Dropstone 1.5

What it does

Dropstone 1.5 is our monthly re-baseline release. We test the top AI coding models every month and rebuild the runtime on whichever wins. This month: DeepSeek V4 Flash, V4 Pro, and Moonshot Kimi K2.6 all hosted in the US, nothing stored on our side. $15/month gets you about 450 deep coding sessions a week. Roughly twice what Claude Code Pro delivers at $20. Full technical report with the cost math and benchmarks: blankline.org/research/dropstone-1-5

• 
  Edgee Turbo ModelsJun 2026 · ▲196

  Use Claude Code with Kimi K2.7 Code, MiniMax M2.7, and more

• 
  DropstoneNov 2025 · ▲113

  A self-learning AI IDE that evolves with your code

• 
  Dropstone 3Feb 2026 · ▲206

  The first multiplayer AI code editor. Now with Share Chat.

• 
  WOZCODEMay 2026 · ▲194

  Cut Claude Code costs by up to 50%

• 
  DropstoneDec 2025 · ▲199

  The Recursive Swarm IDE. 10,000 Agents in one tab

• 
  Edgee Fallback ModelsMay 2026 · ▲176

  Claude Code that never stops

• 
  I trained a 125M model to autocomplete piano on-device▲598

  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▲585

  Automate your B2B brand going viral, with new media creators

  AI · 18d ago · company-app.joinastute.com

• 
  Grok Bot▲547

  AI teammates that you can give real work to

  AI · 25d ago · x.ai

• 
  Needle2: 14MB agentic LLM for phones, wearables, smart home and robots▲537

  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

• 
  Coldtea.ai▲512

  Make your software self-driving

  AI · 30d ago · coldtea.ai

• 
  Soloop▲472

  Approval-first Agent OS for solo founders

  AI · 30d ago · soloop.io

• 
  Fundraisly▲1,544

  AI fundraising agent that finds investors and books meetings

  AI · Jun 2026 · fundraisly.com

• H6
  Homebrew 6.0.0▲1,481

  Today, I’m proud to announce Homebrew 6.0.0. The most significant changes since 5.1.0 are a new tap trust security mechanism, the new faster, smaller, default internal Homebrew JSON API, sandboxing on Linux, better defaults informed by our user survey, many brew bundle improvements, improved performance and initial support for macOS 27 (Golden Gate). Happy to discuss any questions here!

  Dev tools · Jun 2026 · brew.sh

• PU
  Performative-UI – A react component library of design tropes▲1,181

  hope you enjoy

  Life & fun · Jun 2026 · vorpus.github.io

• 
  Upstream▲977

  The inbox designed for humans and agents

  AI · Jun 2026 · upstream.do

• 
  Goldfish▲962

  Press Option. It knows your work and replies like you

  AI · Jun 2026 · goldfish.sh

• IM
  I made Google Trends for Hacker News by indexing 18 years of comments▲822

  Life & fun · Jun 2026 · hackernewstrends.com