agent
-
Perplexity Health Is the Third AI Health Product in 90 Days — and the Most Ambitious One Yet
ChatGPT Health launched in January. Copilot Health followed on March 12. Now, just one week later, Perplexity has entered the ring with Perplexity Health — a product that doesn’t just answer your health questions, but pulls in your medical records, wearable data, and lab results into a single AI-powered dashboard. Three major AI health products… Continue reading
-
Mamba-3 Scores 4% Higher Than Transformers at 7x the Speed — and It’s Fully Open Source
For nearly a decade, Transformers have been the unchallenged default architecture for language models. Challengers have come and gone — RNNs, LSTMs, various state space experiments — but none managed to beat the Transformer on both quality and speed at the same time. They’d win on efficiency but lose on accuracy, or match performance but… Continue reading
-
Project N.O.M.A.D Went from Zero to 5,000 GitHub Stars by Combining Survivalism with Local AI
What would you do if the internet disappeared tomorrow? Not for an hour, not for a day — permanently. Could you still access medical references, maps, educational content, or even a basic encyclopedia? Most of us would be stuck. That uncomfortable reality is exactly why Project N.O.M.A.D — short for Node for Offline Media, Archives,… Continue reading
-
OpenUI (by Thesys) Wants to Replace JSON as the Language Between AI and Your Interface
AI chatbots are everywhere, but most of them still talk in walls of text. You ask for a sales dashboard, you get a paragraph. You request a comparison table, you get bullet points. The models are smart enough to reason about complex data — they just have no good way to show it. OpenUI, the… Continue reading
-
OpenCode Crossed 120K GitHub Stars — and Even Anthropic’s Legal Threats Couldn’t Slow It Down
Eight months. That’s how long it took OpenCode to go from a quiet launch by a serverless framework team to becoming the most-starred open-source AI coding agent on GitHub. With over 120,000 stars, 800+ contributors, 10,000+ commits, and more than 5 million monthly active developers, the numbers alone tell a story. But the real story… Continue reading
-
27 Agents, 109 Skills, 88K GitHub Stars — Is Everything Claude Code Genius or Over-Engineering?
A single GitHub repository now ships 27 specialized agents, 109 skills, 57 slash commands, and 1,282 tests with 98% coverage. It started as one developer’s personal config pack. Ten months later, Everything Claude Code sits at 88.6K stars on GitHub Trending, making it the largest Claude Code configuration framework in existence — and the developer… Continue reading
-
Google AI Studio 2.0 Ships Full-Stack Vibe Coding With Firebase — And It’s Free
Google just made its biggest play in the AI-assisted development space. On March 18, 2026, the company upgraded Google AI Studio into a full-stack vibe coding platform, combining the Antigravity coding agent with native Firebase backend services. The pitch: describe what you want in plain English, and the AI builds, tests, and deploys a complete… Continue reading
-
Claude Channels Scores 375 Points on Hacker News — Anthropic’s Play to Replace OpenClaw
On March 20, Anthropic shipped something that changes how developers interact with Claude Code. Claude Channels is a research preview feature that pushes real-time events — CI builds failing, monitoring alerts firing, Telegram messages arriving — directly into a running Claude Code session. Instead of waiting for you to type a command, Claude now listens,… Continue reading
-
TradingAgents: 33K Stars for an Open-Source Framework That Simulates an Entire Trading Firm with LLM Agents
Wall Street runs on teams. A fundamentals analyst digs through earnings reports. A sentiment specialist monitors social media chatter. A technical analyst watches RSI and MACD. A trader synthesizes it all into a position. A risk manager decides whether to let it through. TradingAgents, built by Tauric Research, takes that exact structure and rebuilds it… Continue reading
-
Kitten TTS: 15 Million Parameters, 25MB on Disk, and Zero GPU Required for Natural Speech
Most text-to-speech models worth using weigh hundreds of megabytes and expect a GPU. Kitten TTS, from the KittenML team, takes a different bet — what if you could get genuinely expressive voice synthesis from a model small enough to fit on a smartwatch? On March 19, KittenML dropped three new models on Hacker News and… Continue reading
Top AI Product 