Zibra AI

What it does

GPU-native data orchestration platform for physical and spatial AI. Spatial AI isn't compute-bound — it's data-bound. Massive volumetric datasets create a data gravity problem: I/O bottlenecks starve GPUs and stall training despite huge compute investment. Zibra removes that bottleneck — over 97% in size reduction, 600+ GB/s decompression, delivered in the compressed unified format directly into GPU. 40% better GPU utilization. 30% faster model convergence. This is the missing data layer.

• 
  ZeroGPUJun 2026 · zerogpu.ai · ▲309

  The compute efficient layer for AI inference

• 
  General ComputeMay 2026 · generalcompute.com · ▲315

  AI models that run on an inference cloud optimized for speed

• 
  nCompass AI AssistantMar 2026 · ▲88

  Enabling everyone to write GPU kernels

• DO
  Demo of Agent Based Model on GPU with CUDA and OpenGL (Windows/Linux)2023 · github.com · ▲55

  Demo of agent based model on GPU with CUDA and OpenGL (Windows/Linux) Agent instances on GPU memory Uses SSBO for instanced objects (with GLSL 450 shaders) CUDA OpenGL interops Renders with GLFW3 window manager Dynamic camera views in OpenGL (pan,zoom with mouse) Libraries installed using vcpkg (https://github.com/KienTTran/ABMGPU)

• CB
  Cua-Bench – a benchmark for AI agents in GUI environmentsJan 2026 · github.com · ▲40

  Hey HN, we're excited to share Cua-Bench ( https://github.com/trycua/cua ), an open-source framework for evaluating and training computer-use agents across different environments. Computer-use agents show massive performance variance across different UIs—an agent with 90% success on Windows 11 might drop to 9% on Windows XP for the same task. The problem is OS themes, browser versions, and UI variations that existing benchmarks don't capture. The existing benchmarks (OSWorld, Windows Agent Arena, AndroidWorld) were great but operated in silos—different harnesses,…

• RL
  Rate limiting, caching and request prioritization for AI apps2024 · fluxninja.com · ▲10

  Generative AI applications pose a unique challenge in production. They are computationally intensive and orders of magnitude slower than traditional data-intensive applications. Scaling these applications is further complicated by expensive hardware requirements and GPU shortages. Consequently, developers are scrambling to implement home-grown caching and rate-limiting solutions, which are error-prone and difficult to get right. FluxNinja Aperture delivers a production-grade experience with a purpose-built load management platform that provides rate & concurrency limiting, caching, and…

• 
  I trained a 125M model to autocomplete piano on-device▲598

  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▲585

  Automate your B2B brand going viral, with new media creators

  AI · 18d ago · company-app.joinastute.com

• 
  Grok Bot▲547

  AI teammates that you can give real work to

  AI · 25d ago · x.ai

• 
  Needle2: 14MB agentic LLM for phones, wearables, smart home and robots▲537

  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

• 
  Monid▲474

  OpenRouter for agent tools

  AI · 6d ago · monid.ai

• 
  Clara AI SDR▲460

  Turn website visitors into qualified pipeline

  AI · 19d ago · clarasdr.ai

• 
  Brila▲1,367

  One-page websites from real Google Maps reviews

  AI · Apr 2026 · brila.ai

• AG
  A game where you build a GPU▲964

  Thought the resources for GPU arch were lacking, so here we are

  Life & fun · Apr 2026 · jaso1024.com

• IB
  I built a tiny LLM to demystify how language models work▲915

  Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.

  AI · Apr 2026 · github.com

• 
  Fathom 3.0▲803

  AI meeting notes: now bot-free, in ChatGPT & Claude + more

  AI · Apr 2026 · fathom.ai

• BC
  Brutalist Concrete Laptop Stand (2024)▲786

  Life & fun · Apr 2026 · sam-burns.com

• IB
  I built a frontpage for personal blogs▲783

  With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.

  AI · Apr 2026 · text.blogosphere.app