Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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 Aufrufe • vor 7 Tagen •via X (Twitter)

28 Kommentare

Profilbild von Blendi
Blendivor 7 Tagen

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

Profilbild von Blendi
Blendivor 7 Tagen

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

Profilbild von Blendi
Blendivor 7 Tagen

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

Profilbild von Blendi
Blendivor 7 Tagen

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

Profilbild von John Shedletsky
John Shedletskyvor 6 Tagen

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

Profilbild von Blendi
Blendivor 6 Tagen

👀👀

Profilbild von Heinzel
Heinzelvor 6 Tagen

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

Profilbild von Blendi
Blendivor 6 Tagen

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 👀

Profilbild von Sael
Saelvor 7 Tagen

finally a reason to play minecraft

Profilbild von John Shedletsky
John Shedletskyvor 6 Tagen

this is art

Profilbild von snaps💀🔺
snaps💀🔺vor 6 Tagen

What a time to be alive.

Profilbild von Leo
Leovor 6 Tagen

this is awesome

Profilbild von aizk ✡️
aizk ✡️vor 6 Tagen

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

Profilbild von Creeper
Creepervor 6 Tagen

Multiplayer ??

Profilbild von Blendi
Blendivor 6 Tagen

Soon 👀

Profilbild von Lee Penkman
Lee Penkmanvor 6 Tagen

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

Profilbild von Name
Namevor 6 Tagen

Thank you for that sir!

Profilbild von greenguy
greenguyvor 7 Tagen

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

Profilbild von astro
astrovor 6 Tagen

Bro just play the game.

Profilbild von Blendi
Blendivor 6 Tagen

This just lets me play more 🤣

Profilbild von Daniel Nadeem
Daniel Nadeemvor 6 Tagen

pretty cool metaverse type situation but with AI and Minecraft.

Profilbild von Sannidhya Sah
Sannidhya Sahvor 6 Tagen

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

Profilbild von Lorian
Lorianvor 6 Tagen

I LOVE THIS SO MUCH

Profilbild von Tabmaster Allen #1 Fan
Tabmaster Allen #1 Fanvor 6 Tagen

Marlow 😬

Profilbild von Angel Y Mendez S
Angel Y Mendez Svor 6 Tagen

Yo made a banger.

Profilbild von Mr Pixel | Driftania 🏝
Mr Pixel | Driftania 🏝vor 6 Tagen

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. 🤩

Profilbild von marcus
marcusvor 6 Tagen

bro yes

Profilbild von king kusaila 👑
king kusaila 👑vor 6 Tagen

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

Ähnliche Videos

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 Aufrufe • vor 5 Monaten