🛠️ Hacker News Tools

[Other] Introducing: ShaderPad

[CLI Tool] Show HN: Libretto – Making AI browser automations deterministic Libretto (<a href="https:&#x2F;&#x2F;libretto.sh" rel="nofollow">https:&#x2F;&#x2F;libretto.sh</a>) is a Skill+CLI that makes it easy for your coding agent to generate deterministic browser automations and debug existing ones. Key shift is going from “give an agent a prompt at runtime and hope it figures things out” to: “Use coding agents to generate real scripts you can inspect, run, and debug”.<p>Here’s a demo: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=0cDpIntmHAM" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=0cDpIntmHAM</a>. Docs start at <a href="https:&#x2F;&#x2F;libretto.sh&#x2F;docs&#x2F;get-started&#x2F;introduction" rel="nofollow">https:&#x2F;&#x2F;libretto.sh&#x2F;docs&#x2F;get-started&#x2F;introduction</a>.<p>We spent a year building and maintaining browser automations for EHR and payer portal integrations at our healthcare startup. Building these automations and debugging failed ones was incredibly time-consuming.<p>There’s lots of tools that use runtime AI like Browseruse and Stagehand which we tried, but (1) they’re reliant on custom DOM parsing that&#x27;s unreliable on older and complicated websites (including all of healthcare). Using a website’s internal network calls is faster and more reliable when possible. (2) They can be expensive since they rely on lots of AI calls and for workflows with complicated logic you can’t always rely on caching actions to make sure it will work. (3) They’re at runtime so it’s not interpretable what the agent is going to do. You kind of hope you prompted it correctly to do the right thing, but legacy workflows are often unintuitive and inconsistent across sites so you can’t trust an agent to just figure it out at runtime. (4) They don’t really help you generate new automations or help you debug automation failures.<p>We wanted a way to reliably generate and maintain browser automations in messy, high-stakes environments, without relying on fragile runtime agents.<p>Libretto is different because instead of runtime agents it uses “development-time AI”: scripts are generated ahead of time as actual code you can read and control, not opaque agent behavior at runtime. Instead of a black box, you own the code and can inspect, modify, version, and debug everything.<p>Rather than relying on runtime DOM parsing, Libretto takes a hybrid approach combining Playwright UI automation with direct network&#x2F;API requests within the browser session for better reliability and bot detection evasion.<p>It records manual user actions to help agents generate and update scripts, supports step-through debugging, has an optional read-only mode to prevent agents from accidentally submitting or modifying data, and generates code that follows all the abstractions and conventions you have already in your coding repo.<p>Would love to hear how others are building and maintaining browser automations in practice, and any feedback on the approach we’ve taken here.

[Other] Show HN: MCP server gives your agent a budget (save tokens, get smarter results) As a consultant I foot my own Cursor bills, and last month was $1,263. Opus is too good not to use, but there&#x27;s no way to cap spending per session. After blowing through my Ultra limit, I realized how token-hungry Cursor + Opus really is. It spins up sub-agents, balloons the context window, and suddenly, a task I expected to cost $2 comes back at $8. My bill kept going up, but was I really going to switch to a worse model?<p>No. So I built l6e: an MCP server that gives your agent the ability to budget. It works with Cursor, Claude Code, Windsurf, Openclaw, and every MCP-compatible application.<p>Saving money was why I built it, but what surprised me was that the process of budgeting changed the agent&#x27;s behavior. An agent that understands the limitations of the resources doesn&#x27;t try to speculatively increase the context window with extra files. It doesn&#x27;t try to reach every possible API. The agent plans ahead, sticks to it, and ends work when it should.<p>It works, and we&#x27;ve been dogfooding it hard. After v1 shipped, the rest of l6e was all built with it. We launched the entire docs site using frontier models for $0.99. The kicker was every time l6e broke in development, I could feel the pain. The agent got sloppy, burned through context, and output quality dropped right along with it.<p>Install: pip install l6e-mcp<p>Docs: <a href="https:&#x2F;&#x2F;docs.l6e.ai" rel="nofollow">https:&#x2F;&#x2F;docs.l6e.ai</a><p>GitHub: <a href="https:&#x2F;&#x2F;github.com&#x2F;l6e-ai&#x2F;l6e-mcp" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;l6e-ai&#x2F;l6e-mcp</a><p>Website: <a href="https:&#x2F;&#x2F;l6e.ai" rel="nofollow">https:&#x2F;&#x2F;l6e.ai</a><p>Happy to answer questions about the system design, calibration models, or why I can&#x27;t go back to coding without it.

[Other] Elevated errors on Claude.ai, API, Claude Code

[Monitoring/Observability] MCP as Observability Interface: Connecting AI Agents to Kernel Tracepoints

[Other] Binary Encodings for JSON and Variant

[Other] Show HN: Every CEO and CFO change at US public companies, live from SEC Built this solo. It watches SEC filings for executive and board changes, extracts the data, and shows it in real time. 2,100+ changes in the last 30 days. The comp data is interesting: average new CEO total comp is $8.4M across 284 appointments. The &#x2F;explore page is fully open, no login needed.

[Other] Retrofitting JIT Compilers into C Interpreters

[Other] Nanopass Framework: Clean Compiler Creation Language

[Other] Show HN: Xit – a Git-compatible VCS written in Zig The marquee feature is patch-based merging, similar to Darcs and Pijul. I think xit is the first version control system (VCS) to have this feature while still being git compatible. See the 100% human-written readme for more.

[Other] Want to Write a Compiler? Just Read These Two Papers (2008)

[Other] Direct Win32 API, Weird-Shaped Windows, and Why They Mostly Disappeared

[CLI Tool] Wacli – WhatsApp CLI: sync, search, send

[Other] CadQuery is an open-source Python library for building 3D CAD models

[Other] Your codebase doesn't care how it got written

[Other] Show HN: Plain – The full-stack Python framework designed for humans and agents

[Other] Turn your best AI prompts into one-click tools in Chrome

[Other] Claude Code Routines

[Database] 5NF and Database Design

[Monitoring/Observability] Show HN: Kelet – Root Cause Analysis agent for your LLM apps I&#x27;ve spent the past few years building 50+ AI agents in prod (some reached 1M+ sessions&#x2F;day), and the hardest part was never building them — it was figuring out why they fail.<p>AI agents don&#x27;t crash. They just quietly give wrong answers. You end up scrolling through traces one by one, trying to find a pattern across hundreds of sessions.<p>Kelet automates that investigation. Here&#x27;s how it works:<p>1. You connect your traces and signals (user feedback, edits, clicks, sentiment, LLM-as-a-judge, etc.) 2. Kelet processes those signals and extracts facts about each session 3. It forms hypotheses about what went wrong in each case 4. It clusters similar hypotheses across sessions and investigates them together 5. It surfaces a root cause with a suggested fix you can review and apply<p>The key insight: individual session failures look random. But when you cluster the hypotheses, failure patterns emerge.<p>The fastest way to integrate is through the Kelet Skill for coding agents — it scans your codebase, discovers where signals should be collected, and sets everything up for you. There are also Python and TypeScript SDKs if you prefer manual setup.<p>It’s currently free during beta. No credit card required. Docs: <a href="https:&#x2F;&#x2F;kelet.ai&#x2F;docs&#x2F;" rel="nofollow">https:&#x2F;&#x2F;kelet.ai&#x2F;docs&#x2F;</a><p>I&#x27;d love feedback on the approach, especially from anyone running agents in prod. Does automating the manual error analysis sound right?