Загрузка видео...

Не удалось загрузить видео

На главную

Introducing AgentCraft: a multi-agent harness that runs inside Minecraft ⛏️ A team of Claude agents plans, builds in real worktrees, and walks over when they need you.

1,038,286 просмотров • 7 дней назад •via X (Twitter)

Комментарии: 28

Фото профиля Blendi
Blendi7 дней назад

it's fully open-source and powered by Claude through the agent SDK. Bring an API key, and point it at your repos!

Фото профиля Blendi
Blendi7 дней назад

i've actually been using this, it's so cool to have your work be in an actual 3D world instead of a desktop app or CLI

Фото профиля Blendi
Blendi7 дней назад

a lead plans and splits the goal, workers build in parallel, each in their own git worktree. When something should genuinely be my call, one walks over and I answer right there

Фото профиля Blendi
Blendi7 дней назад

for now nothing touches my code until i review the real diff in game and hit merge. Conflicts go back to the agent to resolve

Фото профиля John Shedletsky
John Shedletsky6 дней назад

you should make them all talk shit about the boss around the water cooler when you aren't watching.

Фото профиля Blendi
Blendi6 дней назад

👀👀

Фото профиля Heinzel
Heinzel7 дней назад

so because it's in Minecraft, could you like play with your friends on a multiplayer server while working?

Фото профиля Blendi
Blendi6 дней назад

So this mod doesn’t explicitly have this ability but it wouldn’t actually be so hard to do, might have some updates for you soon 👀

Фото профиля Sael
Sael7 дней назад

finally a reason to play minecraft

Фото профиля John Shedletsky
John Shedletsky6 дней назад

this is art

Фото профиля snaps💀🔺
snaps💀🔺6 дней назад

What a time to be alive.

Фото профиля Leo
Leo7 дней назад

this is awesome

Фото профиля aizk ✡️
aizk ✡️6 дней назад

This is cool, but it's shame it's not provider agnostic. Maybe I can throw my hat in the ring 😉

Фото профиля Creeper
Creeper7 дней назад

Multiplayer ??

Фото профиля Blendi
Blendi6 дней назад

Soon 👀

Фото профиля Lee Penkman
Lee Penkman6 дней назад

Lmao the tasks board in there then they break to build actionable business insights for key stakeholders supercharged with AI subagents I'm dieing

Фото профиля Name
Name6 дней назад

Thank you for that sir!

Фото профиля greenguy
greenguy7 дней назад

what happens when Wren and Kit disagree on the approach? does Marlow decide or does it come to you as a popup

Фото профиля astro
astro7 дней назад

Bro just play the game.

Фото профиля Blendi
Blendi6 дней назад

This just lets me play more 🤣

Фото профиля Daniel Nadeem
Daniel Nadeem6 дней назад

pretty cool metaverse type situation but with AI and Minecraft.

Фото профиля Sannidhya Sah
Sannidhya Sah6 дней назад

I thought Minecraft was supposed to distract me from work. Now my work is walking around in Minecraft.

Фото профиля Lorian
Lorian6 дней назад

I LOVE THIS SO MUCH

Фото профиля Tabmaster Allen #1 Fan
Tabmaster Allen #1 Fan6 дней назад

Marlow 😬

Фото профиля Angel Y Mendez S
Angel Y Mendez S6 дней назад

Yo made a banger.

Фото профиля Mr Pixel | Driftania 🏝
Mr Pixel | Driftania 🏝6 дней назад

worktree-per-worker is the actually smart part. 3D world just makes "it needs your call" feel like a coworker tapping your shoulder instead of a modal popup. 🤩

Фото профиля marcus
marcus6 дней назад

bro yes

Фото профиля king kusaila 👑
king kusaila 👑6 дней назад

agents walking over to you when they need you is the best notification system ive seen

Похожие видео

In the future, you’ll be able to accomplish a goal by just giving Claude an outcome and a budget. That’s the direction Anthropic is building in with its new Managed Agents features, announced at this week’s Code with Claude developer event. The basic idea: Claude, wrapped in a computer in the cloud, that you can spin up, scale, and manage as needed. Anthropic is taking on the infrastructure that kills most agent products, and making sure that it scales to meet the needs of agents running 24/7. On this week’s AI & I from Every 📧, I talk with Angela Jiang (Angela Jiang), head of product for the Claude platform, and Katelyn Lesse (Katelyn Lesse), head of engineering for the Claude platform, about what Anthropic is building and what it takes to make agents reliable in production. We get into: - Why the "build a generic harness, hot-swap any model behind it" playbook is already outdated. Angela points to eval data on Memory where the same task across different harnesses performed drastically differently. - The infrastructure wall every team hits in production—and why Katelyn thinks “my sandbox died and took the agent with it” is the real reason internal agents don't ship. - Why Anthropic is so bullish on using file systems and skills within Claude, including Angela's argument that those early design choices can compound for years. This is a must-watch for anyone trying to take an agent past the demo and into production. Watch below! Timestamps: How the Claude platform evolved from API to agents: 00:01:48 The primitives that make up Claude Managed Agents: 00:04:09 Why the harness and the model are becoming a single unit: 00:10:37 The infrastructure wall that kills most agent projects in production: 00:18:49 Why team agents need a different shape than individual productivity tools: 00:24:49 How Anthropic's legal team uses an agent to review marketing copy: 00:26:36 Using multi-agent orchestration for advisor strategies, adversarial pairs, and swarms: 00:34:24 How to measure agent success with outcome and budget as the end state: 00:35:50 What the platform looks like a year from now, when Claude writes its own harness: 00:39:11

Dan Shipper

66,871 просмотров • 5 месяцев назад