Hacker News

Subscribe to Hacker News feed
Hacker News RSS
Updated: 31 min 52 sec ago

Show HN: Seite static site generator with MCP server and Claude Code integration

Wed, 02/25/2026 - 8:50am

I'm CTO at a startup, tired of maintaining five separate tools for our web presence while shipping software with Claude Code every day. So I built seite — a Rust SSG where the AI agent has a proper MCP interface to your site, not just file access.

seite mcp runs a Model Context Protocol server that exposes resources (docs, config, content, themes) and tools (build, create, search, apply theme) to any MCP-compatible agent. seite init also scaffolds a CLAUDE.md context file so the agent knows your schemas and conventions before it writes anything.

Everything else you'd expect: six bundled themes, collection presets for blog/docs/changelog/roadmap, one-command deploy to GitHub Pages/Cloudflare/Netlify, llms.txt and llms-full.txt on every build. Single binary, no runtime, sub-second builds. 331 tests.

MIT licensed, v0.1.6. Early but iterating fast — we're using it on our own startup's site so the feedback loop is tight.

curl -fsSL https://seite.sh/install.sh | sh Site: https://seite.sh Repo: https://github.com/seite-sh/seite

Comments URL: https://news.ycombinator.com/item?id=47151427

Points: 1

# Comments: 0

Categories: Hacker News

Language Models will be Scaffolds

Wed, 02/25/2026 - 8:49am
Categories: Hacker News

Show HN: First native zeroclaw build on Android/Termux (aarch64, no proot)

Wed, 02/25/2026 - 8:46am

Zeroclaw is a Rust-based Nostr client/relay tool. As of a few hours ago, no one had compiled it natively on Android.

Gemini CLI tried. Gemini Android tried. Both failed.

The blockers: — koffi's build script passes `make -j` bare, which Termux's make rejects — The default linker OOM-kills during the final link step (Android blocks swapon for unprivileged processes)

The fix: mold linker + codegen-units=1 + lto=thin + opt-level=z in a .cargo/config.toml

Binary: 15.5MB. Build time: 23m 55s. Kernel: Linux 5.4.284-moto. Completed at 04:11:47 CST.

Repo with binary, build config, and full reproduction steps: https://github.com/BleakNarratives/zeroclaw-android

Comments URL: https://news.ycombinator.com/item?id=47151385

Points: 1

# Comments: 0

Categories: Hacker News

Trig of Inverse Trig

Wed, 02/25/2026 - 8:45am
Categories: Hacker News

The new Design for Stack Overflow is now live [beta]

Wed, 02/25/2026 - 8:43am

Article URL: https://beta.stackoverflow.com/

Comments URL: https://news.ycombinator.com/item?id=47151351

Points: 2

# Comments: 1

Categories: Hacker News

Show HN: I scanned 35 SaaS products across ChatGPT, Claude, Perplexity, Gemini

Wed, 02/25/2026 - 8:43am

I built a scoring system to measure how AI models represent software products when users ask buying questions. The process: I take a product, generate the queries a buyer would ask (category, competitor alternatives, head-to-head), run them through ChatGPT, Claude, Perplexity, and Gemini, then score how prominently the product appears in each response (0-10). Some findings from scanning 35 products: ChatGPT is the biggest blind spot. It scores 0 for most open source challengers, even ones with 30K+ GitHub stars. Incumbents dominate across all models. "Best project management tool" returns Jira, Linear, Asana — never Plane (31K stars on GitHub). Brand-name queries work. "Cal.com vs Calendly" scores 9+ everywhere. But generic category queries ("best scheduling tool") often return 0. Having revenue doesn't help. Trigger.dev raised $16M and scores 0/10 for background job queries. The scoring methodology: each model gets 0-10 per query based on mention position, detail, and recommendation strength. Product consensus = average across all models and queries. Code and methodology are open. Happy to scan any product if you drop it in the comments.

Comments URL: https://news.ycombinator.com/item?id=47151344

Points: 1

# Comments: 0

Categories: Hacker News

UAA – A spec for AI and Human coding collaboration

Wed, 02/25/2026 - 8:42am

I just made my own spec to solve vibecoding issues with modern apps.

This specification is made for structuring how AI agents and humans collaborate in software systems.

Well, I tried to vibecode but my codebase was growing messy really fast. I was frustrated.

So, I tried to understand why, and the reason was simple!

Agents don't properly know where to put code (they need clear rules). In general, they don't know how to architect code. You have to guide them.

Thus, I revised my classics: MVC, Clean Code, Hexagon, etc.

And, took the best from these and made a modern spec that fits modern apps' needs (scalability, iterating fast, etc).

Check it here: https://www.zapstudio.dev/specifications/uaa

Comments URL: https://news.ycombinator.com/item?id=47151334

Points: 1

# Comments: 0

Categories: Hacker News

Show HN: Me.txt – A personal identity file for AI agents

Wed, 02/25/2026 - 8:42am

Article URL: https://www.metxt.org/

Comments URL: https://news.ycombinator.com/item?id=47151328

Points: 1

# Comments: 1

Categories: Hacker News

Pages