This is Ditto. It clones any website in less than 5 minutes. Clean code w/ components, tokens, interactions, hover effects. Free & open source. REST API and MCP server included.

Browser agents, hold the Chromium. Runloop x @usekernel splits browser automation cleanly: agent in a Runloop devbox, browser on Kernel, driven server-side with Playwright. Tutorial + Python/TypeScript cookbook in reply. #AIAgents #DevTools

Today, I’m excited to formally announce @mirendil with my amazing co-founders Harsh Mehta, Shayan Salehian, and Tara Rezaei! We’re fortunate to work with @a16z and @kleinerperkins, who led our seed round of $200M, followed by a major investment from NVIDIA, among others. Mirendil exists to accelerate science and technology, and through them, to help solve humanity's most pressing problems. Self-accelerating AI R&D is the most direct path to delivering on AI's broader promise, which is why we believe the most important application of AI is AI itself. Get this loop right, and it compounds. It fundamentally changes the rate of progress itself across all domains. We believe this capability should be democratized. It should be used to power all scientific efforts trying to innovate at the frontier. There are far more important problems—and broader ones—than any single lab can take on, so more groups should be able to pursue them. This pulls concentration of power away from a few labs: businesses and science labs can own their AI and infrastructure, keep their margins, and control their own destiny instead of ceding it all to a single AI lab. We’re a small team with a singular focus. Our founding team consists of 20 researchers and engineers from frontier institutions including Anthropic, xAI, Google DeepMind, and OpenAI, united by a passion for science and a drive to build the technologies that move it faster. If you want to build the system that builds systems, join us! @HarshMeh1a, @shayan_, @tararezaeikh

Introducing Cohere's first open-source coding model: North Mini Code Small & efficient, designed for agentic performance and built for community input.

Sandboxes are becoming the OS for agents. This is because agents will be more persistent and stateful. I go deep in my Substack: isolation primitives, performance, portability, architecture, build vs buy, market dynamics. Give it a read: crystalxtang.substack.com/p/…

We ran a chess tournament for bugs. The question we wanted to answer: are bugs from Detail "important"? How do they compare to what code review bots catch? One of the most important ways we benchmark ourselves is that we want the bugs we generate to be significantly more important than the typical comment from a code review bot. We took a week of findings from CR bots running on OpenClaw and vLLM, plus findings from Detail on the same week of changes. We put them through an LLM-as-judge tournament. We fed the head-to-head results into a Bradley-Terry model to compute ELO ratings for bugs. Out comes a global ranking from most to least important. Awesome exploration from @sachiniyergreen below, with methodology, charts, and a PostHog secret exfiltration vuln that four code review bots missed.

Vibedeploy with Stripe Projects, now available to everyone: projects.dev/.

Shipping AI agents you can trust in production just got dramatically easier. Agents making autonomous decisions across real workflows need constant validation but running benchmarks used to take days, required constant oversight, and gave teams no structured way to compare results. With Runloop's Benchmark Job Orchestration + Weights & Biases integration, thousands of parallel environments run in hours, not days, without tending, and give full trace-level visibility into every action and agent turn Find out more in our docs 👇