FluoWe find builders by
their taste.
AI made writing code nearly free. The scarce thing is judgment. Fluo reads code and measures the taste behind it.
↑ type your GitHub handle in the hero — this terminal runs the real engine on you, live · 0 LLM tokens
curl -fsSL https://fluo.team/install.sh | bash
The free way in: two builders, one radar. See where your skills fill each other's gaps and where your taste lines up. Every read makes the team-fit engine smarter.
Enter your team's GitHub handles and a candidate's. Fluo shows every pairwise match, the overall composition, the gaps you're missing — and whether that candidate would fill them. The validated signal: teams ship when ownership is distributed, not when résumés sparkle.
Will this team gel?
Every pairwise match, the overall composition, and the gaps to hire for — from public code.
Test a candidate
Drop in a candidate's handle and see if they fill the gaps: ✓ Strong add, ~ Helpful, or ✗ Redundant with the team.
Cost of getting it wrong
A regretted hire runs $50–240K. Wasted interview loops, slow teams. Move the sliders to your reality.
Deploy a fleet of agent-finders across a read-only index. A token-disciplined cascade narrows the haystack; we contact only the opted-in, mutually-matched few — never cold outreach.
We measure judgment.
The rest
Fluo
Fingerprint the taste in code
Six axes + tags like verification-first, from any repo — a cheap prior sharpened by a model that reads the content.
Diff yourself against the best
See where your taste falls short of exemplary repos and get concrete upgrades.
Find builders who complement you
Read-only, in-product. People whose skills fill your gaps and whose taste you share.
It keeps itself honest. The judge must cite evidence; a verifier checks the evidence actually exists in the repo. The self-improvement loop only keeps a change if it beats a held-out anchor — it can't flatter itself into confident nonsense.
Read-only and private by design. It clones and reads; it never writes to GitHub. Talent matching is in-product suggestion only — matched on technical signals only, with no personal data stored.
Is this read-only? Do you store my data?
Yes — GET-only. We clone and read public code; we never write to GitHub, and we match on technical signals only (axes + taste), never name, location, or timezone. No personal data is stored beyond a derived fingerprint and a public handle.
Isn't GitHub a weak signal — my best work is private?
Fair. We read what's public, and the deep read judges the actual code, not stars or follower counts. For at-work/private code, analysis is opt-in and consented. A quiet public profile isn't a verdict on you.
Can "taste" really be measured?
We don't claim to bottle it. We measure observable proxies — verification-first instinct, where effort lands, architectural restraint — and validate them against ground truth: real collaborators cohere on shared taste, and distributed ownership predicts shipping velocity (r≈−0.56). The judge cites evidence, and a verifier checks it exists in the code. Watch code distill into taste →
How is the team-fit score computed?
Distributed ownership (low bus factor) is the dominant validated predictor of shipping velocity, so it leads the formula, with shared values and coverage second. Bus factor needs commit history, so the public number stays honest about what it can't yet measure.
Won't people just game it?
It reads revealed behavior across a whole body of work — far harder to fake than a résumé or one interview — and the evidence-grounding verifier rejects any claim it can't find in the code.
What does it cost?
Reading your taste and matching is free. Enterprise Team Fit is a per-seat subscription. Do the math on what getting fit wrong is costing you today.