craigsmitham

@connecula · X

Guys, if you're building AI agents We are building LinkedIn for ai agents See your ai agents how they talk to other ai agents and hire other AI agents to do work so drop your AI agents here

miketromba · HN

Cronloop, run Claude Code or Codex on a schedule

Gliss — AI Music Agent，用于歌曲生成、翻唱、MIDI 编辑、母带处理与封面艺术；可生成免版税人声与伴奏，并支持精确分轨/元素提取。

@amjLane · X

People will stop vibe coding their own crms, accounting systems and the like when $60/mo falls to $2/mo. Legacy saas cannot do this without cutting 95% of their headcount. That’s why we are building something interesting at

fayazara · HN

Headless Tools – No UI SaaS tools for agents

@amarHarolikar · X

I have rebuilt the Markdown to PDF converter on You paste your text or Markdown, you get a properly typeset PDF back, and your AI agent can do the same over MCP or a plain API call. No sign up, no key, free. Had built this a long time back as a fairly basic thing and then left it alone, and over the last few weeks I could see a rise in traffic. Took a fresh look and found that lot of it was not rendering. Headings below a certain level were being dropped, nested lists were coming out flat, and code blocks were losing their formatting. What is there now: - Page breaks where you want them, using :::pagebreak::: on a line by itself - Tables, nested lists, task lists and code blocks all render properly - Greek letters, maths symbols, arrows and the rupee sign come out right - Emoji and symbols do not break the render - Plain dot txt files keep their line breaks Live tool at API & MCP docs (humans): API & MCP docs (AI)

Loerei · HN

I found that describing where a broken UI is and taking screenshots for AI agents really sucks. I’m too lazy to explain an indescribable visual bug or capture a millisecond-long flash. I also don’t want to remember which file defines an element, whether it's right in the .tsx or a problem with the Parent Styles in .css. And even if you can point out the exact file, your agent still has to dig through thousands of lines of code to know what on earth you're yapping about. In a 7700-file monorepo like Cal.com, simply giving the right file in the prompt for your agent saves about 68.9% of execution time and 94.2% of the tokens your agent needs to digest. HoverSource gives all the needed information and further pushes it to -88.5% time and -94.5% tokens, basically skipping the entire digging session and jumping straight to reasoning and executing. The save is linear to how big your codebase is. I want to save tokens, but don’t want to spend my time and energy digging manually, and a junio