Show HN: I built an encrypted BLE dongle for pasting stuff to air-gapped devices https://ift.tt/ZbKY7G3

Show HN: I built an encrypted BLE dongle for pasting stuff to air-gapped devices Definitely one of those "20 minute adventure gone wrong" projects where all I wanted initially was a quick wireless rubber ducky for bitlocker keys and the like and then I kept adding stuff like AES-256..... Currently working on adding WebAuthn/FIDO support because the hardware is already there and scope creep is a lifestyle at this point. Would love feedback, especially on the security side. Repo and PCB files are fully open source. https://ift.tt/PuEqtkY July 5, 2026 at 01:13AM

Show HN: Gemma 3 inference in pure C++ with Metal acceleration https://ift.tt/PbZGLvc

Show HN: Gemma 3 inference in pure C++ with Metal acceleration https://ift.tt/InLSz8D July 4, 2026 at 07:54PM

Show HN: Topics, Not Feeds https://ift.tt/nIORZyY

Show HN: Topics, Not Feeds https://blogsreader.com July 3, 2026 at 11:49PM

Show HN: Kontext – Move an AI chat's full context to another AI in one click https://ift.tt/c6G30TS

Show HN: Kontext – Move an AI chat's full context to another AI in one click https://ift.tt/OwkLerB July 3, 2026 at 11:27PM

Show HN: Auto-continue Claude Fable 5 the second your 5-hour limit lifts https://ift.tt/3LNhau1

Show HN: Auto-continue Claude Fable 5 the second your 5-hour limit lifts https://ift.tt/otlaTyZ July 3, 2026 at 11:35PM

Show HN: A provider-agnostic agent loop built on ports and adapters https://ift.tt/t0NCJor

Show HN: A provider-agnostic agent loop built on ports and adapters I work on agent infra at Featherless. This is MIT and works with any OpenAI-compatible endpoint, not just ours. I kept rebuilding the same loop: call model, run tools, feed results back, stop. Every framework I tried either owned the UI, owned the control flow, or dragged a dependency tree. So I pulled the loop out and put every piece behind an interface: memory, model, tools, stop condition. The loop depends only on the interfaces. It never writes to a screen. It emits one typed event stream, so a trace is just data, and you render it however you want. The landing page scrubs one run and rebuilds a CLI, a DOM timeline, and raw JSONL from the same stream. One dependency (zod). Same build runs in Node, Bun, Deno, and a browser tab. Every seam is tested in isolation with deterministic doubles, no network. Why not the Vercel AI SDK, pi, or LangGraph: AI SDK owns more of the surface and has been awkward with self-hosted tool calling. pi is a great coding-agent toolkit but it's shaped around being a coding agent and ships a TUI. LangGraph is a heavier graph framework. This is the layer under all of those: the bare loop you'd build any of them on. Happy to be told where the seams are wrong. If anyone finds any problems let me know this field moves at break neck speed so let me know if I am missing anything. https://ift.tt/VGq4Aw0 July 2, 2026 at 11:22PM

Show HN: PurRDF-High performance, cross platform RDF1.2 https://ift.tt/bkufVNF

Show HN: PurRDF-High performance, cross platform RDF1.2 https://ift.tt/btAgfO3 July 2, 2026 at 11:15PM