Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

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.

Blendi

6,589 subscribers

1,038,286 views • 7 days ago •via X (Twitter)

Education Gaming Science & Technology

Anya Rossi• Live Now

Private livecam show

28 Comments

Blendi7 days ago

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

Blendi7 days ago

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

Blendi7 days ago

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

Blendi7 days ago

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 Shedletsky7 days ago

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

Blendi7 days ago

👀👀

Heinzel7 days ago

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

Blendi7 days ago

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 👀

Sael7 days ago

finally a reason to play minecraft

John Shedletsky7 days ago

this is art

snaps💀🔺7 days ago

What a time to be alive.

Leo7 days ago

this is awesome

aizk ✡️7 days ago

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

Creeper7 days ago

Multiplayer ??

Blendi7 days ago

Soon 👀

Lee Penkman7 days ago

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

Name7 days ago

Thank you for that sir!

greenguy7 days ago

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

astro7 days ago

Bro just play the game.

Blendi7 days ago

This just lets me play more 🤣

Daniel Nadeem7 days ago

pretty cool metaverse type situation but with AI and Minecraft.

Sannidhya Sah7 days ago

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

Lorian7 days ago

I LOVE THIS SO MUCH

Tabmaster Allen #1 Fan7 days ago

Marlow 😬

Angel Y Mendez S7 days ago

Yo made a banger.

Mr Pixel | Driftania 🏝7 days ago

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. 🤩

marcus7 days ago

bro yes

king kusaila 👑7 days ago

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

Related Videos

Introducing multi-agent orchestration in Oz, with support for Claude Code, Codex and the Warp Agent. Use /orchestrate to delegate complex tasks across a team of agents, locally or in the cloud.

Introducing multi-agent orchestration in Oz, with support for Claude Code, Codex and the Warp Agent. Use /orchestrate to delegate complex tasks across a team of agents, locally or in the cloud.

Warp

1,198,812 views • 4 months ago

Introducing Offloop! We're a team of four. Today our multi-agent harness hit state of the art on GDPval, ahead of Claude code and Codex across jobs that pay $2.4 trillion a year in the US. Offloop gives every knowledge worker what the Fortune 500 spends billions on: a high-performing agent army that runs itself and grows the business.

Introducing Offloop! We're a team of four. Today our multi-agent harness hit state of the art on GDPval, ahead of Claude code and Codex across jobs that pay $2.4 trillion a year in the US. Offloop gives every knowledge worker what the Fortune 500 spends billions on: a high-performing agent army that runs itself and grows the business.

Offloop

2,641,437 views • 2 months ago

Introducing Claude Managed Agents: everything you need to build and deploy agents at scale. It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days. Now in public beta on the Claude Platform.

Introducing Claude Managed Agents: everything you need to build and deploy agents at scale. It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days. Now in public beta on the Claude Platform.

Claude

21,828,928 views • 6 months ago

Introducing Claude agents in Notion. Your task board is Claude’s to-do list. Anthropic runs the model and the agent harness. Notion is the orchestration layer: context, UI, and a shared place for teams to review and ship, and kick off Claude workflows. Join the waitlist:

Introducing Claude agents in Notion. Your task board is Claude’s to-do list. Anthropic runs the model and the agent harness. Notion is the orchestration layer: context, UI, and a shared place for teams to review and ship, and kick off Claude workflows. Join the waitlist:

Notion

495,762 views • 6 months ago

The Every team runs as much work as possible through agents. To help the whole team share skills when a new model comes out, they built a company agent on Claude Managed Agents that everyone uses in Slack. Once it caught on internally, they released it to their subscribers.

The Every team runs as much work as possible through agents. To help the whole team share skills when a new model comes out, they built a company agent on Claude Managed Agents that everyone uses in Slack. Once it caught on internally, they released it to their subscribers.

Claude

345,089 views • 3 days ago

Introducing October, the world's most advanced agent orchestrator Claude? Codex? Grok? Cursor? Which model? Which harness? How much quota is left? You shouldn't have to care Give October a task. It builds the team, connects the agents with native agent agent comms, and orchestrates the work based on the task, your taste, budget and remaining usage (or build the team yourself) And it's multiplayer: your team's agents can work with yours, live on the same canvas

Introducing October, the world's most advanced agent orchestrator Claude? Codex? Grok? Cursor? Which model? Which harness? How much quota is left? You shouldn't have to care Give October a task. It builds the team, connects the agents with native agent agent comms, and orchestrates the work based on the task, your taste, budget and remaining usage (or build the team yourself) And it's multiplayer: your team's agents can work with yours, live on the same canvas

Harsh Savergaonkar

25,878 views • 22 days ago

Introducing Code Review, a new feature for Claude Code. When a PR opens, Claude dispatches a team of agents to hunt for bugs.

Introducing Code Review, a new feature for Claude Code. When a PR opens, Claude dispatches a team of agents to hunt for bugs.

Claude

23,587,624 views • 7 months ago

THIS IS HOW A SENIOR ENGINEER ACTUALLY SCALES THEMSELVES WITH CLAUDE CODE the biggest change with AI isn't coding faster. it's where you actually spend your time now. more detailed prompts, more code review, more planning, less typing, etc. here's the workflow: this guy has been shipping code since the days of cgi and perl. he uses a compound engineering plugin that runs 5 separate agents on every task. one brainstorms, one plans the technical implementation, one executes, one reviews, one checks different verticals. every step is documented in markdown files. it's slow and way more waiting. but the output quality is way higher because each agent is focused on one thing. then the REAL multiplier is in git worktrees if Claude Code made you 10x faster, worktrees multiplies that again depending on how many agents you can manage in parallel his team runs 4-8 Claude Code sessions at the same time across different worktrees with each one working on a separate task. the skill is managing multiple AI agents in parallel without losing track, that's the next evolution of engineering

THIS IS HOW A SENIOR ENGINEER ACTUALLY SCALES THEMSELVES WITH CLAUDE CODE the biggest change with AI isn't coding faster. it's where you actually spend your time now. more detailed prompts, more code review, more planning, less typing, etc. here's the workflow: this guy has been shipping code since the days of cgi and perl. he uses a compound engineering plugin that runs 5 separate agents on every task. one brainstorms, one plans the technical implementation, one executes, one reviews, one checks different verticals. every step is documented in markdown files. it's slow and way more waiting. but the output quality is way higher because each agent is focused on one thing. then the REAL multiplier is in git worktrees if Claude Code made you 10x faster, worktrees multiplies that again depending on how many agents you can manage in parallel his team runs 4-8 Claude Code sessions at the same time across different worktrees with each one working on a separate task. the skill is managing multiple AI agents in parallel without losing track, that's the next evolution of engineering

Om Patel

159,860 views • 6 months ago

Anthropic Research Lead: "99% of our engineers run swarms of 300+ self-improving agents Close the loop and give the model a way to verify its own output" In a 20-minute session, an Anthropic team member walks through how to build agents that improve after every run Agents → Harness → Loops → Self-Improvement the real setup is Claude running through systems that check, correct, and upgrade themselves the part most agent courses skip this is better than most $1,300 agent engineering courses bookmark and watch the talk then read the full article below

Anthropic Research Lead: "99% of our engineers run swarms of 300+ self-improving agents Close the loop and give the model a way to verify its own output" In a 20-minute session, an Anthropic team member walks through how to build agents that improve after every run Agents → Harness → Loops → Self-Improvement the real setup is Claude running through systems that check, correct, and upgrade themselves the part most agent courses skip this is better than most $1,300 agent engineering courses bookmark and watch the talk then read the full article below

Callan

14,956 views • 7 days ago

Introducing terminal-browser A browser that runs inside your existing terminal - Preview your website next to your agent - Open HTML plans in your terminal - Browser use CLI built in

Introducing terminal-browser A browser that runs inside your existing terminal - Preview your website next to your agent - Open HTML plans in your terminal - Browser use CLI built in

Rob Pruzan

562,238 views • 2 months ago

Introducing AgentHQ 🤖🏢 Multi-agent orchestration shouldn’t feel boring or dull, buried under terminals, JSON, and dashboards. AgentHQ makes agent orchestration fun, simple, and reliable. Hire Claude and Codex agents, assign tasks, and watch your team collaborate in a retro 2D office. Learn more ⬇️ 🧵

Introducing AgentHQ 🤖🏢 Multi-agent orchestration shouldn’t feel boring or dull, buried under terminals, JSON, and dashboards. AgentHQ makes agent orchestration fun, simple, and reliable. Hire Claude and Codex agents, assign tasks, and watch your team collaborate in a retro 2D office. Learn more ⬇️ 🧵

Kye Gomez (swarms)

54,400 views • 1 month ago

anthropic engineers just built a full app from scratch with a loop of agents, start to finish in 40 minutes it's the claude code team. they used three agents: one plans, one builds, one checks the work. they keep cycling until the app actually runs the model matters less than i thought. the loop is what made it work

anthropic engineers just built a full app from scratch with a loop of agents, start to finish in 40 minutes it's the claude code team. they used three agents: one plans, one builds, one checks the work. they keep cycling until the app actually runs the model matters less than i thought. the loop is what made it work

Dean W. Perkins

15,290 views • 4 days ago

Introducing 𝙨𝙚𝙨𝙨𝙞𝙤𝙣-𝙢𝙞𝙜𝙧𝙖𝙩𝙚, a tool for migrating coding agent sessions across Claude Code, Codex, Pi, OpenCode, and more. If you started in Claude but ran of usage, you can now convert your session to another harness in one command:

Introducing 𝙨𝙚𝙨𝙨𝙞𝙤𝙣-𝙢𝙞𝙜𝙧𝙖𝙩𝙚, a tool for migrating coding agent sessions across Claude Code, Codex, Pi, OpenCode, and more. If you started in Claude but ran of usage, you can now convert your session to another harness in one command:

Xing Han Lu

30,709 views • 1 month ago

Why have one AI agent handle everything when you can build a team? 🤝 Multi-agent architecture allows a main agent to spin up specialized sub-agents and handle complex tasks in parallel - making workflows faster and more efficient inside Google AI Studio. Check out the full I/O session: 🧵👇

Why have one AI agent handle everything when you can build a team? 🤝 Multi-agent architecture allows a main agent to spin up specialized sub-agents and handle complex tasks in parallel - making workflows faster and more efficient inside Google AI Studio. Check out the full I/O session: 🧵👇

Google for Developers

12,456 views • 4 months ago

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

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 views • 5 months ago

Now building is a team sport. Introducing Slack Code: a new way for your team and AI agents, like Anthropic's Claude Code, Claude Tag, Devin from Cognition, GitHub Copilot, ChatGPT, and Vercel agents, to write, review, and ship code together. Just mention an agent to spin up a channel, pull in your team, and start building. All in the open. All in Slack.

Now building is a team sport. Introducing Slack Code: a new way for your team and AI agents, like Anthropic's Claude Code, Claude Tag, Devin from Cognition, GitHub Copilot, ChatGPT, and Vercel agents, to write, review, and ship code together. Just mention an agent to spin up a channel, pull in your team, and start building. All in the open. All in Slack.

Slack

589,923 views • 1 month ago

Anthropic's Claude team just showed how to build an AI agent with real memory in under 30 minutes. 24-minutes. free. by the people who built Claude. one person + 10 agents with memory = a team that runs 24/7, remembers every customer improves itself. worth than $500 vibe-coding course.

Anthropic's Claude team just showed how to build an AI agent with real memory in under 30 minutes. 24-minutes. free. by the people who built Claude. one person + 10 agents with memory = a team that runs 24/7, remembers every customer improves itself. worth than $500 vibe-coding course.

Codez

1,626,612 views • 5 months ago

I built a real estate AI Agent team with multi-agents using gpt-OSS and Firecrawl. It has 3 AI agents working together as a team: 1. Property Search Agent 2. Market Analysis Agent 3. Property Valuation Agent 100% Opensource with step-by-step tutorial.

I built a real estate AI Agent team with multi-agents using gpt-OSS and Firecrawl. It has 3 AI agents working together as a team: 1. Property Search Agent 2. Market Analysis Agent 3. Property Valuation Agent 100% Opensource with step-by-step tutorial.

Shubham Saboo

116,974 views • 1 year ago

Claude Code Unpacked! Visual walkthrough of the entire 500k-line leaked codebase. What happens when you type a message: - the agent loop - 50+ tools - multi-agent orchestration - unreleased features Want to understand the internals or build your own agent harness? start here:

Claude Code Unpacked! Visual walkthrough of the entire 500k-line leaked codebase. What happens when you type a message: - the agent loop - 50+ tools - multi-agent orchestration - unreleased features Want to understand the internals or build your own agent harness? start here:

Akshay 🚀

24,552 views • 6 months ago