Chat with Orion
Visual AI Agent for interacting with image, document, video
What it does
Introducing VLM Run Orion — a visual agent that sees, reasons, and acts. Frontier VLMs can describe images but fail at real visual tasks. Orion unites VLM reasoning with precise vision tools to detect, segment, read, and analyze any image, video, or document. It executes multi-step visual workflows reliably, bringing true action-driven visual intelligence to a simple chat interface.
Does a similar job
all alternatives →- CWChat with Orion – a visual agent that sees, reasons and actsNov 2025 · chat.vlm.run · ▲22
Hey HN! We’re excited to share Orion [1] — our new visual agent that sees, reasons, and acts across images, videos, and documents. Frontier VLMs (GPT, Claude, Gemini) can describe what they see, but they can’t reliably act on visual inputs. Ask them to detect objects, segment images, or chain visual steps — they’ll fail in surprisingly inconsistent ways. High-res images collapse to ~1024px. And the visual AI ecosystem is fragmented across separate APIs for image understanding, OCR, image-gen, video-gen, etc. We built Orion to fix this. Orion combines VLM reasoning with reliable…
- VAVisual Agents with Code ModeJun 2026 · vlm.run · ▲8
Rather than calling tools one by one, Orion 2 generates a program and runs it end to end, meaning fewer round-trips and lower latency. You can try it out at https://chat.vlm.run When orchestration is code, every workflow is composable, inspectable, and deterministic. We put together a short Orion 2 demo video: https://www.youtube.com/watch?v=rzhXcNAYQ-0
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 · 18d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d 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, November 2025
the whole month →
- IB
Life & fun · Nov 2025 · bitsnpieces.dev
- BBoing▲782
Life & fun · Nov 2025 · boing.greg.technology