g023 Code
DeepSeek V4 Flash Optimized Harness w/Ollama vision support
What it does
A pure-Python AI coding agent harness optimized for DeepSeek v4 Flash that reads your project, searches code & the web, runs commands, and fetches pages, all while showing you exactly what it's doing and estimating what it costs. Built on DeepSeek's Responses API with native web search, subagent-first architecture, and a terminal-native interface. You can also use Ollama local or on another server to power the vision capabilities.
Does the same job
all alternatives →
DeepSeekGUI – A Windows desktop client for DeepSeek's coding agent7d ago · github.com · ▲5Hi HN, I built a desktop client for DeepSeek Harness (DeepSeek's open-source coding agent). V1 wraps the official Harness Web UI in an Electron shell with some desktop additions — installer, system tray, built-in browser panel (visible Edge, so you can watch the agent browse), and a sandboxed terminal. One-click install, just need an API key. V2 is in development — replacing the upstream Web UI with a custom workbench built for desktop. Source available under PolyForm Perimeter. Would love feedback on what you'd want from a desktop coding agent client.
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