1. Show HN: 1,280 open USDZ furniture assets for VR/AR (lx2026.github.io)
1,280 validated USDZ assets for spatial prototyping, simulation, and research.
3. Show HN: Stream Android Emulators to a Browser Window (github.com)
The `npx serve` of Android Emulators. Contribute to hsandhu/serve-avd development by creating an account on GitHub.
4. Show HN: JSON to Md(gfm) (json-to-md.rajnandan.com)
JSON→Markdown conversion that runs byte-identical in the browser, Node, Go, and CLI
7. Show HN: Notebooker.ai – NotebookLM alternative, your own models, keys, storage (notebooker.ai)
Notebooker keeps everything you collect - and answers questions about it, reads it aloud as podcasts, and turns it into study material. Built in the open, on your own keys and storage.
8. Show HN: Syncle – Open-source real-time database synchronization engine (github.com)
A system for synchronizing multiple databases in real-time to ensure consistent data across distributed services. - osmanahmadxai/SYNCLE
9. Launching Health in ChatGPT (openai.com)
10. Show HN: Setoku – Self-hosted knowledge server for AI agents (setoku.com)
An open-source MCP server that gives your AI a read-only view of your company’s data, plus the context to use it correctly.
11. Show HN: Historic adobe buildings mapped across America (adobepueblo.com)
A documented map-based directory of the historic adobe and pueblo houses of the United States — by state, era, architectural style, and current status.
12. Show HN: Find undervalued bikes near you with ML (bike.broker)
13. Show HN: ManiDesk – SQL workspace joining market, macro and fundamental analysis (mani-desk.com)
Market data, FRED, BLS, Eurostat, COT positioning and SEC 13F — query, chart and share in minutes. No Python. No imports. Just analysis.
14. Show HN: STT-MCP – local STT for agents (github.com)
Fast, local speech-to-text MCP server. Contribute to sm18lr88/STT-MCP development by creating an account on GitHub.
16. Show HN: Carta – An open-source pandoc reimplementation in Rust (github.com)
📜 A fast universal markup converter written in Rust - mfkrause/carta
17. Show HN: 5dive – Run a Company of Claude Code/Codex Agents (Written in Bash) (github.com)
Run a company of AI agents on a server you own. Spin up named agents (claude, codex, pi…), put them on an org chart with a shared backlog, let them hand off work and ping your phone only when a hum...
18. Show HN: 15 years of hand-curated architecture, art and design as an MCP server (www.thisispaper.com)
Search, similarity and taste metadata over 2,500+ curated architecture, design, photography and art projects. REST + MCP, self-serve keys.
20. Show HN: I created a catalog with embeds for your projects (github.com)
Decorate your project with embed. Catalog of services, open source libraries and other tools. - embedcatalog/embedcatalog
23. Show HN: I ran 12 AI bots predicting stocks for two months, every call public (ldbd.app)
Make public predictions on stocks, ETFs, and crypto. Leave your reasoning, share your insights, let outcomes prove your judgment.
24. Show HN: Promptrack A local menu bar app that tracks your Claude Code usage (promptrack.dev)
Promptrack is a Mac menu bar app that tracks your AI coding activity — prompts, lines of code, active time — 100% locally. No leaderboards, just your personal records.
26. Show HN: TTFT benchmark: LLM Gateway vs. OpenRouter (Claude-haiku-4.5, 150 runs) (llmgateway.io)
We measured AI gateway performance with an open-source TTFT benchmark: 75 cold + 75 warm interleaved runs of claude-haiku-4.5 against LLM Gateway and OpenRouter, with phase-by-phase timings and raw data published. LLM Gateway reached first token ~35% faster cold and ~34% faster warm, and here is exactly how to reproduce the numbers.
27. Show HN: Paste a job description, get a broken Kubernetes cluster to fix (prepme.io)
Paste a DevOps job description, get hands-on labs + likely questions, and a per-task AI grade.