Developer Tools1 month ago
BareMetalRT — Bare Metal AI
Run LLM inference on consumer GPUs with NVIDIA TensorRT-LLM optimization.
brianhabana123 · HN
TensorRT-LLM running natively on Windows (no WSL)
The full gallery
Tech stack
60 projects
Run LLM inference on consumer GPUs with NVIDIA TensorRT-LLM optimization.
brianhabana123 · HN
TensorRT-LLM running natively on Windows (no WSL)
Analytics dashboard for LLM API spending by model and environment with optimization suggestions.
ATsimbalistov · HN
Show HN: Tracking GenAI cost and endpoint fragility so app teams don't have to
Route API requests to multiple AI models—OpenAI, Anthropic, Gemini—using one API key.
@AstroBo71280348 · X
Hi , I build for indian developers to access all ai llm models on one platform,it also supports UPI payment no visa credit card required,It is more transferent and better then openrouter
Take any link you were going to share anyway. Routee shortens it, puts one quick step in front, and pays you for every person who passes through.
@RouteeLink · X
Use one API to access and switch between LLM providers while optimizing inference costs.
justin2025 · Product Hunt
Auriko Trading desk for LLM calls
A real-time dispatch log for open Web3 ground across Arbitrum, Ethereum, Avalanche, and Base.
@Drapevangelist1 · X
Just shipped my first vibecoded project. Last weekend, I attended an Avalanche Builders Meetup and got updates on vibe coding. A few days later, I went from “I’m learning this” to actually putting a project live. @AvaxTeam1 @Team1NG @TechyDom @N1Fredy
Collaborate on AI projects using a spatial node canvas to organize LLM context.
jebuehler55 · HN
I built a spatial node canvas to fix LLM context drift
Visualize hardware performance metrics while running LLM inference on your system.
dev_dan_2 · HN
WatchMachineGo – A visualizer to show hardware performing LLM inference
Route AI coding tasks to the cheapest capable model based on estimated complexity.
@viiforwinn · X
Hey, let's connect! 🚀 I got tired of the manual grind (picking Claude models, checking diffs for secret leaks, and guessing agent parallel counts), so I automated all three. Built kodemux—it's completely free and open source:
Connect Strava or your bike odometer to track service intervals.
@GadgetsCars · X
Built a mountain-bike service-tracker with no accounts and no server-side data nothing to breach, I don't have your data. Garage stays on-device, cloud backup is encrypted on your phone before it leaves. Built with Claude behind a strict test+CI gate.
Submit kernel patches and engine optimizations for LLM inference speed, benchmarked on dedicated hardware.
carsenk · HN
Frontier.fast – Help push the frontier of LLM speed forward
One OpenAI-compatible gateway in front of 13 providers. Budgets with hard caps, rate limits, and analytics. Flat subscription, zero token markup.
@tokenrouter · X