AgentATS — the open-source, AI-native applicant tracking system that runs inside your own Google account

Every AI hiring feature the paid tools have — free, open-source, and yours.

Full applicant tracking: AI résumé parsing, candidate scoring, a careers page, pipeline, feedback and analytics — running inside your own Google account, with nothing to pay and nothing to lock you in.

Companies pay thousands a year for this. You won’t. · Open source · MIT

Why AgentATS — free vs. thousands a year, you own your data, no per-seat pricing, bring your own AI key, explainable and bias-aware, open source
Everything an ATS should do

A full hiring stack, not a toy.

The complete loop — from requisition to offer debrief — running on Google Sheets, Drive, Gmail and Calendar you already have.

Requisitions

Titles, levels, salary bands, openings, priorities — with hiring manager and recruiter ownership.

Public careers page

A hosted apply page out of the box, plus CV-by-email: forward to careers@ and it's parsed automatically.

AI parsing & 37-category scoring

Gemini reads every CV into structured fields and scores it on a transparent rubric you can tune in plain English.

Pipeline & stages

Kanban-style stages, stage-change tracking, and stuck-candidate SLA alerts on your Today view.

Scheduling & feedback

Google Calendar + Meet invites, RSVP tracking, per-role interview plans, structured feedback forms.

Debrief & candidate packet

A debrief view and a one-click candidate packet PDF for hiring committees.

Sourcing engine

Opt-in live sourcing plus an X-ray query builder for LinkedIn, GitHub and resume search.

Recruiting analytics

Per-manager and per-role metrics, interview round stats, and a Looker Studio data tab for live dashboards.

Bias-masked screening

Evaluate candidates with identifying details hidden — fairer first reads, by design.

Roles & audit trail

Admin, Recruiter, Hiring Manager, Interviewer — enforced server-side, with a full audit log.

Backups & archiving

Automated tracker backups, plus archiving that keeps big pipelines fast without losing your metrics.

Yours to change

MIT-licensed source. Read every line, edit any behavior, swap the AI provider if you want.

And it’s also…

Things the tools you pay for don’t give you.

Feature-complete is the baseline. Here’s where free-and-open pulls ahead.

🔒

You own your data

Every candidate, CV and score lives in your Google account — not a vendor’s cloud. No lock-in, ever.

🔑

Bring your own AI key

You pay Google cents directly for AI. No per-token markup, no surprise “AI add-on” invoice.

👥

No per-seat pricing

Invite every recruiter, hiring manager and interviewer. Unlimited seats, always — because it’s yours.

💬

Ask your pipeline in plain English

“Who are my strongest backend candidates?” — agentic search that most ATSs simply don’t have.

⚖️

Explainable & bias-aware

Every score shows its reasons across 37 dimensions, with a one-click bias-masked screening mode. Not a black box.

📥

Auto-intake

A public careers page plus CV-by-email that reads résumés on arrival and files candidates for you.

🛠️

Open source

Read every line, extend anything, trust what runs. MIT-licensed — a gift to the TA community.

The AI, made visible

Watch it work. This is what your screening week looks like now.

Four things AgentATS does in seconds that used to eat your afternoons. All data below is fictional sample data — animated, not screenshots.

Résumé → structured profile, in seconds

Drop in a CV — Gemini reads it and fills every column for you.

NameAisha Rahman
Current roleSr. Backend Engineer
CompanyNorthwind Labs
Experience7 yrs
SkillsGoKafkaAWS
Notice period30 days
AI parsed in ~4s · sample data

Six applicants in. A stack rank out.

Every candidate scored against the role — then ranked, tiered and ready to review.

Priya MenonStaff Eng · QuantivaStrong0
Marcus ChenSr. SWE · BrightloopStrong0
Aisha RahmanSr. Backend · NorthwindGood0
Diego AlvarezBackend Eng · Vellum SystemsGood0
Lena NovakFull-stack · OrbitaFair0
Yuki TanakaSWE II · CraneworksFair0
AI scored 37 dimensions per candidate · sample data

A fit score you can actually interrogate

Not a black box — every score breaks down into rubric categories you can read and tune.

4 of 37 rubric categories shown · sample data

Ask your pipeline in plain English

No filters, no exports. Just ask — and get a ranked answer with reasons.

1Priya Menon94 · distributed systems at scale
2Marcus Chen88 · strong Go + on-call ownership
3Aisha Rahman81 · Kafka pipelines, fast ramp
AI answered from your own Sheet · sample data
Setup

Live before your coffee cools.

Fully self-provisioning — it creates its own spreadsheet, folders and tabs. You never touch an ID.

STEP 1

Create an Apps Script project

Go to script.google.com and click New project. Free with any Google account.

STEP 2

Paste the files

Copy the six files from the GitHub repo into your project.

STEP 3

Add your Gemini key

One Script Property: GEMINI_KEY, from Google AI Studio. It never lives in code.

STEP 4

Run firstRun & Deploy

One function builds everything and makes you Admin. Deploy as a web app — that URL is your ATS.

~2 minutes. No servers. No bill.

Compare

Confident, and fair about it.

Against the tools it replaces for small and mid-size teams. They're excellent products — they're just built for a different buyer.

CriterionAgentATSLeading paid ATS platforms
PriceFree forever + cents of AI on your own key~$300–$1,000+/mo for small teams
Own your data100% — the database is a Sheet you can openVendor cloud; exports on request
AI scoringIncluded — a 37-category rubric you can read & tunePaid add-ons or opaque scoring
Open sourceYes, MIT — edit anythingNo
Setup time~2 minutes, self-provisioningDays to weeks, sales-led onboarding

If you're a 2,000-person company with a compliance team, buy an enterprise ATS — genuinely. If you're a founder, an agency, or a TA team of one to fifteen, this was built for you.

Honest limits

What it's not (yet) — because we'd rather you know.

You're evaluating a hiring system, so here's the full picture up front. Most of these are the deliberate tradeoff of a free tool that runs entirely inside your own Google account.

Google's platform limits

Apps Script has execution caps and daily quotas (API calls, ~100–1,500 emails/day). Very heavy bulk operations can bump them.

AI takes a few seconds

Parsing or scoring a CV isn't instant — expect a few seconds per action. Assistive, not real-time. And AI can misjudge; it assists, it doesn't replace human review.

Best up to mid-size

The database is a Google Sheet: great for hundreds to low-thousands of active candidates, not enterprise volumes. A built-in archiver helps.

Bring a paid Gemini key

Software is free; AI usage is pay-as-you-go on your own key (cents, not seats). Use a paid tier for real candidate data — free tiers may train on inputs.

Not SOC 2 certified

No SOC 2 / ISO certifications, no third-party pen test. Security is app-level and depends on your Google account hygiene. Regulated buyers need more.

Single workspace, no job boards

One company per install, no SSO/SCIM, and no built-in LinkedIn/Indeed integrations — intake is your careers page, CV-by-email, or manual.

In one line: the most capable ATS you can run for free inside your own Google account, with real AI — built for startups and lean TA teams, not regulated enterprises. Community open-source means no SLA: you self-host, you self-support, and you own everything.

Get started

Own your hiring stack. Free.

Star it, fork it, or have it running before your next intake meeting.

★ Get AgentATS on GitHub