Show HN: Furnish – AI-powered home design with editable 2D plans and 3D views
I built Furnish for the Kane CLI Hackathon. It's an AI-powered home design studio where you can generate editable floor plans, furnish rooms, make changes using AI, and explore your design in 3D. Built via GMI Cloud using an AI coding agent. I also used Kane CLI to verify the application. The first run identified 9 issues, which I fixed before running the same audit again. The demo video was created using Kane CLI, with voiceover generated using Inworld AI. GitHub: https://github.com/Joystonm/fu
Read original sourceSource record
Recorded metrics
points · 2 votes
2026-11-16 13:19:58.061Z
cumulative since publication
Research analysis
Project record
Repository: Joystonm/furnish. Source account: I built Furnish for the Kane CLI Hackathon. It's an AI-powered home design studio where you can generate editable floor plans, furnish rooms, make changes using AI, and explore your design in 3D. Built via GMI Cloud using an AI coding agent. I also used Kane CLI to verify the application. The first run identified 9 issues, which I fixed before running the same audit again. The demo video was created using Kane CLI, with voiceover generated using Inworld AI. GitHub: https://github.com/Joystonm/fu
Observed adoption & comparisons
Source votes: 2 votes (Nov 16, 2026 UTC; cumulative since publication) Recent records to compare: “NVIDIA SkillEvaluator Framework for Agent Evaluation” (Hackobar, Nov 16, 2026); “ChromeDevTools/chrome-devtools-mcp” (Trendshift, Nov 16, 2026). Shared themes are navigation hints; they have not been verified as the same need or independent corroboration.
Adoption decision
Evaluate it against the tool or manual workflow it would replace. The stored record supports discovery; it does not yet establish reliability, lower operating cost or commercial adoption.
Unverified requirements
Not verified: license permissions, required hardware, installation steps, maintenance status and a representative task with its failure cases.
Next test
Choose one real task and a current alternative. Record the commit, environment, input, output, elapsed time and failure behavior; retain the result before recommending adoption.