Townhouse
The property app that works for you, not the agent
What it does
Every property app works for the seller. Townhouse is the first one built for the buyer. A daily AI-ranked shortlist of London listings that actually fit. Open any property for an honest read on lease, layout, value. Saved gets smarter. No repeats.
Does a similar job
all alternatives →
- WMWe made a photo search engine for homes for sale2025 · ▲71
We're a small team of 3 engineers, and wanted to make a better way to look for for properties online. Traditional portals (esp. outside of US) are just a bit rubbish for doing anything other than basic searching. So we've: - Created a crawler that reads through estate agents websites to find homes for sale - Parses that through a series of LLMs and other models to understand each home in depth (e.g. floor type, location, total sqft) - Parses every photo through an embeddings vector space so that people can search for whatever they want. Check it out: https://jitty.com Currently…
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 · 17d 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, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com