cd /news/ai-tools/show-hn-oort-a-prompt-library-where-… · home topics ai-tools article
[ARTICLE · art-17825] src=oortstack.com pub= topic=ai-tools verified=true sentiment=· neutral

Show HN: Oort – A prompt library where every listing has a shipped project

Oort launched a prompt library where every listing is tied to a shipped project, allowing developers to clone and run prompts using their own API keys from providers like Anthropic, OpenAI, and Google. The platform features usage-weighted rankings based on real run counts, encrypted key storage, and unlimited BYOK runs under a flat subscription model, with a free tier available. It targets solo developers and staff engineers seeking verified, production-tested prompts without AI-generated filler.

read2 min publishedMay 29, 2026

Clone a prompt that shipped someone else's project. Your keys, any model, ranked by real usage.

Drop in Anthropic, OpenAI, Google, xAI, or DeepSeek keys. Encrypted at rest. Never touches your browser.

Every listing shows real run counts, the dev who shipped it, and the project it came from. Usage-weighted ranking, no upvote games.

Clone a repository pack in one click. Stream from any provider. Chain prompts into workflows when one isn't enough.

These are new — no run data yet. Be the first to take one for a spin.

Give your table schema and a question in English. Get correct, readable SQL for your dialect, plus a note on indexes and any assumption it had to make.

Paste an overgrown file. Get a safe, incremental refactor plan — seams to cut, the order to cut them, and how to keep it green at every step. No rewrite-from-scratch advice.

Paste a stack trace and the relevant code. Get a plain-English explanation of the root cause and three ranked fixes, each with a one-line tradeoff.

Give a function signature and what it should do; get a focused test suite covering the happy path, edges, and error cases — written to fail until you implement it.

Translates an 'it's broken' message into a triage-ready ticket: steps to reproduce, expected vs actual, severity, and the first place to look in the code.

Paste a diff and get a prioritized review: correctness bugs first, then security, then maintainability. Cites exact lines, proposes fixes, and skips nitpicks unless they hide a bug.

Staff engineers, solo devs, and indie-hacker founders authoring prompts they use in their own work. No AI-generated library filler.

BYOK runs are always unlimited — you pay providers directly. Oort takes a flat subscription. Free tier is real, not a trial.

BYOK-first, forever

For solo devs who ship Highest limits, priority support

For procurement-heavy buyers: dedicated success manager, custom pricing on platform credits, and bespoke procurement paperwork. SAML SSO, RBAC, and custom DPA are on the roadmap — let's talk about what your team needs. Platform runs are requests routed through Oort's provider keys. BYOK runs — using an API key you store in Settings → Keys — are unlimited on every tier.

Fair-use: "unlimited" means "no hard cap under honest use." Documented per-minute rate limits apply. Full terms in Terms of Service. Join 3 devs already on Oort. BYOK means your first run costs pennies, not a subscription.

── more in #ai-tools 4 stories · sorted by recency
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/show-hn-oort-a-promp…] indexed:0 read:2min 2026-05-29 ·