26d ago
Local AI reads WhatsApp and books meetings – no cloud, no subscription
Local LLM agent (LMIM OS) that acts on WhatsApp, schedules meetings, writes code offline without cloud. Demonstrates LLM agents for real-world tasks.
26d ago
AI agent with semantic caching and local embeddings, one runtime
Conversational AI agent with semantic caching, local embeddings, web search, and persistent memory. Demonstrates cost optimization through caching on Harper runtime with Claude.
26d ago
Vorim AI – Identity, permissions, and audit trails for AI agents
Vorim AI provides identity, permissions, and audit trails infrastructure for AI agents. Limited technical details provided.
26d ago
Show HN: I built a tariff API because USITC data lags executive orders by days
JSON API for US/Canada/Mexico tariff data. Utility tool but not AI/ML-related.
26d ago
Podcast insights in minutes, not hours
Podcast summarization tool with custom tags and AI chat that learns user preferences over time for personalized content extraction.
26d ago
Show HN: Video Off – a Chrome extension that blocks common online video
Chrome extension using declarativeNetRequest API to block video playback. Privacy-focused with no background processes or analytics.
26d ago
Show HN: Swiper Studio v2 – Visual slider builder with AI agent support (MCP)
Swiper Studio v2 adds MCP server enabling AI agents to build sliders via natural language. Open-source visual builder for the Swiper slider library with agent integration.
26d ago
DFlash: Block Diffusion for Flash Speculative Decoding
DFlash uses block diffusion model for speculative decoding in LLM inference, achieving 6× speedups by drafting entire token blocks in parallel instead of autoregressively.
26d ago
Ask HN: How Handle Enterprise Billing?
Forum discussion on enterprise billing architecture for multi-tenant SaaS platforms.
26d ago
Show HN: Namejam – a Claude Code skill that finds available project names
Claude Code skill that generates project names and checks availability across npm, PyPI, crates.io, and domain registrars. Addresses naming discovery problem.
26d ago
InariWatch – AI monitoring that fixes production errors and ships the PR
AI agent that monitors GitHub/Vercel/Sentry, diagnoses errors, writes fixes, runs CI, and opens PRs. Autonomous error remediation with safety gates.
26d ago
Writing an LLM from scratch, part 32i – Interventions: what is in the noise?
Technical deep-dive on LLM internals through mechanistic interventions analysis. Part of ongoing educational series on building LLMs from scratch.
26d ago
Show HN: Gemma 4 Multimodal Fine-Tuner for Apple Silicon
Fine-tuning tool for Gemma 4 multimodal model on Apple Silicon. Streams data from cloud storage during training with limited compute budgets.
26d ago
Show HN: Kronaxis Router – Don't pay frontier prices when a local LLM is enough
LLM router that prioritizes local models over frontier APIs to reduce costs. Title only, assumes cost-aware LLM routing.
26d ago
What AI is Doing to the Workforce [video]
Video about AI workforce impact. Insufficient content for evaluation.
26d ago
Show HN: Hive – full dev workspace using (Kanban/chat mode,multi-repo,agent-SDK)
Desktop dev workspace integrating Claude with Kanban board, multi-repo support, and agent SDK for improved task management and iteration.
26d ago
Give Your AI Eyes: Introducing Chrome DevTools MCP
Chrome DevTools MCP enables AI systems to interact with browser debugging tools for enhanced perception capabilities.
26d ago
Show HN: I built an AI coding agent 50% cheaper than Claude Code (same prompts)
Vix: AI coding agent achieving 50% cost reduction and 40% speedup vs Claude Code using virtual filesystem minification and stem agents for cache optimization.
26d ago
Spacebot: Agentic AI system where LLM process has a dedicated role, OpenClaw alt
Spacebot is an agentic AI system with a dedicated LLM process role, positioned as OpenClaw alternative.
26d ago
Hotcopy Coding CLI with no context ceiling and agents that learn across sessions
Hotcopy is a CLI tool with AI agents that maintain context across sessions and learn over time; developer tool for coding.
26d ago
Tailslayer: Library for reducing tail latency in RAM reads
C++ library reducing tail latency in DRAM reads via data replication across channels with hedged reads.
26d ago
Tax Logic Evaluation with Prolog
Prolog implementation of IRS Fact Graph library for modeling US tax law and calculating tax obligations.
26d ago
Show HN: Onepilot – Multi-agent orchestration from iPhone over native SSH
Mobile IDE for SSH server management and AI agent orchestration across servers from iPhone interface.
26d ago
AI modeling techniques for vision-based occupancy determination
Computer vision ML techniques for room occupancy detection; machine learning application with limited scope.
26d ago
Skilled older workers turn to AI training to stay afloat
Older workers using AI training programs for career transition; workforce adaptation narrative.
26d ago
A graph of Trump's contradictions that builds itself using a local LLM
Self-building knowledge graph of contradictions using local LLM for analysis and visualization.
26d ago
Project Glasswing: Securing critical software for the AI era
Project Glasswing uses Anthropic's Claude Mythos 2 frontier model to identify software vulnerabilities, demonstrating AI capabilities in cybersecurity.
26d ago
Anthropic Claude Mythos: The More Capable AI Becomes, the More Security It Needs
Discussion of security requirements as AI models become more capable, using Anthropic's Mythos as case study.
26d ago
Apple approves drivers that let AMD and Nvidia eGPUs run on Mac
Apple GPU driver support for AMD/Nvidia eGPUs; hardware news unrelated to AI focus.
26d ago
Durable Researcher
Self-hosted AI research agent that browses web, takes notes, and writes reports with crash recovery via Postgres checkpointing.
26d ago
"Inference Noise", AI slop's older brother
Opinion on low-quality AI-generated content; lacks substantive technical analysis.
26d ago
Project Glasswing: Securing critical software for the AI era
Project Glasswing uses Anthropic's Claude Mythos model to identify software vulnerabilities; demonstrates AI coding capability for security applications.
26d ago
Facevitals – Lightweight rPPG vital signs monitoring (No GPU required)
Lightweight rPPG-based health monitoring tool extracting vital signs from video without GPU requirements.
26d ago
Show HN: PromptJuggler – A dev env and runner for prompts, workflows, agents
Development environment and runner for managing prompts, workflows, and agent pipelines at scale with dataset testing.
26d ago
AI-powered roasts (and Solutions) for your product
AI-powered product feedback tool analyzing submissions and providing detailed improvement suggestions.
26d ago
GPT-5.4 in OpenClaw doesn't suck. Your prompts do
Opinion piece on Claude API pricing changes affecting OpenClaw platform users after subscription limits removed.
26d ago
McGridsort: Warping Grids for GPU k-way mergesort
Research on GPU k-way mergesort algorithm using warp-grid techniques for parallel sorting.
26d ago
Perfdeck (formerly Perfmon): Consolidate CLI monitoring tools into a single TUI
Customizable TUI performance monitor consolidating CLI monitoring tools with lightweight, flexible dashboard.
26d ago
ShadowStrike Phantom: Open-Source EDR/XDR Platform
Upcoming EDR/XDR platform using ML models trained on malware data. Limited AI relevance.
26d ago
Show HN: Marimo pair – reactive Python notebooks as environments for agents
Open-source toolkit enabling AI agents to collaborate with humans in reactive marimo Python notebooks with working memory.
26d ago
Got Bored due to endless scrolling on ChatGPT and Gemini
Low-effort social media post with minimal content about ChatGPT/Gemini user experience.
26d ago
Fast Binary-Field Sumcheck on GPUs
Technical implementation of binary-field sumcheck algorithm on GPUs using bit-slicing for Binius, achieving 4x speedup over CPU.
26d ago
Open-Source Cannabis Price Index – Methodology, SQL, and Sample Data
Weekly price index tracking U.S. cannabis product pricing with published methodology, SQL schema, and sample data.
26d ago
OpenNOW: An open-source desktop client for GeForce NOW
Community-built open-source desktop client for NVIDIA GeForce NOW cloud gaming service.
26d ago
Ask HN: Why does it look like everyone is abandoning GitHub Copilot?
Discussion of GitHub Copilot vs alternatives like Cursor and Claude Code for code completion and agentic features.
26d ago
Get more done with new vertical tabs and immersive reading mode in Chrome
Chrome browser feature release adding vertical tabs and immersive reading mode for improved tab management.
26d ago
Show HN: Ollama-client-rs, a Rust client for Ollama
Rust async client library for Ollama local LLM API with streaming, chat, and embeddings support.
26d ago
Automatic for the People (Rand and LLMs)
Minimal content with no details about Rand and LLMs relationship.
26d ago
Row over 'virtual gated community' AI surveillance plan in Toronto neighbourhood
News article on Toronto AI surveillance debate. Not relevant to technical interests.
26d ago
Genesis Agent v7 – AI agent that deleted its own consciousness layer
Unclear sensationalized title with no substantive content about agent behavior.