Distill

What it does

Distill is a token-efficiency toolkit for AI coding agents that attacks both sides of your token bill — what the model writes and what gets loaded into its context — with one rule no other compression tool enforces: safety-relevant content is never, ever compressed. Not by prompt etiquette. By code. Works with Claude Code, Cursor, Windsurf, Cline, Codex, Copilot, Gemini CLI, and any MCP-compatible agent.

A Smarter Token-Compression Toolkit. Contribute to arzoo14/distill development by creating an account on GitHub.

Beta. The architecture is tested (65 unit tests, a soak test with 3.95M real MCP operations, CI on Node 18/20/22) and the benchmark numbers below are real — but this is a first release with limited field usage. APIs, defaults, and telemetry formats may still shift before 1.0. Feedback and issues genuinely welcome: that's what a beta is for. Distill is a token-efficiency toolkit for AI coding agents that attacks both sides of your token bill — what the model writes and what gets loaded into its context — with one rule no other compression tool enforces: safety-relevant content is never, ever compressed. Not by prompt etiquette. By code. Works with Claude Code, Cursor, Windsurf, Cline, Codex,…from github.com

• 
  Distill2017 · distill.pub · ▲200

  An interactive, visual journal for Machine Learning research

• 
  Distilling DeepSeek into GPT-OSS doesn't transfer censorship. Try itJul 2026 · ctgt.ai · ▲170

  We recently used DeepSeek V4 Flash as a teacher for finance tasks with GPT-OSS-120B. Distillation works well on this problem. At a constrained 8k token budget, our self-distilled 120B scores 83.61% on FinanceReasoning, above Kimi K3 (81.93%) and Inkling (65.13%). We released the 20B open weights. With V4 as the teacher though, we realized it would be timely to measure if the censorship characteristic of it transferred to the distilled version of the base model. tl;dr it didn't, the teacher answered politically sensitive questions 7 SDs differently than expected, but the distilled model's…

• 
  DistilKitPlus, a distillation framework between any LLMs2025 · github.com · ▲10

  Over the past few months, I have built a distillation toolkit that supports cross-tokenizer distillation (e.g., distilling from LLaMA to Qwen vocab, or others). This approach has worked well on reasoning datasets like AIME, and we’ve validated on models like Phi and Qwen. We’ve also integrated Modal for quick deployment (with $30/month credits to try it out). Would love any feedback! GitHub: https://github.com/agokrani/distillKitPlus Docs: https://distillkitplus.mintlify.app/

• 
  AgentReadyFeb 2026 · agentready.cloud · ▲118

  Compression API that reduces prompt size by 40-60% before sending to your LLM. Your API key never leaves your environment.

• 
  Distill[bot]May 2026 · distillbot.com · ▲3

  Stop drowning in duplicate AI code review feedback

• 
  DistillNov 2025 · distillintelligence.com · ▲20

  Hi everyone, I just launched Distill, a tool automate company and industry monitoring by tracking every move from any company on autopilot. I built it to solve a problem I had working in VC - that there's no way to get all the news and updates from all companies you care about in the same place and feed. Larger companies may be covered in regular news media, but smaller ones may only post something on their websites. Distill solves this with your own news feed where you can add any company (large or small, public or private), and get all relevant updates summarized and sent to you…

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 17d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 17d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 19d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 20d ago · stillwet.art

• 
  PixVerse R2▲381

  A real-time world model you can explore and change

  AI · 29d ago · world.pixverse.video

• 
  Hemory▲381

  Keep listening. Searchable memory for your AI agents.

  AI · 30d ago · hemory.com

• TL
  The load-bearing vocabulary of Claude▲710

  Life & fun · Aug 2026 · louisabraham.github.io

• 
  Hey Noah▲656

  A proactive AI executive assistant for founders

  AI · Aug 2026 · heynoah.io

• 
  Clipto MCP▲655

  Hey HN, We recently built Clipto. It’s a tool that lets you search over terabytes of video, audio, and images on your computer, without relying on the cloud. Motivation: we probably all had this similar experience, we know a moment exists in a video or audio, but finding it takes hours scrubbing the timeline. You can send all the media to process in the cloud, but it’s slow, expensive and raises privacy concerns. So we decided to build our own on-device media search engine. How it works (high level): 1. We ingest video, audio, image; normalize formats via ffmpeg; run content analysis to…

  Work · Aug 2026 · clipto.com

• 
  Simple algorithm and color space to generate diverse skin tones▲627

  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

• 
  AdAnt AI▲620

  Claude for viral, high-converting social ads

  AI · Aug 2026 · adant.ai

• 
  Astute▲606

  Automate your B2B brand going viral, with new media creators

  AI · Aug 2026 · company-app.joinastute.com