Generate docs from your public repos
Hello HN, I’m Andrew from docs.dev (https://docs.dev/), an AI powered docs assistant. With docs.dev you can generate your docs directly from your codebase, existing docs and other context sources. We don’t believe AI will replace technical writers—our goal is to make it easier for teams to get a solid first draft that they can review, edit, and improve. Think of it as a head start, not a finished product. More info on what we’ve built below but we wanted to release a quick, 1 minute, generate docs from your codebase tool. Try it out here:…
In plain words
docs.dev is an AI-powered documentation assistant that generates documentation directly from public GitHub repositories, existing docs, and other context sources. Designed for development teams, it creates a first-draft foundation that writers can review, edit, and refine rather than starting from scratch. The tool works on moderately sized public repos and aims to accelerate documentation creation while preserving the role of technical writers in the review and improvement process.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hello HN, I’m Andrew from docs.dev (https://docs.dev/), an AI powered docs assistant. With docs.dev you can generate your docs directly from your codebase, existing docs and other context sources. We don’t believe AI will replace technical writers—our goal is to make it easier for teams to get a solid first draft that they can review, edit, and improve. Think of it as a head start, not a finished product. More info on what we’ve built below but we wanted to release a quick, 1 minute, generate docs from your codebase tool. Try it out here: https://app.docs.dev/generate-docs-instantly. We built this page, so folks could generate some docs easily and quickly on some of their open source projects. It is still new so let us know if there are bugs but feel free to give it a try! It should work on any moderately sized public repo on GitHub. Why build another docs tool? We believe there are many great tools out there to help teams host their docs and make them look great, but that there aren’t enough tools to help teams manage the content that goes into them. We found that often there’s a disconnect between the devs shipping code and the teams managing the docs, often leading to delays in getting new features out the door or outdated docs. We kept hearing that the only thing worse than no docs is incorrect docs. So, we built tools to help you manage docs directly from your codebase—no special platforms or vendor lock-in required. With docs.dev you can not only generate first drafts of new docs, but also audit your existing docs in bulk, analyze them for effectiveness, and keep everything up to date as the product changes. docs.dev can: Work with any markdown-powered framework Generate clean markdown files synced with your GitHub repo Support existing markdown docs, your codebase, and even Slack threads as context More info at docs.dev (https://docs.dev/) and on our docs page (https://learn.docs.dev/) We’d love for you to check us out and welcome any feedback, criticism, suggestions, questions, or ideas! Thanks so much for reading!
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, March 2025
the whole month →
Mimic Human Research & Save Findings in AI Knowledge Base
AI · 2025 · sider.ai
