-
Glaze by Raycast turns a chat into a real Mac app — and hit 1 on Product Hunt with 494 upvotes
Raycast, the team behind the keyboard launcher power users swear by, just shipped Glaze. You describe the app you want in plain language, and the AI builds a real desktop app — icon in your dock, launches instantly, no browser tab pretending to be software. What it actually is Not a code generator that hands… Continue reading
-
Caveman — make your AI coding agent talk like a caveman (65% fewer output tokens)
Your coding agent burns tokens saying “I’d be happy to help!” before every answer. Caveman kills that. It’s a skill/plugin — not an app, not an API — that you drop into Claude Code and 30+ other agents, and it rewrites how the model talks: short fragments, no filler, no hedging. Same answer, 65% fewer… Continue reading
-
Alibaba bans Claude Code for all employees — the ‘backdoor’ fight with Anthropic escalates
Reuters reported on July 3 that Alibaba will ban Claude Code — Anthropic’s agentic coding tool that lives in your terminal — from all work environments starting July 10, citing “embedded backdoor risks.” This is the sharpest escalation yet in the Anthropic–Alibaba war. What the “backdoor” actually was Since v2.1.91 (April 2), Claude Code quietly… Continue reading
-
Apple ships an official Safari MCP Server in Safari Technology Preview 247
Apple is now the second browser giant with a native MCP server, after Google’s chrome-devtools-mcp. Safari Technology Preview 247 builds one right into the browser, and the pitch is simple: your coding agent can finally see how its code actually renders in a real browser. What agents get It’s a standard local MCP server —… Continue reading
-
openai/codex-plugin-cc hits 22,700 stars: OpenAI built an official plugin for rival Claude Code
OpenAI just shipped a plugin for its competitor’s product. openai/codex-plugin-cc is an official Claude Code plugin that lets you call Codex — OpenAI’s coding agent — inside Anthropic’s terminal tool. 22,700+ GitHub stars, +352 today, still climbing on Trending. What it actually does Claude writes the code, Codex checks it. /codex:review runs a standard review,… Continue reading
-
Devin Security Swarm (Cognition) finds 36 of 50 real GHSA vulnerabilities — 3 that every other tool missed
Devin isn’t just writing code anymore. On July 1, Cognition launched Devin Security Swarm, an AI agent product that hunts exploits: a swarm of parallel Devin agents sweeps your entire codebase (Cognition calls it Agentic MapReduce), reproduces every finding in an isolated sandbox to prove it’s actually exploitable, then ships a remediation PR. No pattern… Continue reading
-
GPT-5.6 Sol on Cerebras — 750 tokens/s: OpenAI’s frontier model gets 15x faster in July
OpenAI will serve its flagship GPT-5.6 Sol on Cerebras infrastructure starting July, at up to 750 tokens per second — roughly 15x the ~50 tokens/s baseline of today’s API tiers. No new model, no new benchmark. Just speed. And that’s the point. Why 750 tokens/s changes the game for agents Frontier models have always forced… Continue reading
-
Anthropic × California ‘Poppy’ Partnership: 300,000 State Workers Get Claude at Half Price
California just became Anthropic’s biggest government customer. Governor Newsom signed a first-of-its-kind deal giving every state agency — plus cities and counties — Claude at a 50% discount, with free workforce training and Anthropic engineers embedded to redesign workflows. It’s the largest state-level AI deployment in US history. What Poppy actually is Poppy (named after… Continue reading
-
Claude in Microsoft Foundry (Azure) hits GA — the first frontier model family on all three clouds
June 29: Claude went generally available in Microsoft Foundry on Azure. With AWS and Google Cloud already covered, Claude just became the first frontier model family you can buy on all three major clouds. Microsoft — OpenAI’s biggest backer — is now selling Anthropic’s models on its own platform. Read that twice. What enterprises actually… Continue reading
-
Squidbleed：Claude Mythos 挖出潜伏 29 年的 Squid 漏洞
Security firm Calif.io pointed Claude Mythos Preview, running multi-agent analysis, at Squid proxy’s FTP parsing code. The model flagged a heap over-read almost immediately. The bug dates to a January 1997 commit — older than Squid’s own GitHub history. Human code review missed it for 29 years. It’s now CVE-2026-47729, aka Squidbleed. One line of… Continue reading
Top AI Product
Every day, hundreds of new AI tools launch across Product Hunt, Hacker News, and GitHub. We dig through the noise so you don't have to — surfacing only the ones worth your attention with honest, no-fluff reviews. Explore our latest picks, deep dives, and curated collections to find your next favorite AI tool.
Top AI Product 