Show HN: Grammit – Local-only AI grammar checker (Chrome extension)
Hacker News (score: 13)Description
Here’s a 2-minute overview: https://www.loom.com/share/baf501ee6cf14a919a7384128246ed67
Because it uses an LLM, it catches more than spelling and grammar. For example, it can correct some wrong statements like “The first US president was Benjamin Franklin.”
Grammit also includes an in-page writing assistant that can rephrase or draft new text. It also uses the local LLM.
We used many new web features to build this, such as:
- Chrome’s new Prompt API to talk to the local model.
- Anchor Positioning API to place the UI with minimal impact on the DOM.
- CSS Custom Highlights API for inline error marking.
- The new CSS sign() function to create CSS-driven layout with discontinuities.
Part of the fun of being early adopters of bleeding edge tech is we’re discovering new Chrome bugs (e.g., https://issues.chromium.org/issues/428354426, https://issues.chromium.org/issues/428039224).
I’d love your feedback on:
- Where the UX feels rough
- What do you think of the corrections and suggestions
Happy to answer questions about the tech or the Prompt API. Thanks for trying it out!
Chrome Web Store extension link: https://chromewebstore.google.com/detail/grammit-the-ai-gram...
More from Hacker
Security vulnerability found in Rust Linux kernel code
Security vulnerability found in Rust Linux kernel code
Show HN: Wirebrowser – A JavaScript debugger with breakpoint-driven heap search
Show HN: Wirebrowser – A JavaScript debugger with breakpoint-driven heap search Hi HN!<p>I'm building a JavaScript debugger called Wirebrowser. It combines network inspection, request rewriting, heap snapshots, and live object search.<p>The main experimental feature is BDHS (Breakpoint-Driven Heap Search): it hooks into the JavaScript debugger and automatically captures a heap snapshot at every pause and performs a targeted search for the value or structure of interest. This reveals the moment a value appears in memory and the user-land function responsible for creating it.<p>Another interesting feature is the Live Object Search: it inspects runtime objects (not just snapshots), supports regex and object similarity, and lets you patch objects directly at runtime.<p>Whitepaper: <a href="https://fcavallarin.github.io/wirebrowser/BDHS-Origin-Trace" rel="nofollow">https://fcavallarin.github.io/wirebrowser/BDHS-Origin-Trace</a><p>Feedback very welcome, especially on whether BDHS would help your debugging workflow.
Show HN: Dograh – an OSS Vapi alternative to quickly build and test voice agents
Show HN: Dograh – an OSS Vapi alternative to quickly build and test voice agents Hi HN, I have been building voice agents for sometime now. I was earlier automating parts of visa processing, and we needed real-time, multilingual voice calling.<p>I assumed the hard work was just wiring LiveKit/Pipecat + STT/TTS + an LLM. It wasn’t.<p>Even with solid OSS (Pipecat/LiveKit), we still had to do a lot of plumbing- variable extraction, tracing, testing etc and any workflow changes required constant redeploys.<p>We eventually realized we’d spent more time building infrastructure than building the actual agents. Everything felt custom. We hit every possible pain with Pipecat and VAPI style systems.<p>So we built Dograh - a fully open-source voice agent framework that includes all the boring, painful pieces by default.<p>What’s different:<p>- Pipecat-based engine, but forked - custom event model, and concurrency fixes<p>- One-click start template generated by an LLM Agent for a quick get start template for any use case<p>- Drag-and-drop visual agent builder for quick iteration (the thing we wished existed earlier)<p>- Variable extraction layer (name/order/date/etc.) baked into the LLM loop<p>- Built in Telephony integration (Twilio/ Vonage/ Vobiz/ Cloudonix)<p>- Multilingual support end-to-end<p>- Select any LLM TTS STT (add their credits, if any)<p>- AI-to-AI call testing: automatically stress-test an agent before shipping (still a work in progress- so patchy as of now)<p>- Fully Open Source<p>It's built and maintained by YC alumni / exit founders who got tired of rebuilding the same plumbing.<p>Why we open-sourced it: We kept feeling that the space was drifting toward closed SaaS abstractions (VAPI, Retell). Those are good for demos, but once you need data controls, privacy or self/offline deployment, you end up stuck. We wanted a stack where you can see every part, fork it, self-host it, and patch it as needed.<p>Try it:<p>- Repo: <a href="https://github.com/dograh-hq/dograh" rel="nofollow">https://github.com/dograh-hq/dograh</a><p>This spins up a basic multilingual agent with everything pre-wired.<p>Who this is for:<p>- If you are looking for self hosting a Vapi like platform for Data Privacy etc.<p>- Anyone trying to build production-grade voice agents without reinventing audio plumbing.<p>- If you’ve tried to glue STT→LLM→TTS manually, you probably know the exact pain this is built for<p>Happy to answer technical questions, show the architecture, or hear how we can improve the product.
Reinventing how .NET builds and ships (again)
Reinventing how .NET builds and ships (again)
No other tools from this source yet.