agent
-
Dreamer Raised $56M to Build an Agent OS — 5 Weeks After Launch, Meta Hired the Entire Team
Five weeks. That’s how long Dreamer existed as a public product before Meta swooped in and acq-hired the entire founding team. On February 18, 2026, the startup formerly known as /dev/agents launched its open beta — a no-code platform where anyone could build, discover, and remix AI agents using plain English. By March 23, Bloomberg… Continue reading
-
Agent Kernel Gives Any AI Coding Agent Persistent Memory — with Just Three Markdown Files
The AI agent memory problem has become one of the most debated topics in developer tooling. Every major coding assistant — Claude Code, Cursor, Windsurf, OpenAI Codex — resets between sessions. Your agent forgets what it learned yesterday, what conventions your project follows, and what mistakes it already made. Dozens of startups and frameworks are… Continue reading
-
Zoer.ai Turns a Single Sentence Into a Full-Stack App — But Can It Replace Lovable and Bolt.new?
The AI app builder space is getting crowded. Lovable, Bolt.new, Cursor, Replit — the list keeps growing. But most of these tools still leave gaps. You either get a pretty frontend with no backend, or you get code output that needs hours of manual wiring before it can accept a payment or authenticate a user.… Continue reading
-
Terafab: $25 Billion, Zero Chip-Making Experience, and 80% of the Output Goes to Space
Elon Musk stood on the stage of a decommissioned power plant in Austin, Texas on March 21 and announced what he called “the most epic chip building exercise in history by far.” The project is called Terafab — a joint venture between Tesla, SpaceX, and xAI — and the pitch is staggering: a single facility… Continue reading
-
GitHub Spec-Kit Hits 71K Stars by Telling AI Agents What to Build Before They Build It
Vibe coding has a problem. You describe what you want, an AI agent spits out code, and it looks right — until it doesn’t. The loop of prompting, reviewing, re-prompting, and hoping gets old fast, especially on anything beyond a weekend prototype. GitHub’s answer is Spec-Kit, an open-source toolkit that flips the script: write the… Continue reading
-
A Single API String Exposed Cursor’s Secret: Composer 2 Runs on Moonshot AI’s Kimi K2.5
On March 19, a $29.3 billion coding startup launched what it called a breakthrough proprietary model. Within 24 hours, a developer found this string in the API response: kimi-k2p5-rl-0317-s515-fast. That one line of text unraveled the entire narrative. Cursor’s Composer 2 — the model that supposedly beat Claude Opus 4.6 on coding benchmarks at one-tenth… Continue reading
-
WordPress MCP Write Capabilities: AI Agents Can Now Write, Edit, and Publish on 43% of the Web
WordPress powers 43% of all websites on the internet. On March 20, 2026, Automattic flipped a switch that lets AI agents — Claude, ChatGPT, Cursor, and any MCP-compatible client — not just read WordPress.com sites, but write to them. Draft blog posts. Build landing pages. Manage comments. Restructure categories. Fix SEO metadata. All through natural… Continue reading
-
Tencent ClawBot Turns WeChat Into an AI Command Center for 1 Billion Users
China’s AI agent war just found its biggest distribution channel. On March 22, Tencent launched ClawBot — a tool that embeds the OpenClaw AI agent directly into WeChat as a contact. Not a mini-program buried three taps deep. Not a separate app download. A contact. Sitting right there in the chat list of the world’s… Continue reading
-
Design Agent by Lokuma Topped Product Hunt With a Simple Pitch: AI Agents Need Designers Too
AI agents can write code, draft emails, research markets, and deploy apps. But ask one to build a landing page that actually looks good? The output usually screams “AI made this.” Centered text, generic spacing, no visual hierarchy — functional, sure, but not designed. Design Agent by Lokuma launched on Product Hunt on March 21,… Continue reading
-
From 35% to 80% on WebVoyager: Holotron-12B Sets a New Bar for Open-Source Computer-Use Agents
The race to build AI agents that can actually operate a computer — clicking buttons, filling forms, navigating websites — has been dominated by closed-source giants. Anthropic’s Claude Computer Use and OpenAI’s Operator have set the pace, but they come with API costs, usage limits, and zero visibility into the model weights. That changed on… Continue reading
Top AI Product 