Rieda
AI route planner for road, gravel and MTB cyclists
What it does
Rieda is an AI route planner for cyclists. Tell it what you want in plain language — "37 miles from Boulder, a bit rolling, quiet roads" — and it builds 20 loops, scores each on surface, traffic and climbing, and hands you the best three, back at your door. Ask for flatter, longer, or "as gravel" and it replans while you talk. Untagged road counts as risk, not tarmac: a road ride goes around it, a gravel ride goes looking for it. Road, gravel and MTB. Free for ten routes a month.
The first AI agent for your next ride: say one sentence, the AI reads it, a routing graph builds the loop — tarmac for the road bike, gravel for the gravel bike, forest tracks for the MTB.
Your AI route planner for road, gravel and MTB. Tell it where you’re starting and what you’re in the mood for. Rieda finds the way. Verified tarmac. Unknown surface counts as risk, and big roads never make the loop. Tracks and forest roads sought, not avoided. Sand and broken ground still stay out. Tour MTB: forest tracks up, real descents down — built around climbing and descending, not trail-chaining. All three loops are real output from the US graph — numbers exactly as the router returned them. The AI reads your sentence. A routing graph picks the roads. You do not get a route. You get the best three of 20 loops, ranked by what matters. Tap any point: surface, way type, gradient. This…from rieda.app
Does the same job
all alternatives →- FRFlattest Route - A web app to help you avoid hills in SF2013 · flattestroute.com · ▲237
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 · 9d 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