CareerRat rates the postings actually worth chasing, applies with honest artifacts drawn from your own evidence, and tracks every outcome. It runs on the AI CLI you already have — Claude Code, Codex, or anything else on your PATH.
Rate what's worth chasing, apply with real evidence, track what happens next. That's the whole loop — R, A, T.
On first launch it finds the AI CLIs already installed. Pick one — your subscription, your machine, nothing leaves it.
CLAUDE CODE · DETECTED · V2.3Drop your résumé and answer a short interview. CareerRat fills its own file as you talk — roles, floors, dealbreakers — and you can edit any of it by hand.
ROLES ✓ · GUARDRAILS ✓ · TARGETING.YML UPDATEDSweeps run in the background: pull, dedupe, cut, rank, prep. Everything it does leaves a receipt, and nothing is sent without you.
SWEEP 6:12 AM · 9 CUT · 12 RANKED · AI · CLAUDE CODEHonest tailoring isn't a limitation — it's a design choice. Applications that overclaim don't hold up in interviews. Artifacts built from your real evidence do.
You build a bank of real things you did — projects, metrics, decisions. Every tailored artifact draws only from that bank.
If a claim isn't in your evidence, it won't write it. No hallucinated roles. No inflated titles. No fake metrics.
It reorders, reframes, and emphasises what genuinely fits the role. That's tailoring. That's honest.
Every posting gets rated against your constraints before tailoring starts. You never write a cover letter for a job that doesn't fit.
Run CareerRat on your own machine and your résumé, comp numbers, evidence bank, and full pipeline stay on your laptop. No account to create, no telemetry, nothing syncing in the background.
Job searches are personal. Your comp floor, your reasons for leaving, your backup options — run CareerRat yourself and all of it stays on your machine, full stop.
No signup, no telemetry, nothing phoned home. The self-host version runs on your machine and uses the AI CLI you already have. What you put in stays in.
CareerRat is an agent runtime. It doesn't lock you into a model or a subscription. Bring whatever AI CLI you already use — Claude Code, Codex, or anything else on your PATH.
CareerRat scaffolds the workspace, installs skills, starts the dashboard, and hands off to a supported agent CLI. Model choice, cost, and local data stay under local control.
With your own CLI you get all of it — the AI features included. No account, no sign-in, no trial clock.
The whole app. AI features run on your installed CLI — your subscription, your machine.
No CLI, no setup — we run the model. Same app, same receipts.
It all ships together, and none of it is built for one industry. A nurse, an engineer, and a driver each answer onboarding their own way and get the same loop.
Free to self-host, open source (MIT). No wizard, no signup — one command and the agent takes it from there.
npm install -g @anthropic-ai/claude-code claude.com/claude-codenpm install -g @openai/codex github.com/openai/codexPaste a job posting and say “evaluate this” to kick off the loop. Or try the bundled sample under examples/sample-jobs/.
Free. Local. Honest. One command to get going. Run it yourself and your data stays put.
# one command, then the agent takes it from here