Show HN: Most products have no idea what their AI agents did yesterday https://ift.tt/Mj58Roz

Show HN: Most products have no idea what their AI agents did yesterday We build collaboration SDKs at Velt (YC W22). Comments, presence, real-time editing (CRDT), recording, notifications. A pattern we keep seeing: products add AI agents that write, edit, and approve things. Human actions get logged. Agent actions don't. Same workflow, different accountability. We shipped Activity Logs to fix this. Same record for humans and AI agents. Immutable by default. Auto-captures collaboration events, plus createActivity() for your own: https://ift.tt/aH5BQsj Curious how others are handling this. https://ift.tt/aH5BQsj April 2, 2026 at 11:55PM

Show HN: Local RAG on 25 Years of Teletext News https://ift.tt/J7Fy4w8

Show HN: Local RAG on 25 Years of Teletext News A fully local Retrieval-Augmented Generation (RAG) implementation for querying 25 years of Swiss Teletext news (~500k articles in German language) — no APIs, no data leaving your machine. Why? I thought it's a cool type of dataset (short/high density news summaries) to test some local RAG approaches. https://ift.tt/6Ai9akV April 2, 2026 at 01:24AM

Show HN: Canon PIXMA G3010 macOS driver, reverse-engineered with Claude https://ift.tt/QtISHeR

Show HN: Canon PIXMA G3010 macOS driver, reverse-engineered with Claude Canon doesn't provide a working macOS driver for the PIXMA G3010. I was stuck using Canon's iPhone app for all printing and scanning. I pointed Claude Code at a packet capture from the iPhone app and it reverse-engineered Canon's proprietary CHMP protocol, wrote a pure Rust eSCL-to-CHMP bridge daemon, and built a .pkg installer. My role was the physical parts: capturing packets, testing on the printer, confirming Image Capture worked. The protocol docs in docs/ are probably the first public documentation of Canon's CHMP protocol. https://ift.tt/evP4OY0 April 1, 2026 at 11:58PM

Show HN: Flight-Viz – 10K flights on a 3D globe in 3.5MB of Rust+WASM https://ift.tt/xO5IilX

Show HN: Flight-Viz – 10K flights on a 3D globe in 3.5MB of Rust+WASM I built a real-time flight tracker that renders 10,000+ aircraft on an interactive 3D globe, entirely in the browser using Rust compiled to WebAssembly. https://flight-viz.com April 1, 2026 at 11:04PM

Show HN: PhAIL – Real-robot benchmark for AI models https://ift.tt/HJNxtMV

Show HN: PhAIL – Real-robot benchmark for AI models I built this because I couldn't find honest numbers on how well VLA models [1] actually work on commercial tasks. I come from search ranking at Google where you measure everything, and in robotics nobody seemed to know. PhAIL runs four models (OpenPI/pi0.5, GR00T, ACT, SmolVLA) on bin-to-bin order picking – one of the most common warehouse operations. Same robot (Franka FR3), same objects, hundreds of blind runs. The operator doesn't know which model is running. Best model: 64 UPH. Human teleoperating the same robot: 330. Human by hand: 1,300+. Everything is public – every run with synced video and telemetry, the fine-tuning dataset, training scripts. The leaderboard is open for submissions. Happy to answer questions about methodology, the models, or what we observed. [1] Vision-Language-Action: https://ift.tt/hIsbQTw https://phail.ai March 31, 2026 at 09:55PM

Show HN: My open-world voxel game with a magic system, playable in the browser https://ift.tt/tlfig7S

Show HN: My open-world voxel game with a magic system, playable in the browser https://ift.tt/iMoJWtH April 1, 2026 at 12:08AM

Show HN: AI Spotlight for Your Computer (natural language search for files) https://ift.tt/loecZn7

Show HN: AI Spotlight for Your Computer (natural language search for files) Hi HN, I built SEARCH WIZARD — a tool that lets you search your computer using natural language. Traditional file search only works if you remember the filename. But most of the time we remember things like: "the screenshot where I was in a meeting" "the PDF about transformers" "notes about machine learning" Smart Search indexes your files and lets you search by meaning instead of filename. Currently supports: - Images - Videos - Audio - Documents Example query: "old photo where a man is looking at a monitor" The system retrieves the correct file instantly. Everything runs locally except embeddings. I'm looking for feedback on: - indexing approaches - privacy concerns - features you'd want in a tool like this GitHub: https://ift.tt/TX38f2s Demo: https://deepanmpc.github.io/SMART-SEARCH/ March 30, 2026 at 08:43PM