HN Showcase
Back to browse
Qurt – open-source desktop AI coworker (BYOK, agent mode)

Qurt – open-source desktop AI coworker (BYOK, agent mode)

by buhhalter·Mar 6, 2026·2 points·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidShip ItSolve My Problem

Electron app with agent mode and BYOK, but competes with Cursor, Continue, and Claude Desktop.

Strengths
  • •True BYOK + multi-provider model selection (GPT, Claude, Gemini in one app) removes vendor lock-in and subscription friction vs. Cursor/Continue
  • •'Review-before-run' for agent actions (web, terminal, files) is thoughtful UX choice addressing genuine trust/safety concern in agentic workflows
  • •Desktop-native, no server, keys/chats/files stay local—clear architectural commitment to privacy and offline-first design
Weaknesses
  • •v0.1.1 with limited feature breadth; agent capabilities (web search, terminal) are table stakes, not differentiation vs. established tools
  • •No obvious moat: if Cursor adds BYOK or Continue adds better UX, this loses appeal unless community adoption creates lock-in
Target Audience

Developers, power users wanting local-first AI without SaaS vendor lock-in

Similar To

Cursor · Continue · Claude Desktop

Post Description

Hi HN — I built Qurt, an open-source desktop “AI coworker” for Windows + macOS.

The goal: provider freedom + local-first UX. You bring your own API keys (no subscription / no lock-in), and your chats/keys/files stay on your machine (nothing stored on our servers).

What it does: - BYOK + multi-provider model switching (keep control of keys/data) - Desktop-native chat with file/image attachments - Agent mode: web browsing/search, terminal commands, browser automation, and file edits — with “review before run”

Downloads (GitHub Releases): https://github.com/qurtai/qurt/releases/tag/v0.1.1

Repo: https://github.com/qurtai/qurt

Landing page: https://qurt.ai/

I’d love feedback on: 1) the “review-before-run” UX (too noisy? not strict enough?) 2) what provider/model integrations you’d want next 3) what would make you trust/install this faster (docs, sandboxing details, etc.)

Similar Projects