Airbolt – Call LLM APIs from your app with zero back end
Hi HN! We love the "backend-less" stack: Stripe for payments, Supabase for data, Clerk for auth. But the moment we add AI features, we're forced to spin up a backend to hide API keys, implement per-user token-based rate limits and graceful degradation, etc. So we built Airbolt. What it does: Drop in our SDK and start making OpenAI calls directly from your frontend. Your keys are AES-256-GCM encrypted on our servers, never exposed to the client. We provide token-based per-user rate limits and origin allow lists to address inference abuse. Short-lived JWTs and bring-your-own-auth are coming…
What it does
In the maker’s words, at launch
Hi HN! We love the "backend-less" stack: Stripe for payments, Supabase for data, Clerk for auth. But the moment we add AI features, we're forced to spin up a backend to hide API keys, implement per-user token-based rate limits and graceful degradation, etc. So we built Airbolt. What it does: Drop in our SDK and start making OpenAI calls directly from your frontend. Your keys are AES-256-GCM encrypted on our servers, never exposed to the client. We provide token-based per-user rate limits and origin allow lists to address inference abuse. Short-lived JWTs and bring-your-own-auth are coming soon (like this week). Why this matters: Current tools solve fragments. Teams still build custom backends. The cost compounds: more code, more bugs, slower shipping, and worse AI-coding tool performance as context grows. We provide a TypeScript API, React Hooks, and React Component. Coming soon: - Multi-provider support (OpenRouter, Anthropic, Gemini, and more) - No-redeploy upgrades: we want our self service dash to be your "control plane" so you cane change providers, models, context and more without changing your project source and redeploying - Native mobile SDKs - Bring-your-own-auth integration (Auth0, Clerk, Auth.js, etc) - RAG/vector search Built this after implementing the same proxy pattern for the 10th time. When we consider ease of use and speed vs flexibility tradeoffs, we're intentionally choosing extreme ease and speed (when it seems everyone else is building more ways to define complex agents). Try it out: https://www.airbolt.ai/ [email protected]
Does the same job
all alternatives →
- AAAirQL: An Airtable API with OAuth2 access control and permissions2022 · airql.dev · ▲9
Hey there! At our company, Bit Complete [1], we use Airtable a bunch for managing operations. We really like how easy it is to throw up a form to collect information, or to build automations for offline processing like aggregations. One challenge we kept running into was how to build more complicated interactive apps using the API, while maintaining fine-grained access control to Airtable data. Airtable ties identity to API access control via API keys, which makes it very hard to build apps with realistic access control needs. So we built AirQL! [2] It’s a utility layer between Airtable’s…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, September 2025
the whole month →
- AS
Commerce · Sep 2025 · anycrap.shop
- TE
I made a built-from scratch Wayland Compositor to display any GUI app* in the terminal! I think there is a lot of unexplored potential in custom Wayland compositors, a lot of really cool things you can embed existing applications into! So, I started with embedding apps into the terminal because that is the easiest input/output (output is just utf-8 and I use the great `chafa` library for that, and I just read from stdin for the input). If you have any other ideas for cool Wayland compositors, let me know. I purposedly wrote 80% the app in Typescript to appeal to the most developers and…
Dev tools · Sep 2025 · github.com
- IR
Years ago I stumbled across a basic version of this concept and it stuck with me. I knew if I was ever going to take on such a project, it would need to be flawless, but without coding experience it was just another idea that would never happen. By the end of 2024, as AI coding tools exploded everywhere, I finally had a way to make it real. I started from zero knowledge and spent months collaborating with AI agents as a learning experience. Every pixel and every function went through me. The AI translated what I asked for into code, but every decision was human. I didn't use existing OS…
AI · Sep 2025 · mitchivin.com
