DEV Community

Md. Ramjan Miah
Md. Ramjan Miah

Posted on

I built RoleTect: A local AI resume tailor & CRM with an embedded, 0-dependency LaTeX compiler (Tauri v2 + Rust) πŸ¦€

Managing a modern tech job search is an operational mess.

Most workflows require browser extensions to scrape details, standalone Kanban sites to track pipelines, web LLMs to write copy, and cloud engines or heavy distributions to handle layouts. Worst of all, you end up uploading your phone number, email, home address, and complete professional history to third-party databases just to tweak a bullet point.

I wanted a single, unified native app that could automate this entire cycle safely right on my desktop.

So I built RoleTectβ€”a local-first job hunter command center, AI tailoring pipeline, and integrated LaTeX compiler built entirely with Tauri v2, Vue 3, and Rust.



Core Architecture and Features

RoleTect hooks a browser layout to a local execution environment to streamline your entire applications pipeline from one dashboard:

  • 0-Dependency Local LaTeX Compiler: You do not need a bloated 5GB local system distribution (like TeX Live or MacTeX) or an Overleaf account. RoleTect embeds the Tectonic typesetting engine directly into the Rust layer. You get a side-by-side active editor and real-time local PDF previews instantly out of the box.
  • Instant Job Ingestion: Found an opening on LinkedIn, Indeed, or a corporate job board? A single click on the companion Chrome/Firefox extension captures the raw details and sends them straight to your app inbox using a background Axum server running inside the client.
  • Local-First AI Customization: Securely input your own API keys (Gemini, OpenAI, Anthropic, or Groq) which remain encrypted locally. Using the rig library, the app handles targeted LLM prompting to surgically align the variables in your master LaTeX templates to match the ingested job description.
  • Isolated Data Vault & CRM: No remote user accounts, no analytics tracking, and no external application servers. Your documents, logs, salary tracking metrics, and historical statuses (Applied, Interviewing, Offer) stay completely offline in a fast, sandboxed SQLite instance.

Behind the Technical Stack

  • Core Systems Layer: Rust + Tauri v2 (native window binding and minimal footprint)
  • Frontend Application: Vue 3 + Vite + Pinia configured into a dense, IDE-style workspace
  • Local Processing & Persistence: Axum Server + SQLite
  • Typesetting Engine: Embedded Tectonic Crate

Your resume contains your most sensitive structural identity data. RoleTect strips out the middleman entirelyβ€”your configuration profile remains on your local file system, and outbound network requests only happen when directly streaming prompts to your chosen AI vendor.


Clone the Code / Grab the App

The project is completely open-source, released, and ready to optimize your pipeline. I would love for you to check it out, run it locally, or review the architecture.

GitHub Project: AhmedTrooper/RoleTect

You can clone the code and spin it up right away using bun install && bun run tauri dev, or pick up a pre-compiled native standalone installer for Windows, Linux, or macOS straight from the repository's releases tab.

Top comments (0)