Atomic Chat provider with local/private LLMs now working with goose: https://github.com/AtomicBot-ai/Atomic-Chat (new speculative decoding speedup with MTP)

Wondering what WebMCP is? ❌ It's not an MCP server ❌ It's not the same thing as Playwright MCP ✅ Instead of automating the UI, WebMCP turns your website into callable tools for AI agents. Read our blog post to learn more! https://block.github.io/goose/blog/2026/03/17/webmcp-for-beginners/

1.26.0 is here, which means: - local inference just got an upgrade - chat with goose via telegram - and even more providers

What if your AI agent could order your lunch. Well it can now with the Neighborhood MCP server. Check out our post showing you how it works and make sure you give it a try yourself. https://block.github.io/goose/blog/2026/02/25/order-lunch-with-goose

Heard of WebMCP? It's a new standard from Chrome that bridges AI agents and websites. Instead of AI guessing how to click buttons, sites can declare what actions they support. Join Rizel today as she explore how we can use it with goose. 📆 Feb 26 at 1pm ET 📺 https://youtube.com/live/4LfBsSWEitE

What if your AI agent could order lunch? 🥑 We connected Goose to Square's Neighborhood MCP App. Now it can find nearby restaurants, browse real menus, and build your order. Avocado toast with feta? It's on the way! Try it out ⬇️

Just ordered lunch without leaving my AI agent 🤯 With the Neighborhood extension in goose, I found nearby restaurants, browsed menus with images right in the chat, and added my orders to the cart, all from a simple prompt. The future of AI-powered food ordering is here 🍜🥗 youtu.be/DG1HUFsekyc

Bradley Axen, Creator of goose, joined Open Source Security to talk about: ✅ Why Block donated goose to the Agentic AI Foundation ✅ AI-generated PRs and open source quality ✅ What comes after chat-based agents https://opensourcesecurity.io/2026/2026-02-goose-aaif-brad-axen/

What's new in goose v1.25.0: 🛡️ macOS sandboxing for every command ⚡ Unified Summon — one extension, two tools 🎨 Rich interactive UI in chat via MCP Apps 📋 Model & provider recipe config right from the GUI 🔏 SLSA build provenance on every binary Watch the full breakdown 👇

Still drawing architecture diagrams by hand and screenshotting whiteboards? The @excalidraw.com MCP App turns visual workflows into a tool call. Prompt goose to generate, edit, and export Excalidraw files.

Happy Friday! Let's see what's up next in goose programming.

the results of a successful meetup! 👏

Still running one agent at a time like it's 2025? We took the vision of Gas Town and built Goosetown: a lean multi-agent orchestration layer for goose. Goosetown orchestrates subagents across worktrees so you can run flocks, not babysit a single thread. block.github.io/goose/blog/2...

With the Playwright CLI skill you can ask goose in natural language to do browser automation and even generate tests. Join Debbie as she dives into skills and how to use the Playwright CLI skill 📆 Feb 19 at 1 pm ET/10am PT 📺 https://linktr.ee/goose_oss

Check out our tutorial on how to use the Playwright CLI skill to automate your tests using natural language. https://block.github.io/goose/docs/tutorials/playwright-skill

Come join us as we explore agentic testing and browser automation using the newly released Playwright CLI skill: https://linktr.ee/goose_oss

Happy Friday! Let's see what's up next in goose programming.

In this video, we show how to set up @playwright.dev Skills to browse the web and record traces and video, and turn agent actions into real tests. Agentic testing in action. youtu.be/_MpbmD_unnU?...

goose made this video about itself making videos. Yes, it's as meta as it sounds. Try goose today with Remotion Agent Skills.

goose is going home... literally. 🏡 Meet our newest goose grant project by Jerry Ochieng: "Goose In A Pond", a local-first AI home assistant running entirely on edge hardware. ✦ Offline voice interaction ✦ Smart device control ✦ Privacy-first, no cloud required ✦ Powered by goose on NVIDIA Jetson

Welcome to goosetown! Population: your distributed team of async subagents. Inspired by Steve Yegge’s Gas Town, a multi-agent workspace manager. Join Rizel as she dives into goosetown and stress-tests it in real time. 📆 Feb 12 at 12 pm ET/9am PT 📺 https://linktr.ee/goose_oss

One shot prompting died the moment we tried to build something real. A clever prompt can’t compensate for broken context. Check out the blog to learn the workflow that replaced it, so your agent stops forgetting and your work stops resetting. block.github.io/goose/blog/2...

Code Mode was trending for weeks. Most devs don't know what it is. What people think: ❌ An MCP replacement ❌ Faster execution What it actually is: ✅ A pattern built on MCP ✅ Batched tool calls ✅ Fewer tokens https://block.github.io/goose/blog/2026/02/06/8-things-you-didnt-know-about-code-mode

Everyone's buying Mac Minis to run OpenClaw. @blackgirlbytes.bsky.social built her own version using goose as the backend instead. She used the RPI method to stop the agent from hallucinating non-existent APIs and wrote about it: block.github.io/goose/blog/2026/02/06/rpi-openclaw-alternative

There are 4 quadrants of AI usage: • Learning Zone • Thinking Ahead • Underutilizing • Frontier rp-why is a goose skill that shows where you are and how to level up. block.github.io/goose/blog/2026/02/06/rp-why-skill

Happy Friday! It's time to see what's up next in goose programming.

Last time we turned our MCP UI server into an MCP app. Today we’re plugging that same app into ChatGPT. Join us at 1PM ET | 10 AM PT 📺: https://linktr.ee/goose_oss

From suggesting new features to helping troubleshoot issues, it's time to see who are the top goose community stars for January 2026!

We teamed up with @MCPJams to share everything we learned building MCP Apps. Here's some tips that would've saved us hours: → Adapt to host themes → Control what the model sees → Handle loading states properly → Keep the model in sync → Restrict who can trigger tools Link to blog in the thread 👇

🚀 Goose Flight Log is ready for takeoff! Discover everything the team tackled together in open source with the community, from contributions, to building new features and more. Subscribe for new editions in your inbox every month. ❤️

Skill issue? We fixed that. goose now has a skill registry where you can: ✅ share skills you've built ✅ discover skills from the community ✅ easily plug them into your agent add yours → https://block.github.io/goose/skills/

Wondering what Beads is or why engineers keep talking about it? It promises easier parallel work, memory, task coordination. Join Rizel live as she puts the hype to the test, using goose with Beads and Ghostty to ship multiple features in parallel. 📆 Jan 29 at 1pm ET 📺 https://linktr.ee/goose_oss

Forgot what you were working on? goose remembers. With Beads, goose can track your tasks and dependencies across sessions so you can pick up right where you left off. Get started with this tutorial ⬇️ https://block.github.io/goose/docs/mcp/beads-mcp

Learn how to migrate your MCP-UI server to an MCP App. Our Developer Advocate, Ebony Louis, walks through the real process, code changes, and why this matters for portability across hosts. https://block.github.io/goose/blog/2026/01/22/mcp-ui-to-mcp-apps

Can you spot the difference between MCP-UI and MCP Apps? Trick question: the UI looks the same. The architecture is what changes. Quick walkthrough of what MCP Apps unlock and why it actually matters. Full video: https://youtu.be/QcojQ3Fwqsw

You can use @Remotion Skills to create videos from a prompt. Here's how to set it up in goose: 1. Run npx skills add remotion-dev/skills 2. Enable the Skills extension in goose settings 3. Prompt

Happy Friday everyone! It's time to check out what's coming up next week.

Join Ebony Louis this Thursday (1/22) for a live walkthrough of MCP Apps. Learn what they are, how they differ from MCP-UI, and how to turn an MCP-UI server into an MCP App. 📆 Jan 22 · 10am PT / 1pm ET 📺 https://linktr.ee/goose_oss

MCP sampling, explained visually. See the difference between tools that just return data vs. tools that actively participate in reasoning. https://block.github.io/goose/blog/2026/01/15/why-tool-descriptions-arent-enough/

If Ralph Wiggum Loop keeps showing up on your feed, this video breaks down what it actually is and the problem it’s trying to solve. https://www.youtube.com/watch?v=IS_naHhVeOo

Happy Friday 🪿 It's time to see what events are coming up next! Spoiler alert: get ready for incredible (virtual) workshops! 🧵

Open source maintenance is a marathon. So, we put our own agent to work on its own backlog by embedding goose into a GitHub Action to autonomously fix issues. Learn how this self-healing workflow keeps our backlog moving. ⬇️ https://block.github.io/goose/blog/2025/12/28/goose-maintains-goose/

Ralph Wiggum loops have been all the rage! Our Developer Advocate, Rizel Scarlet, is going live in 1 hour to walk through it all. Update: The MCP-UI to MCP App stream has been rescheduled to Thurs, Jan 22 at 1:00 PM ET. Thanks for your flexibility, hope you can join both!

Ralph Wiggum loop: real or gimmick? You can decide after you see it run. Join Rizel as she executes the Ralph Loop she engineered for goose. Built to avoid context bloat and powered by a multi-model worker/reviewer setup. 📆 Jan 15, 2025 at 10am PT / 1pm ET (TODAY) 📺 https://linktr.ee/goose_oss

We brought the Ralph Wiggum loop to goose with a multi-model approach where one model does the work and a second model reviews it. Tutorial 👇 https://block.github.io/goose/docs/tutorials/ralph-loop

First it was MCP-UI ..... now its MCP Apps 👀 Join me as we explore MCP Apps, what they are, how they differ from MCP-UI, and how to turn an existing MCP-UI server into a proper MCP App. Bonus: if time allows, we’ll try making it compatible with ChatGPT apps.

It's Friday~ You know what that means...the team is back from the holidays, and have upcoming events you don't want to miss!🪿 (links in the replies)

Is the real AI skill gap coding or orchestration? This short shows MCP sampling in action, using the Council of Mine MCP server as an example. One question → nine LLM conversations → one synthesized conclusion. Do you agree with the council’s conclusion?

Ever felt like your agent isn’t behaving the way you expect? Join us live as we show you how to leverage Skills and goose Recipes to shape agent behavior beyond prompting. 📆 Jan 8 at 10am PT/ 1pm ET 📺 linktr.ee/goose_oss