Orion
Your AI workspace for research, agents & workflows
What it does
Orion is an AI workspace that brings research, multiple AI models, custom agents and automated workflows into one place. Instead of switching between different AI tools, you can research topics, choose the right model, create specialized agents and automate tasks. Built by Singularity AI, Orion makes powerful AI tools simpler, more accessible and easier to use from one unified workspace.
Welcome to Orion! Download and experience the ultimate AI arsenal. Access 8 premium models including Gemini, Claude, and Grok. Advanced DeepSearch and Custom Agents for everyone.
Access Gemini, Claude, Grok, Llama, DeepSearch and Custom AI Agents—all in one place. This is the real Orion product, tap-for-tap — swipe or tap through, or let it play itself. The home screen greets you by name. Type into the search bar, switch on DeepSearch, or pick a model like grok-4.1-fast. Start a new thread, jump Home, open Settings, or pick up a recent chat from the date-sorted history. Saved material lives in folders — a Default collection, plus any you make, like "exam." My Tasks lists what every agent has run, with a live COMPLETED / FAILED status on each card. The Scheduled tab shows next run time, repeat rule, and how many times a job has already fired. Pick an agent, describe…from download-orion-ai.web.app
Does the same job
all alternatives →
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 · 16d 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 · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
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 · 16d ago · simedw.com