正在加载视频...

视频加载失败

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 次观看 • 7 天前 •via X (Twitter)

28 条评论

Blendi 的头像
Blendi7 天前

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

Blendi 的头像
Blendi7 天前

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

Blendi 的头像
Blendi7 天前

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

Blendi 的头像
Blendi7 天前

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

John Shedletsky 的头像
John Shedletsky7 天前

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

Blendi 的头像
Blendi7 天前

👀👀

Heinzel 的头像
Heinzel7 天前

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

Blendi 的头像
Blendi7 天前

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 👀

Sael 的头像
Sael7 天前

finally a reason to play minecraft

John Shedletsky 的头像
John Shedletsky7 天前

this is art

snaps💀🔺 的头像
snaps💀🔺7 天前

What a time to be alive.

Leo 的头像
Leo7 天前

this is awesome

aizk ✡️ 的头像
aizk ✡️7 天前

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

Creeper 的头像
Creeper7 天前

Multiplayer ??

Blendi 的头像
Blendi7 天前

Soon 👀

Lee Penkman 的头像
Lee Penkman7 天前

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

Name 的头像
Name7 天前

Thank you for that sir!

greenguy 的头像
greenguy7 天前

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

astro 的头像
astro7 天前

Bro just play the game.

Blendi 的头像
Blendi7 天前

This just lets me play more 🤣

Daniel Nadeem 的头像
Daniel Nadeem7 天前

pretty cool metaverse type situation but with AI and Minecraft.

Sannidhya Sah 的头像
Sannidhya Sah7 天前

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

Lorian 的头像
Lorian7 天前

I LOVE THIS SO MUCH

Tabmaster Allen #1 Fan 的头像
Tabmaster Allen #1 Fan7 天前

Marlow 😬

Angel Y Mendez S 的头像
Angel Y Mendez S7 天前

Yo made a banger.

Mr Pixel | Driftania 🏝 的头像
Mr Pixel | Driftania 🏝7 天前

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. 🤩

marcus 的头像
marcus7 天前

bro yes

king kusaila 👑 的头像
king kusaila 👑7 天前

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

相关视频

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 次观看 • 5 个月前