitHub
Fill job applications from your saved answers, without inventing personal details.
- Forks
- 4
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Agents & MCP
Jev Apply — theadaply
Job-application skill with a memory for CLI agents: given a résumé and a posting it fills what your record supports, drafts grounded prose when you allow it, and leaves the rest open rather than guessing.
- Stars
- 13
- Language
- JavaScript
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- TheAdaply
- Last verified
- Oct 2026
- Languages
- JavaScript
- Capabilities
- Open sourceRequires API key
Highlights
- Fills hosted Greenhouse, Ashby, and Lever job forms; the README lists no LinkedIn Easy Apply support.
- Setup is handled by your CLI agent from SKILL.md and INSTALL.md; you provide a TypeSafe Jev key privately, not in chat.
- Requires Node 20+ and Chrome; OpenAI is optional. Runs take --no-submit on every run and rerun while you review.
- Personal facts, demographic choices, and policy attestations come from you; the skill asks only for what is missing.
- The demo shows a real run: two applications filled and submitted in 16 seconds, fills shown at 2x.
Watch out
Copy reviewed against the repository README on 2026-10-15; it labels hosted Greenhouse, Ashby, and Lever support experimental and states no benchmarks beyond a linked demo video. Private memory stays on disk, but model APIs receive request data and may incur costs.
Questions about this entry
Short answers drawn from the linked project or page.
It is a job-application skill with a memory: give it a résumé and a posting and it fills what your record supports, drafts grounded prose when you allow it, and leaves the rest open rather than guessing.
It fills what your résumé record supports and leaves the rest open rather than guessing. Personal facts, demographic choices, and policy attestations come from you, and the skill asks only for missing facts, choices, or attestations.
Hand it to a CLI agent such as Codex or Claude Code and tell it to read SKILL.md and INSTALL.md and configure everything. Setup needs Node 20+ and Chrome, and you enter your TypeSafe Jev key privately rather than in chat.
Hosted Greenhouse, Ashby, and Lever forms are supported and labelled experimental. LinkedIn Easy Apply is not supported.
The documented agent prompt passes --no-submit on every run and rerun and shows you the filled form, so submission stays in your hands until you decide otherwise.
It is MIT licensed and open source. A TypeSafe Jev key is required and OpenAI is optional, and the README notes that model APIs receive request data and may incur costs.
Private memory stays on disk according to the README, so your saved answers live in local files rather than in chat, though model APIs still receive the request data they are asked to draft from.
Other listings of this project
Forks and copies of this project in the directory. This entry is the canonical one.
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.
Jev Tools & CLIs#community#github#job-applications
Community
Noface07/SystemOne-ApplyPython
Noface07/SystemOne-ApplyPythonMore Jev resources like this
Open-source Codex plugin that consults TypeSafe Jev about tools, models, tasks, skills, context, and strategies, diagnoses failed commands, and checks completion claims against evidence. The current package is version 0.4.0.
Jev Agents & MCP#community#catalog-import#logicrw
A Codex plugin that prepares traceable context handoffs: Jev answers one narrow classification question per old, verified read-only tool pair, and code validates the answers, preserves protected content and builds a JSON or Markdown packet.
Jev Agents & MCP#community#catalog-import#logicrw
Agent skill that pairs Ego Lite's Chromium control with Jev's semantic judgment: the agent keeps the plan, Ego Lite drives the browser, and Jev resolves choices like which observed link actually matches the intent. Exact work stays in local code.
Jev Agents & MCP#community#catalog-import#logicrw
Community
zhuboer/ego-jevJavaScript
zhuboer/ego-jevJavaScriptAn open-source, self-hosted AI agent platform: role-based agents with custom tools, RAG knowledge bases, and 50+ integrations, deployable to Slack, WhatsApp, Teams, Telegram, a web widget, or a REST API from one platform.
Jev Agents & MCP#community#catalog-import#logicrw
Community
getsynkora/synkora-aiPython
getsynkora/synkora-aiPythonA demo-MVP coding-agent skill and CLI that hunts AI and software jobs on real company sites: Chrome sees and acts, Jev scores every link and job, and the host LLM never picks what to click.
Jev Agents & MCP#community#catalog-import#logicrw
Community
hqman/jevscoutPython
hqman/jevscoutPythonA small, opinionated harness setup for the Pi coding agent: scope control keeps tasks to declared files, an improvement loop turns friction into tested changes, eight pinned packages are verified before install, and LANCET Nano screens shell commands.
Jev Agents & MCP#community#catalog-import#logicrw
Community
tannermidd/specpiJavaScript
tannermidd/specpiJavaScriptFrom 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.