akadhanu

Re: on Wednesday September 30, 2026 @01:21PM (#49911790)

I kept running into broken OG/Twitter Card previews while building websites, especially with localhost and staging URLs.

So I came across this Prevu a small open-source tool to inspect social metadata and preview how a URL will look when shared.

Runs fully locally, no data retention.

Re:Show HN: Hallx – Hallucination risk scoring for LLM outputs on Friday April 03, 2026 @03:03AM (#47623985)

yeah.. right now working on that.. thank you for your insights :)

Show HN: Hallx – Hallucination risk scoring for LLM outputs

Posted by akadhanu on Thursday April 02, 2026 @11:35AM
from the show-hn dept.

https://github.com/dhanushk-offl/hallx

I got tired of LLM outputs silently failing in pipelines, so I built a small scoring layer around it.It checks three things before your output moves forward: does it match the schema you expected is it consistent across runs does it actually align with the context you providedReturns a confidence score and a risk level. That's mostly it.Works with OpenAI, Anthropic, Gemini, Ollama and a few...

( Read More... | 2 comments | on HN )

Show HN: Guro – Python CLI system monitoring, benchmarking and telemetry tool

Posted by akadhanu on Thursday February 05, 2026 @02:24PM
from the show-hn dept.

https://github.com/dhanushk-offl/guro

I built Guro as a lightweight, cross-platform CLI tool for system monitoring and basic benchmarking in Python.It focuses on a clean, script-friendly interface with real-time CPU, memory, thermal, and (where available) GPU metrics. Installation is via pip, and it runs on Linux, macOS, and Windows.This started as a personal tool to better understand system behavior during development and testing....

( Read More... | no comments | on HN )