Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
roledesk
A job-search engine for one person. It reads the public job boards of the companies you follow (Greenhouse, Lever, Ashby, Workable, SmartRecruiters, Recruitee, Personio) and runs saved searches on boards that span companies (Jobindex, Adzuna), keeps every posting with when it was first seen and when it closed, scores the open roles for each of your search agents, and tracks the applications you make.
Built on the boilerplate: its job queue and scheduler (pipeline/), password (auth/) and deploy kit (deploy/), plus the plugin contract and tools from news (desk/). FastAPI, Jinja2, SQLite, uv, no build step.
Quick start
uv sync --all-extras
uv run app companies seed # 186 companies from seed/companies.json, one board each
uv run app job pull # read every board and search, then extract, embed and score
uv run app serve # http://127.0.0.1:8790
uv run app worker drains the queue without the web app, and uv run pytest runs the app's tests and the copied modules' own. config.yaml is the committed default, with one starter agent and four Copenhagen searches on Jobindex; config.example.yaml documents every key, including the summarise: block below.
Searches and companies
The Searches and Companies sub-tabs do all of this; the same actions exist on the command line:
uv run app searches add jobindex "Copenhagen golang" --q "golang go-udvikler" --area 1
uv run app searches add adzuna "Berlin backend" --q backend --country de --where Berlin
uv run app searches list
uv run app companies prune --in DK,SE,NO,EU # lists; add --apply to unsubscribe
A Jobindex query is its own syntax: words are OR, "a b" is a phrase, +word is required; --area 1 is Region Hovedstaden. An Adzuna search needs a free key from developer.adzuna.com in ADZUNA_APP_ID and ADZUNA_APP_KEY. searches add runs the search once and saves it only if it finds something. Switching a board or search off closes its open roles; the next pull after switching it back on reopens the ones it still lists. The embeddings extra is what fit needs, agent is for extract on a model, passkeys for the Account tab's passkeys.
The tabs
Two tabs, and a cog for settings.
| Roles | open roles, newest or by Best match, with filters, votes (▲ like ● neither way ▼ pass) and a Save button. A title opens the role's own read page |
| Applications | the saved roles and their status, each change recorded as an event |
The cog opens /settings, one shell with six sub-tabs:
| Ranking | the one search agent the UI edits: intent, weights, and require/prefer gates behind an Advanced disclosure. Saving rescores it |
| Searches | saved searches that find roles across companies (try, save, edit, remove) |
| Companies | every company whose board is read, its open roles, and its affinity: hidden, neutral, liked, favourite; following a company and pruning boards by region live here too |
| Pulls | a Pull now button and what is running, the pull schedule, and the extract/embed/score buttons behind a disclosure |
| Messages | everything the server said that nobody has cleared |
| Account | the password, sessions and passkeys. Open on loopback, locked on anything else |
A role's read page, /roles/{uid}, shows the full posting: the same vote and Save controls, the company's own affinity, and the summary when there is one. A search role's posting is a teaser; its page offers a Fetch button that scrapes the original listing once and stores the text. A Summarise button asks for a short summary of that one role; config.yaml's summarise: block turns summarising on for the pull itself, bounded to the top per_agent roles of each agent so the cost stays flat.
Docs
docs/decisions.md: what was decided for roledesk and why.docs/open.md: what is left to do, for whoever picks this up next.desk/README.md,pipeline/README.md,auth/README.md,deploy/README.md: the copied modules, where each comes from and how to refresh it.docs/hosting.md,docs/release.md,docs/server.md,docs/password-protection.md,docs/llm-backends.md: the boilerplate's deployment docs.