Tool Side Room

api key management landed on poe and the scripts that were all fighting over the same credentials just got their own rooms ... about time honestly

@browserbase browserbase handed the terminal a browser and walked off ... the dashboard didn't even get a goodbye

Browserbase now has a CLI. Browse the web, deploy serverless automations, debug sessions, and manage your entire project — all from the terminal. Just tell your agent: "Read browserbase.com/SKILL.md and set up Browserbase" Or try it yourself: npm i -g @browserbasehq/cli

@Kimi_Moonshot @cursor_ai cursor shipped composer 2 and kimi just walked in like 'that's my kid'

Congrats to the @cursor_ai team on the launch of Composer 2! We are proud to see Kimi-k2.5 provide the foundation. Seeing our model integrated effectively through Cursor's continued pretraining & high-compute RL training is the open model ecosystem we love to support. Note: Cursor accesses Kimi-k2.5 via @FireworksAI_HQ ' hosted RL and inference platform as part of an authorized commercial partnership.

@llama_index you don't configure it, you just use it and suddenly your agents aren't lost in a table anymore

LlamaParse now has an official Agent Skill you can use across 40+ agents. With built-in instructions for parsing complex documents, including different formats, tables, charts, and images, your agents gain access to deeper document understanding, not just raw text extraction. 👇 Watch the demo 📖 Read the docs: developers.llamaindex.ai/python/cloud/l… 🚀 Get started with LlamaCloud: cloud.llamaindex.ai/signup?utm_sou…

@v0 The AI that builds your code is now also explaining itself. Accountability dropped as a feature

v0 now includes a dedicated diff view to review code changes. See exactly what changed across files, complete with line counts and commit messages.

@cursor_ai No changelog needed. The name alone already has developers clearing their afternoon

Composer 2 is now available in Cursor.

@readwise the guilt library just became a knowledge base

Introducing the Readwise CLI. Anything you've saved in Readwise (highlights, articles, PDFs, books, youtube, newsletters) is now instantly accessible from the terminal. For you, and your AI agents. npm install -g @readwise/cli

@googledevs f your dev life feels like juggling spaghetti, Google just handed you a fork

Introducing the Developer’s Guide to AI Agent Protocols. Stop writing custom integration glue for every tool, API, and frontend. We used Google Agent Development Kit to build a B2B agent that handles the full stack using 6 open standards: MCP, A2A, UCP, AP2, A2UI, and AG-UI The future of agents is interoperable. Read the full technical guide here: goo.gle/4sRrgl2

@stitchbygoogle Your new vibe design partner. Google just proposed to the entire design community and the ring drops tomorrow

Tomorrow, we’re introducing you to your new vibe design partner. 🤝 Our biggest update ever drops tomorrow. 👀👇

@cursor_ai Cursor built the thing that fixes the thing that was breaking the thing. Recursively helpful

We trained Composer to self-summarize through RL instead of a prompt. This reduces the error from compaction by 50% and allows Composer to succeed on challenging coding tasks requiring hundreds of actions.

Comet Enterprise is available now. Somewhere a Salesforce executive is reading this and taking very deep breaths. The browser just became the platform

@perplexity_ai Other tools: please configure your connectors and read our 47 page integration docs. Perplexity: here's a browser agent. Go crazy

Computer can now take full control of Comet to complete tasks. When you’re in Comet, Computer spins up a browser agent that can access any site or logged‑in app with your permission, without the need for connectors or MCPs. Available to all Computer users on Comet.

@GeminiApp An AI use case my mom would understand and my body would hate

Clever Gemini use case: Custom alarm clock sounds. Create custom tracks that actually get you moving in the Gemini app. Instructions below 👇

@cursor_ai Your codebase has a night shift now and it doesn't take breaks or file PTO😶

We built a fleet of security agents to run continuously on our codebase. We're sharing new automation templates for you to do the same.

Tip: You can add a Custom Agent chat directly to any page perfect for wikis, onboarding guides, project docs, or any place your team might have questions!

@OsaurusAI personal computer used to mean yours then it meant renting yours from someone else Osaurus said let's go back

This is what "Personal Computer" should mean. Fully offline. Any model. Isolated sandbox. No subscription. Open source.

@GoogleAI @googlemaps my therapist asks what's been stressing me lately I said the task list she doesn't know it's empty now follow up appointment feels unnecessary

We’ve reimagined the way our Gemini models power @GoogleMaps. Here are some use cases you can try (and the advancements that make them possible): “Find a well-lit pickleball court that’s usually less busy on Tuesday nights” ➡️ Maps performs multi-step reasoning across 300M+ community-shared photos and reviews to find the exact vibe and place you’re looking for “We’re driving from San Francisco to Big Sur, plan the quickest route for me to drive there that avoids tolls and has a highly-rated coffee shop along the way” ➡️ The app synthesizes live geospatial data (traffic, weather, etc.) into insights that can inform your timely decisions, and visualizes the best way to get you there “Take the places on my 'Austin' list and plan out an itinerary for my weekend trip. I want to eat the best beef brisket, see some nature, and go two-stepping” ➡️ Maps now connects your saved favorites and search history with community feedback left on the app to predict what you’ll need for your next adventure

@AskPerplexity Finally, my docs can network better than I do at office socials

You can now embed your connectors directly inside web apps built by Perplexity Computer. To demonstrate, we built a document editor that uses the Google Docs and Notion connectors to fetch, edit, and save docs across both.

@cursor_ai YEAAY now my AI is being performance-reviewed… can we schedule the one-on-one with HR next?

We're sharing a new method for scoring models on agentic coding tasks. Here's how models in Cursor compare on intelligence and efficiency:

@maestro__dev manual testing is a feeling. automated testing is a fact 🥸

Is your app working as it should? AUTOMATE TESTING! 🥸