News for hackers. Stuff that matters.

QaysHaji

Show HN: Azurite – Triage Linear and GitHub issues using MCP (Deck of Cards UI)

https://azurite-labs.vercel.app/

Hello HN,I’m the builder behind Azurite. I built this because I found that my bottleneck wasn't the volume of notifications (Linear, Slack, GitHub), but the context switching cost required to process them.The Problem: Every time I opened a Linear ticket, I had to:Read the ticket.Search Slack to find the thread where the decision was made.Check GitHub to see if the PR was actually merged....

( Read More... | 1 comment | 3 points | on HN )
Mornings used to be a war: 90+ minutes lost triaging Slack threads, Gmail, Linear tickets—just to get to real work. Endless tabs, unread badges, context switching. It's chaos designed to keep you trapped. I built Azurite to end it. It's like Tinder, but for your workspace notifications: everything distilled into one beautiful stack of decisions. No noise, no scrolling—just the context, AI-powered suggestions, and lightning-fast actions. How it works:

Pulls pings, emails, tickets via API into a clean, local-first queue. The Context: Summarizes what matters (no re-reading threads). The Brain: AI drafts replies, assignments, or summaries. The Gavel: Decide in seconds – Execute, Decline, Conditional, Customize. Latency <100ms, all offline-capable.

Result? That 90-minute morning slog → 4 minutes of clarity. Hours reclaimed for deep work. Azurite is coming Q1 2026 (macOS/Windows desktop app first). Integrations at launch: Gmail, Slack, Linear (+ more soon). Opening Charter Alpha-1 cohort (limited to 1,000 seats):

Instant access on launch day (skip the public queue). Roadmap voting + private community.

Join the waitlist (no card required): https://azurite-labs.vercel.app/ HN folks: Comment your biggest notification pain or which tool you'd mute forever—I'll prioritize real feedback for early spots.

Re:Runiq – A local, sovereign runtime for AI Agents (MCP) on Monday December 22, 2025 @10:42AM (#46355014)
Hi HN — I built Runiq: a local “sovereign runtime” that lets LLM agents (Claude Desktop, local Llama, etc.) use hardened tools to interact with your OS, instead of executing arbitrary shell/Python.

Runiq implements Anthropic’s Model Context Protocol (MCP) and exposes a small set of controlled capabilities:

Stealth Chromium browser for scraping/automation (aimed to survive common bot checks)

File operations and local workflow tools

Human-in-the-loop security: native OS popups block risky actions (write/delete/etc.) until you approve

It ships as a single static Go binary (no venv/daemon). It’s localhost-only and auditable; if you pair it with a local model, nothing leaves your machine. There’s also an optional Python adapter to use the same tool interface with OpenAI/Groq/LangChain-style agents.

Repo: https://github.com/qaysSE/runiq

I’d love feedback on the MCP implementation in Go, and on the security/UX tradeoffs for permission-gated agent actions.