janwilmake
Re:Markdown Browser
on Friday March 06, 2026 @11:38AM (#47277263)
I created a browser that lets you see the markdown variant of all pages you visit, and llms.txt becomes your navigation.
Markdown Browser
Re:Show HN: Badge that shows how well your codebase fits in an LLM's c...
on Thursday March 05, 2026 @06:51AM (#47260557)
Hi, i just open sourced my alternative at https://github.com/janwilmake/forgithub.badge, which is backed by uithub.com. The advantage is that you don't need a github action to calculate and it still auto-updates daily; also, if you click, you go to uithub to further trim the context window which can be useful if the whole codebase doesn't fit or if you want higher quality outputs.
Show HN: Markdown Browser – See the Web the Way AI Sees It
Re:Llmtext – an open source toolkit for llms.txt adoption
on Thursday October 30, 2025 @04:03PM (#45764662)
Hey HN! Super excited to launch this OSS project to support the llms.txt ecosystem.
Similar to how Context7AI works, but you use LLM reasoning on the overview of the entire docs, instead of vector search. Also, you get a dedicated MCP server for the websites you need it for most!
In the process of making this, I discovered more than half of llms.txt live today are not spec-compliant. with LLMTEXT we're fixing this with tools to validate and create better llms.txt's! Read more in the blogpost.
Would love feedback from the HN community on both the tools and the broader question of how we should be serving AI agents vs. humans on the web.
Re:Launch HN: Airweave (YC X25) – Let agents search any app
on Tuesday September 30, 2025 @03:24PM (#45430066)
Hey Lennert, congrats on the launch! Still open to chat about uithub
Show HN: OpenAPI to MCP
https://github.com/janwilmake/openapi-to-mcp
Hell yeah! I had this idea since MCP came out, but I FINALLY got it to work: OpenAPI to MCP is a fact:Convert ANY server described with openapi into an MCP endpoint!mcp.openapisearch.com/anyhostname.tld/mcpThere are a few requirements to it, but: If the server serves REST described with OpenAPI and if it either has NO auth OR implements OAUTH the MCP way, it will automatically work!Check the repo!
Re:JWTs and OAuth suck for AI agents. Meet Wafers
on Tuesday September 02, 2025 @12:36PM (#45105439)
really cool! the problem with new standards though is that it's hard to adopt. what's your plan to adoption? because nobody will understand it if it's not in terms of things they already use/understand.
curious if this can somehow slot into oauth too, or this is impossible? I've been thinking about oauth proxies that alter the oauth scopes into more fine-grained ones, working on this. maybe this is the key to adoption.
After hours of iteration, I one-shotted a Web Search Agent
Re:After hours of iteration, I one-shotted a Web Search Agent
on Wednesday August 27, 2025 @07:46AM (#45038333)
Sharing my context engineering process in detail!
Since every developer is independently building new strategies to do good context engineering, I'm super curious to hear other people's takes on how to do builds like this!
Re:Show HN: OverType – A Markdown WYSIWYG editor that's just a textarea
on Sunday August 17, 2025 @12:53PM (#44932986)
Really cool! I just love the simplicity of it: has no drawbacks compared to regular textarea, but has lots of benefits. you basically improved textarea, by a lot!
I also made a similar thing a while ago called contextarea.com, maybe, I should add overtype!
Show HN: I built a directory of public appearances of tech people across the web
Hey HN! I've always been frustrated by having to follow people across 10 different platforms just to catch what they actually say. Lately I've quit following other media entirely and am just hanging out on twitter, but the amount of things I'm missing is vast, I'm sure.Recently I started playing with this new API from Parallel AI that let's you do super deep web research and collect tons of...
Re:Show HN: TokenDagger – A tokenizer faster than OpenAI's Tiktoken
on Monday June 30, 2025 @10:18AM (#44423620)
You know what's also faster to roughly get the amount of tokens? string.length/5
Re:Building a Hacker News OAuth Provider from First Principles
on Friday June 27, 2025 @07:48AM (#44396019)
Email sent.
Re:Building a Hacker News OAuth Provider from First Principles
on Friday June 27, 2025 @07:29AM (#44395926)
Hey HN,
Today I woke up with the idea of making an agent-friendly version of hacker news. The coolest would be to also make it able to login, but that didn't work out, since I got blocked.
However, I made an oauth provider for HN, and it works on my machine. Unfortunately the IP gets blocked in production, so this isn't gonna work out. Even with a residential proxy, I started to get Captcha protection.
I'd love to make a 'login with Hackernews' so third party apps can build cool stuff with it. The code's all there.
Can you whitelist me?
Cheers, Jan
Building a Hacker News OAuth Provider from First Principles
Show HN: GoogLLM – Google search that returns Markdown instead of HTML
As part of my bigger goal to make the web more agent-friendly, this weekend i decided to tackle google. The "AI-native" search APIs like Tavily and Exa exist, but they require setup and don't actually use Google's results.So I built something simple - a proxy that takes Google search URLs and returns the results as clean markdown instead of HTML. You literally just change "google.com" to...
Show HN: Let Me Prompt It for You
Ok so over the last 9 days I built lmpify. my personal driver was i want to replace claude because it's annoying. Their Claude3.7 model is perfect for coding, but the Claude.ai interface doesn't cut it for me for these reasons:- Very slow to start up and TTFT is terrible. lmpify hits within 100ms and doesn't need to wait for pageload to start seeing result, result is already starting in DO as...
Dorm 1.0.0 next – OSS Turso Alternative
Re:Dorm 1.0.0 next – OSS Turso Alternative
on Monday May 12, 2025 @10:25AM (#43963338)
Here's the prerelease of DORM 1@next. I needed cheap performant multi-tenant databases on cloudflare, and the experience on Durable Objects was very painful.
This is my attempt at solving that DX.
Now it's slowly becoming a OSS Turso Alternative, I think. What does it not have yet? Curious for your feedback.
Re:UIT – performant, modular, low-memory file processing at scale, in ...
on Friday April 25, 2025 @06:02PM (#43798946)
I think especially at the start the modularity of a system is relatively expensive, but once you add more modules, it starts making sense. Gotta find a vertical where lots of variety in modules can create value.
Re:UIT – performant, modular, low-memory file processing at scale, in ...
on Friday April 25, 2025 @10:31AM (#43793987)
Early release. Please see the repo for the X thread.
Hope you like it. I'm happy to answer any questions here or on X.
UIT – performant, modular, low-memory file processing at scale, in the Cloud
Show HN: UIT – Library for performant, modular, low-memory file processing
https://github.com/janwilmake/uit
UIT is a library for performant, modular, low-memory file processing at scale, in the Cloud. It works by offering a 4-step process to gather a file hierarchy from any desired modalty, apply filters and transformations, and output it in any desired modality.- *performance*: speed is of essence when navigating and searching through large amounts of data - *low-memory* by applying streaming and...
Re:Shared Application Layer for Agents, Crawlers, Humans, and APIs
on Wednesday March 26, 2025 @01:47PM (#43484771)
The web’s stuck serving one format for all—HTML for humans, but what about bots, APIs, or social previews? It’s a legacy mess.
Here’s the thing: one page should adapt—HTML for crawlers, JSON for APIs, Markdown for agents, and PNG for social. Same data, smartly served.
I built a Cloudflare Worker to ditch legacy bloat. Vanilla JS/HTML/CSS, no frameworks, just a shared layer for all clients. First principles.
Meet my User-Agent Router: a Worker that picks the right format (HTML, MD, JSON, YAML, PNG) via headers or paths. Simple, fast, flexible.
Read more in the repo, check the demo, and lmk what you think!
Shared Application Layer for Agents, Crawlers, Humans, and APIs
Show HN: XYMake – Turn Your Posts into LLM-Ready Data
I just built XYMake (https://xymake.com), a tool that lets you convert any X (Twitter) thread into clean markdown, making your conversations accessible for LLMs, MCPs, or any API.## What it does: - Transforms any X thread URL into markdown by simply changing "x.com" to "xymake.com" in the URL - OAuth2 login to "free your data" and make your threads available - Auto-generates OG images with...
Show HN: OpenAPISearch – Make APIs Accessible for AI Codegen
Hey Hackernews!In the last few days I've dug up some work I was working on last year but never was able to ship due to perfectionism.But with my new attitude, here it is: I also immediately got it in MCP-form so you can use it in Claude and Cursor as well.Enable Claude / Cursor to know ANY API!! Video and links here: https://x.com/janwilmake/status/1903497808134496583P.S. Expect bugs....