Ask HN: What Are You Working On? (April 2026)

Building https://vazi.io/ - AI intelligence for your brand. Basically AEO for your brand / website

I’m working on docmancer (https://github.com/docmancer/docmancer), an MIT-licensed, local-first tool that fetches and indexes technical docs on your machine so coding agents can query it directly.

The goal is to become a local, version-aware alternative to tools like Context7. Pull the docs once, query locally, and use audited packs that match your project stack.

Docmancer also reduces context bloat by returning only the relevant sections instead of dumping full docs into the prompt, which can cut token usage by up to 80%.

No MCP server required. Your coding agents can access docs directly through the CLI.

[dead]

Hey HN!

I’m building Reviewskits (https://reviewskits.com).

Most startups today use 3+ different tools to manage user feedback: one for testimonials (Senja/Testimonial.to), one for feature voting (Canny), and another for bug reports. It’s a mess of different invoices and fragmented data.

We are building a unified platform for all customer sentiment, starting with a headless testimonial engine.

Why Reviewskits?

    Headless & Dev-first: Instead of heavy, slow iFrame widgets that mess with your CLS, we provide clean APIs and SDKs (React, Vue, Svelte). You keep 100% control over the UI/UX.

    Open-Source: You can self-host it to own your data or use our managed Cloud version.

    Consolidated: One tool for testimonials today, feature requests and feedback loops tomorrow.

The project is early-stage and fully open-source. We’d love your feedback on the architecture or the "Headless" approach for social proof.

Repo: https://github.com/reviews-kits-team/reviews-kits Cloud Waitlist: https://reviewskits.com/

If you like the vision of an open-source, unified feedback stack, we’d appreciate a on GitHub!

[dead]