Wingman – Open-source Chatbot that's light, functional and not ugly
Hey HN, I’m really excited to show off a project I’ve been tweaking and tuning for more than seven months. One thing that drove me nuts about running LLMs locally was having to use terminals, install Python, and write code for the most basic things. I write software, but I don’t want to have to write it just to use a chatbot. So, I made Wingman with a friendly interface that lets you get started with zero coding or terminals required. It runs on MacOS and Windows, and even evaluates AI models up front to determine if they will run on your machine. There’s other stuff it does, too, like let…
In plain words
Wingman is an open-source chatbot application for MacOS and Windows that eliminates the need for terminal commands, Python installation, or coding to run large language models locally. It features a straightforward interface, evaluates whether AI models will run on your machine before loading them, and allows users to save prompts, set system instructions per conversation, and switch models mid-chat. The application also sorts models by popularity and trending status to help users discover new options.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN, I’m really excited to show off a project I’ve been tweaking and tuning for more than seven months. One thing that drove me nuts about running LLMs locally was having to use terminals, install Python, and write code for the most basic things. I write software, but I don’t want to have to write it just to use a chatbot. So, I made Wingman with a friendly interface that lets you get started with zero coding or terminals required. It runs on MacOS and Windows, and even evaluates AI models up front to determine if they will run on your machine. There’s other stuff it does, too, like let you save prompts, set system prompts per conversation, and change AI models mid-conversation. I added a way to sort models by popular or trending. It’s been pretty helpful to me for staying on top of all of the new models dropping. But it still has a little way to go to be ready for really special things like planning and reasoning. So, I need to get some more feedback from people on different configurations. I’d love it if you checked it out, saw if it was useful, and maybe broke it so I could find fixes. Thank!
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 · 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, April 2024
the whole month →
Supabase▲2,328The Postgres developer platform is now generally available
Dev tools · 2024 · supabase.com
Cal.com Platform▲1,602Build your pixel-perfect booking experience with Atoms
Dev tools · 2024 · cal.com
deco.cx 2.0▲1,080Build web apps 10x faster with Deno, JSX, TS & Tailwind
Dev tools · 2024 · decocms.com
