Agentsearch – browse any docs as a filesystem
Hi HN, I built agentsearch, a free tool that turns any documentation website into a browsable filesystem that you can access with one command. npx nia-docs https://docs.anthropic.com This opens a shell where the docs are mounted as files. You can: - tree to explore - grep across pages - cat specific files The idea is simple: let agents read docs the same way developers read codebases. Most coding errors from agents come from stale or incomplete context. Docs change constantly, but models are trained on old data. RAG helps, but it returns fragments. In practice, a lot of answers…
What it does
In the maker’s words, at launch
Hi HN, I built agentsearch, a free tool that turns any documentation website into a browsable filesystem that you can access with one command. npx nia-docs https://docs.anthropic.com This opens a shell where the docs are mounted as files. You can: - tree to explore - grep across pages - cat specific files The idea is simple: let agents read docs the same way developers read codebases. Most coding errors from agents come from stale or incomplete context. Docs change constantly, but models are trained on old data. RAG helps, but it returns fragments. In practice, a lot of answers live across multiple pages or require exact structure that chunking loses. Instead of retrieving snippets, this lets the agent just browse the docs directly. Under the hood: - we crawl the docs site and map each page to a file - expose basic filesystem ops (read, grep, tree, find) - run a lightweight bash-like shell client-side - Everything is read-only and cached. You can also plug it into agents in one line: npx nia-docs setup https://docs.site.com | claude Then the agent can do things like: - grep -rl "webhook" . - cat getting-started.md and write code against the latest docs instead of training data. The reason for the filesystem approach is that agents already know it. Models have seen a huge amount of bash usage during training, so tools like grep and cat work out of the box without teaching new abstractions. Right now this works on documentation sites. The longer term idea is making more of the web navigable like a codebase. Would love feedback, especially from people building agent workflows. Website: https://www.agentsearch.sh/
Does the same job
all alternatives →
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 2026
the whole month →
- AG
Thought the resources for GPU arch were lacking, so here we are
Life & fun · Apr 2026 · jaso1024.com
- IB
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
AI · Apr 2026 · github.com
- BC
Life & fun · Apr 2026 · sam-burns.com
- IB
With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.
AI · Apr 2026 · text.blogosphere.app