HN ilreb 26d ago

Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

Lightweight 0.2B image inpainting model achieving 10B-level performance through systematic diffusion backbone optimization.

HN debankad 26d ago

Show HN: AgentArk – open-source self-hosted AI agent OS

AgentArk is open-source self-hosted AI agent runtime. Build agents from prompts/tools, deploy as apps/automations, monitor actions, manage context. Full lifecycle management.

HN BetaDeltaAlpha 26d ago

Show HN: Western Highway Alerts

Rust web app providing email alerts for California highway closures.

HN HoraDomu 26d ago

Atheon -Atheon is a community-driven pattern matching engine

Pattern matching CLI engine for detecting credentials, identifiers, and compliance violations.

HN calvinmorrison 26d ago

XLibre XServer 25.2.0 Released

X Server 25.2.0 release with refactored EGL architecture and improved Nvidia support.

HN sg0nzalez83 26d ago

Show HN: Muninn - 8 Security scanners in one GitHub Action

Open-source GitHub Action combining eight security scanners with unified output format.

HN gregsadetsky 26d ago

Help I Accidentally a Wigglegram

Photography blog post about accidentally creating wigglegrams (looped stereo images) from camera roll. No AI/tech relevance.

HN turtleyacht 26d ago

Software Optimization Resources

Reference manuals for x86/x86-64 code optimization and microprocessor architecture.

HN matt_d 26d ago

LLMs Are Complicated Now

Analysis of increasing architectural complexity in modern LLMs compared to earlier Transformer-based designs.

HN azhenley 26d ago

I am dreading our LLM-written incident report future

Critical perspective on LLM-generated incident reports, discussing risks and limitations while acknowledging toil reduction benefits.

HN joesdomingo 26d ago

Build a full knowledge graph locally with any video

GoodQ4All: offline video processing system with transcription, diarization, semantic search using local Whisper, Qdrant, and SQLite.

HN erinmeryl 26d ago

Out of Stealth (Kinda)

LodeDB: embedded vector database for local RAG with GPU acceleration, achieving 24k-50k queries/sec with sub-millisecond persistence.

HN pipeabello 26d ago

Show HN: Agentcard – virtual cards for AI agents, now with DoorDash checkout

Agentcard: virtual card infrastructure enabling AI agents to interact with real-world services like DoorDash with payment processing.

HN grandrew 26d ago

Show HN: P34 – tabular profit prediction without the optimism bias

P34 framework addressing optimism bias in ML models trained on historical business decisions, preventing over-optimistic production deployments.

HN DesoPK 26d ago

Kernhelm: A Linux authority wall for untrusted agents

Linux security module for controlling untrusted agent access. Incomplete documentation snippet provided.

HN gurjeet 26d ago

Cirrus: ATProto Personal Data Server That Runs on Cloudflare Workers

Single-user AT Protocol Personal Data Server implementation running on Cloudflare Workers with edge computing, relevant to Bluesky infrastructure.

HN webstorms 26d ago

Automating model design for edge AI

DeepGate's automated model search produces edge AI models 45× faster and using 11× less RAM than reference implementations.

HN webstorms 26d ago

Our edge AI compiler outperforms Google and vendor toolchains

DeepGate compiler achieves 3× RAM reduction and 2× speedup vs Google TFLM on microcontrollers.

HN sonabinu 26d ago

GPU Puzzles (2021)

Interactive notebook teaching GPU programming fundamentals using NUMBA for Python developers to build GPU kernels without prior GPU experience.

HN azhenley 26d ago

Knowledge workers don't need frontier models

Analysis arguing smaller LLMs with intelligent routing outperform frontier models for knowledge workers, optimizing cost and performance tradeoffs.

HN 3stacks 26d ago

Show HN: Evaluating Local LLMs as language translators for my app

Evaluation of local open-source LLMs for language translation tasks, comparing against Google Translate with methodology discussion.

HN FayzanMalik 26d ago

Show HN: CWC scans your Claude Code history and auto-builds agent workflows

Visual desktop app for composing multi-agent Claude Code workflows with drag-and-drop canvas interface.

HN truth_seeker 26d ago

Show HN: PostgreSQL MCP Server with 135 tools for various purpose

PostgreSQL MCP server with 135 tools for Claude Desktop and MCP-compatible AI systems. Lock-free connection pooling, sub-10ms latency.

HN Vicbona 26d ago

Purple Wolf – A fast, verifiable WAF for Traefik

Web Application Firewall plugin for Traefik running as WASM with signed releases and Kubernetes support.

HN andrewacove 26d ago

Show HN: Surface skill for HTML pages a coding agent watches and reacts to

Web interface framework for AI agents to interact with rich UIs beyond text. Enables agents to manipulate tables, images, and complex layouts.

HN vforno 26d ago

Show HN: NanoEuler – GPT-2 scale model in pure C/CUDA from scratch

GPT-2-scale language model built from scratch in pure C/CUDA without ML frameworks. Includes hand-written tokenizer, training pipeline, and CUDA engine.

HN ibobev 27d ago

Connecting Peripherals to Atari 8-bit Computers

Guide to connecting peripherals to vintage Atari 8-bit computers.

HN ledoge 27d ago

Reverse engineering the Qualcomm NPU compiler

Reverse engineering Qualcomm NPU compiler to enable faster edge deployment of ML models on NPU hardware.

HN andrewstetsenko 27d ago

Spending money on GPU's was my best investment

Minimal post about GPU investment.

HN uptime-com-mcp 27d ago

Uptime.com's New MCP

Model Context Protocol server for Uptime.com monitoring, enabling AI assistants to manage infrastructure checks and alerts.

HN gpi 27d ago

I Shipped a Facebook Feature So Fast Sheryl Sandberg Called an Emergency Meeting

Personal anecdote about shipping a Facebook feature quickly.

HN v5n_r8n 27d ago

Show HN: QuickRetro – Open-source sprint retrospective app

Open-source sprint retrospective meeting app built with Go, Vue, Redis, and WebSockets.

HN tosh 27d ago

querychat

Natural language interface for querying tabular data using LLMs and SQL, available for R and Python.

HN rozumbrada 27d ago

Self-adapting and mutating LLM based viruses/worms

Discussion of hypothetical self-mutating LLM-based malware that adapts using local models and exploits non-determinism for propagation.

HN ingve 27d ago

How to get product feedback from agents

Sanity MCP server handles 3M+ agent tool calls; article describes gathering feedback from AI agents using a Model Context Protocol integration.

HN adamhh 27d ago

Teams using AI for outbound email are finding it harder, Folderly research finds

Folderly survey shows 70% of B2B sales teams use AI for outbound email but face 79% delivery failure rates as recipients detect AI content.

HN Byron230686 27d ago

Beast – governed output gateway for AI coding agents

Beast is a governance layer for AI coding agents that enforces output contracts, repairs patches, and optimizes tool calls before filesystem writes.

HN pseudolus 27d ago

Pentagon used Elon Musk's Grok AI to fire 2k missiles at Iran, official says

Unverified clickbait claim about Pentagon using Grok AI for military operations.

HN pseudolus 27d ago

2k retired Google Pixel phones get a second life as a private cloud

UC San Diego and Google deploy 2,000 retired Pixel phones as a distributed compute cluster for private cloud infrastructure.

HN giuliomagnifico 27d ago

Estonia to give digital identities to AI agents

Estonia issuing digital identities to AI agents for legal/regulatory recognition.

HN breve 27d ago

Tesla HW3 claim grows to 7,000 owners, gets backing for collective action

Legal action by Tesla HW3 owners over FSD promises. Not AI/tech development.

HN adrianvi 27d ago

GitHub Copilot App

GitHub Copilot standalone app announcement. Product update, limited details.

HN dylandeheer 27d ago

Conversations Should Stay Yours

Local meeting recording and transcription tool with privacy-first design. Not AI research focused.

HN DDerTyp 27d ago

Node-Fetch on latest Node Update broken

Bug report on Node-Fetch breaking with Node v24.17.0 in HTTP keep-alive scenarios.

HN jaquelinejaque 27d ago

Show HN: I built an 11-LLM consensus engine to detect AI hallucination

11-LLM consensus engine to detect hallucinations in AI outputs. Developer tool for improving LLM reliability.

HN alecco 27d ago

Barret Zoph is out at OpenAI again after just five months

Personnel news about Barret Zoph leaving OpenAI after five months. Corporate gossip with minimal technical content.

HN CapricornNoble 27d ago

Lisuan Tech LX Pro 24GB GPU

Incomplete product page for GPU hardware. Insufficient content.

HN johnbarron 27d ago

Conservatives plan nationwide protest against AI data centers

Political opposition to AI data center construction. Not development-focused.

HN turkeywelder 27d ago

Show HN: Tracking iCal feed latency across O365/Google/Apple

Analytics tracking iCal feed latency across email providers. Not AI/ML focused.

HN gs202 27d ago

PageToMD – A CLI tool to turn web pages into clean Markdown for AI agents

CLI tool converting webpages to clean Markdown for AI agents. Open source utility with piping support and crawling capability.