Find jobs
Search postings near your city, or anywhere you choose, through JSearch (LinkedIn, Indeed and more) or Adzuna. Score any of them against your profile and start an application with one click.

One profile, a tailored resume and cover letter for every job, written only from facts in your profile, and every application tracked from draft to offer. With the AI model you choose, and your data in your own database.
Free, for Windows and Linux. One click to install, nothing to set up.
The video plays from YouTube, and nothing loads from there until you press play. Watch it on YouTube
Writes with the model you choose
Free software under the AGPL-3.0. Runs with Docker on Linux, macOS and Windows.
How it works
Basics, skills and languages, experience, projects, education, publications and references, in the order you choose. Start it from an existing resume (PDF, Word or Markdown) if you like. A strength meter counts only what a profile needs.
Dossier pulls out the details and requirements and matches them against your profile. What you have is ticked off, with where it comes from. What you don't have is shown as a gap.
In the tone you pick, set in one of twelve themes and printed to PDF on your server. Ask for changes in a chat, edit or regenerate any part, undo what the AI changed or go back to any earlier version.
A board and a table of every application, and a dashboard with your funnel, a week-by-week chart and what's worth a look next, upcoming interviews included.
Honest by design
Drafts only use facts from your profile. When a posting asks for something your profile doesn't have, Dossier shows you the gap instead of papering over it, and you decide what to do about it.
Features
Search postings near your city, or anywhere you choose, through JSearch (LinkedIn, Indeed and more) or Adzuna. Score any of them against your profile and start an application with one click.

Startups that are hiring, from YC startups' job posts and Hacker News' monthly “Who is hiring?” thread, kept to the ones that hire where you live or remotely from your country, and ranked against your profile.
Once a day it runs a search for you, skips what you've seen and keeps the best new postings, with its reasons. It can prepare drafts for your review. It never sends or applies.
And a theme builder, previewed live and printed to PDF on your server. Duplicate themes, or share them as files.
Resumes and cover letters in any of 21 built-in languages, with headings, dates and language levels to match.
An email to go with each application, to whoever the posting names, with the resume and cover letter PDFs to attach.
Send from your own address, see employers' replies next to each application, have answers drafted from your profile, and keep interviews in step with Google Calendar. Optional, and nothing goes out without your confirmation.

Use Dossier from Claude, on your own Claude plan: search jobs, score them, and save the resume and letter Claude writes as a draft, checked like Dossier's own. Optional.
Everything lives in your own PostgreSQL database, and leaves it on your terms.
Privacy
Dossier is for one person, on your own computer or a small server: your data in your own database, and an AI model of your choice.
What goes whereNo accounts and no service in between. Run it on your laptop, or on a small server with your own domain.
With Ollama or LM Studio, your profile, postings and documents never leave your hardware. A hosted model receives what it writes from.
Dossier asks once whether it may send a daily usage ping, a random ID and the version number, and sends nothing until you agree.
Every line is on GitHub under the AGPL-3.0, so you can check what it does, change it and share it.
A look around
The screens show the demo data: Jane Doe is made up.
Install
The desktop app installs like any other. With Docker or on a server, the guides take you through each step.
For 64-bit Intel and AMD processors; there's no version for macOS yet. The app isn't signed yet, so Windows may ask before it opens: choose More info, then Run anyway.
Dossier runs inside the app, with your data in one file on your computer: no server, no password, nothing to configure. On my server opens a Dossier you host instead.
It helps you choose an AI model, where jobs come from and how they're scored, one step at a time, and starts your profile from your resume. The desktop app in the wiki
All you need is Docker Desktop on macOS or Windows, or Docker Engine with its Compose plugin on Linux, and about 2 GB of free memory.
$ mkdir ~/dossier && cd ~/dossier
$ curl -fsSL -o compose.yml https://raw.githubusercontent.com/AienTech/dossier/main/compose.production.yml
$ echo "POSTGRES_PASSWORD=$(openssl rand -hex 24)" > .env
$ echo "DOSSIER_SECRET=$(openssl rand -base64 32)" >> .env
$ docker run --rm -it ghcr.io/aientech/dossier hash-password
It asks for the password twice and prints a line that starts with argon2id:. Add it to .env as DOSSIER_PASSWORD=argon2id:…. Dossier only keeps the hash, never the password.
$ docker compose up -d
Open http://localhost:3000, sign in, and pick an AI model in Settings → AI provider. The first start downloads the image (about 1.7 GB). Choosing an AI provider
Put Dossier on a server, on your own domain with HTTPS. Give it at least 2 vCPUs and 2 GB of memory. The installation guide walks through each way, step by step.
On your own computer, you can also run it with plain Docker or Node.js.
Community
On Dossier's Discord, people looking for work help each other get hired: honest resume feedback, interview practice, and how hiring works country by country. It's also where you help decide what Dossier does next.
Free and in English, whether you use Dossier or not. No ads, and never pay for a job.
Free, open source, and yours to run.