正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Announcing Agent Bricks: auto-optimize agents for your domain tasks. Provide a high-level description of the agent’s task, and connect your enterprise data — Agent Bricks handles the rest. Agent Bricks builds out an agent system that automatically optimizes against your goals and generates domain-specific synthetic datasets, accelerating agent development... show more

Databricks

90,708 subscribers

47,044 次观看 • 1 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

5 条评论

plockett.eth (🅰️,🌶) 的头像

plockett.eth (🅰️,🌶)1 年前

current docs for those looking:

plockett.eth (🅰️,🌶) 的头像

plockett.eth (🅰️,🌶)1 年前

All the links in this article are to internal dogfood links instead of public ones

Zachary Guthrie 的头像

Zachary Guthrie1 年前

Huge!

Jeff BasedOS 的头像

Jeff BasedOS1 年前

AGENT BRICKED UP

huduga 的头像

huduga1 年前

@dhrtha wonder if they are doing DSPy optimization in the backend.

相关视频

We released iOS app for Hermes Agent 📱 Connect to your self-hosted agent over Tailscale, Cloudflare Tunnel or ngrok. Or deploy on a VPS. Run tasks and manage your agent from anywhere.

We released iOS app for Hermes Agent 📱 Connect to your self-hosted agent over Tailscale, Cloudflare Tunnel or ngrok. Or deploy on a VPS. Run tasks and manage your agent from anywhere.

atomicbot.ai

113,186 次观看 • 5 个月前

Your Mastra agent now has an inbox. Connect external sources like GitHub or Slack, subscribe to emitted events, wake up your agent with `urgent` priority events:

Your Mastra agent now has an inbox. Connect external sources like GitHub or Slack, subscribe to emitted events, wake up your agent with `urgent` priority events:

Sam Bhagwat

11,621 次观看 • 4 个月前

Automate your Agent Development Life Cycle using Antigravity 2.0 and Gemini Enterprise Agent Platform. Build, Evaluate and Deploy AI Agents without even leaving Antigravity. This is the WAY.

Automate your Agent Development Life Cycle using Antigravity 2.0 and Gemini Enterprise Agent Platform. Build, Evaluate and Deploy AI Agents without even leaving Antigravity. This is the WAY.

Shubham Saboo

14,247 次观看 • 4 个月前

Assign a custom, on-chain domain to your AI agent in seconds. Use ⚡️ A verified domain = a unique identity, discoverability, trust. We made it simple: register your domain, verify ownership via a TXT record, assign it to your agent. Just watch 👇 is your all-in-one platform for agent discoverability and analytics. Give it a go.

Assign a custom, on-chain domain to your AI agent in seconds. Use ⚡️ A verified domain = a unique identity, discoverability, trust. We made it simple: register your domain, verify ownership via a TXT record, assign it to your agent. Just watch 👇 is your all-in-one platform for agent discoverability and analytics. Give it a go.

Fetch.ai

14,896 次观看 • 6 个月前

Agents are now your customers. Here are 9 startup ideas for that customer: - An agency that makes agents cite you. - A system that gives an agent an identity and permissions. - Receipts and audit trails for the work an agent does. - A generator that makes your documents ready for agents. - Security for the agent that reads your inbox. - A service that makes your pricing page readable to an agent. - MCP servers for franchises. - A support desk that agents call. - A sandbox where agents test your software. Pick one and build it.

Agents are now your customers. Here are 9 startup ideas for that customer: - An agency that makes agents cite you. - A system that gives an agent an identity and permissions. - Receipts and audit trails for the work an agent does. - A generator that makes your documents ready for agents. - Security for the agent that reads your inbox. - A service that makes your pricing page readable to an agent. - MCP servers for franchises. - A support desk that agents call. - A sandbox where agents test your software. Pick one and build it.

The Startup Ideas Podcast (SIP) 🧃

14,148 次观看 • 1 个月前

Your agent can recreate your top-performing ads. At scale. Connect Ad Reference via MCP. The agent reads any video that worked and generates new ones built around the same patterns. Built for pipelines on OpenClaw and other agents.

Your agent can recreate your top-performing ads. At scale. Connect Ad Reference via MCP. The agent reads any video that worked and generates new ones built around the same patterns. Built for pipelines on OpenClaw and other agents.

Higgsfield AI 🧩

77,738 次观看 • 5 个月前

OpenClaw Now Lives on Solana — Free AI Agents in Your Pocket We've integrated .molt domains with OpenClaw, bringing personal AI agents to the Solana ecosystem. Each .molt domain is a Metaplex Core NFT that unlocks your own AI agent instance. What you get: Wallet-based access — No accounts, no passwords. Connect your Solana wallet, prove NFT ownership, instant access Per-domain agents — Each domain NFT gets its own isolated AI agent with persistent memory Configure your channels — Set up Telegram, Discord, or Slack bots directly from the UI. Enter your bot token, click save, restart your agent Persistent storage — Your agent's memory and conversations persist in R2 storage, tied to your NFT The best part? It's free. You don't need a $600 MacBook. You don't need a $15/month VPS. You don't need to manage servers, Docker containers, or API keys. Just mint a .molt domain, connect your wallet, and you have OpenClaw in your pocket — accessible from any device, anywhere. Your domain. Your agent. Your data. All on-chain, all yours. Live on devnet:

OpenClaw Now Lives on Solana — Free AI Agents in Your Pocket We've integrated .molt domains with OpenClaw, bringing personal AI agents to the Solana ecosystem. Each .molt domain is a Metaplex Core NFT that unlocks your own AI agent instance. What you get: Wallet-based access — No accounts, no passwords. Connect your Solana wallet, prove NFT ownership, instant access Per-domain agents — Each domain NFT gets its own isolated AI agent with persistent memory Configure your channels — Set up Telegram, Discord, or Slack bots directly from the UI. Enter your bot token, click save, restart your agent Persistent storage — Your agent's memory and conversations persist in R2 storage, tied to your NFT The best part? It's free. You don't need a $600 MacBook. You don't need a $15/month VPS. You don't need to manage servers, Docker containers, or API keys. Just mint a .molt domain, connect your wallet, and you have OpenClaw in your pocket — accessible from any device, anywhere. Your domain. Your agent. Your data. All on-chain, all yours. Live on devnet:

Molt.id

315,151 次观看 • 8 个月前

I made a real-world AI hedge fund team. It has 4 agents: 1 • market data agent 2 • quant agent 3 • risk manager agent 4 • portfolio manager agent You can run all of my code below. No prior coding experience is required. The agents work sequentially, passing messages to the next agent. 1 • Market Data Agent gathers market data and calculates technical signals. 2 • Quant Agent takes market data and generates a buy, sell, or hold signal. 3 • Risk Management Agent takes trading signal and generates a risk signal. 4 • Portfolio Management Agent considers all signals and makes a final trading decision.

I made a real-world AI hedge fund team. It has 4 agents: 1 • market data agent 2 • quant agent 3 • risk manager agent 4 • portfolio manager agent You can run all of my code below. No prior coding experience is required. The agents work sequentially, passing messages to the next agent. 1 • Market Data Agent gathers market data and calculates technical signals. 2 • Quant Agent takes market data and generates a buy, sell, or hold signal. 3 • Risk Management Agent takes trading signal and generates a risk signal. 4 • Portfolio Management Agent considers all signals and makes a final trading decision.

Virat Singh

369,381 次观看 • 1 年前

Introducing MemCurrent, a persistent memory architecture designed to help production agents stop starting from zero. MemCurrent combines episodic memory with derived memory across three access patterns: • Plugins to log and load context automatically • Tools the agent calls on demand • An offline “dreaming” pipeline that consolidates memory in the background Agents carry forward user preferences, prior corrections, metric definitions and successful workflows instead of rediscovering them every session. On our internal benchmark built from real enterprise data, MemCurrent triples the agent's pass rate while using 31% fewer tokens and running 26% faster. It's built into Agent Bricks' Memory offering and already powers memory in Genie. Read the research:

Introducing MemCurrent, a persistent memory architecture designed to help production agents stop starting from zero. MemCurrent combines episodic memory with derived memory across three access patterns: • Plugins to log and load context automatically • Tools the agent calls on demand • An offline “dreaming” pipeline that consolidates memory in the background Agents carry forward user preferences, prior corrections, metric definitions and successful workflows instead of rediscovering them every session. On our internal benchmark built from real enterprise data, MemCurrent triples the agent's pass rate while using 31% fewer tokens and running 26% faster. It's built into Agent Bricks' Memory offering and already powers memory in Genie. Read the research:

Databricks

41,866 次观看 • 6 天前

Today Air becomes an agent that can run all your creative tasks for you. You make the work. Air handles the rest.

Today Air becomes an agent that can run all your creative tasks for you. You make the work. Air handles the rest.

Shane Hegde

63,758 次观看 • 20 天前

Introducing Duet CLI. Now coding agents like Claude Code and Codex can call Duet (our agent-building agent) directly from the terminal to build and modify Decagon agents. Duet handles work within Decagon and returns the result while your coding agent stays focused on the broader task.

Introducing Duet CLI. Now coding agents like Claude Code and Codex can call Duet (our agent-building agent) directly from the terminal to build and modify Decagon agents. Duet handles work within Decagon and returns the result while your coding agent stays focused on the broader task.

Decagon

770,006 次观看 • 2 个月前

Now in VS Code stable: Agent Skills, the open standard created by Anthropic. These folders of instructions, scripts, and resources can be loaded to perform specialized tasks, allowing you to teach the coding agent new capabilities and provide domain-specific knowledge.

Now in VS Code stable: Agent Skills, the open standard created by Anthropic. These folders of instructions, scripts, and resources can be loaded to perform specialized tasks, allowing you to teach the coding agent new capabilities and provide domain-specific knowledge.

Visual Studio Code

116,348 次观看 • 9 个月前

🚀 Introducing Queue: A Smarter Way to Build with Replit Agent Today, we’re excited to launch Queue, a powerful new capability designed to enhance your experience with Replit Agent. With Queue, you can submit multiple tasks while your Agent is still working—no more waiting around or breaking your flow. As each task completes, the Agent automatically moves to the next. You can: ✅ Add multiple tasks for the Agent to process in order. ✅ Edit, reorder, or reprioritize messages on the fly. ✅ Attach files and adjust settings—including toggling extended thinking or selecting a different model—per task.

🚀 Introducing Queue: A Smarter Way to Build with Replit Agent Today, we’re excited to launch Queue, a powerful new capability designed to enhance your experience with Replit Agent. With Queue, you can submit multiple tasks while your Agent is still working—no more waiting around or breaking your flow. As each task completes, the Agent automatically moves to the next. You can: ✅ Add multiple tasks for the Agent to process in order. ✅ Edit, reorder, or reprioritize messages on the fly. ✅ Attach files and adjust settings—including toggling extended thinking or selecting a different model—per task.

Replit ⠕

75,751 次观看 • 1 年前

Simply and securely optimize and monitor production-grade AI agents in minutes entirely on Gemini Enterprise Agent Platform. Learn more about Agent Platform's new capabilities, available to everyone—from Agent Observability to Agent Evaluations →

Simply and securely optimize and monitor production-grade AI agents in minutes entirely on Gemini Enterprise Agent Platform. Learn more about Agent Platform's new capabilities, available to everyone—from Agent Observability to Agent Evaluations →

Google Cloud Tech

33,506 次观看 • 2 个月前

Now your AI friend can buy a domain for that site you're working on easily with This was the first roadblock I ran into with my AI, it couldn't buy a domain! Now your agent can do it easily with L402. Point your agent to the site or npx unhuman domains

Now your AI friend can buy a domain for that site you're working on easily with This was the first roadblock I ran into with my AI, it couldn't buy a domain! Now your agent can do it easily with L402. Point your agent to the site or npx unhuman domains

Nick Slaney

29,018 次观看 • 8 个月前

We just launched Twin 2 500,000+ tasks automated in our first month. Now: multi-agent automation. → Master agent that orchestrates all your agents → Workspaces where agents share context and collaborate → Persistent databases for long-term memory → See and edit your agent brain for maximum control → Runner mode: scale at 1/10th the cost → Auto-generated web apps to share your agents Try it out now!

We just launched Twin 2 500,000+ tasks automated in our first month. Now: multi-agent automation. → Master agent that orchestrates all your agents → Workspaces where agents share context and collaborate → Persistent databases for long-term memory → See and edit your agent brain for maximum control → Runner mode: scale at 1/10th the cost → Auto-generated web apps to share your agents Try it out now!

Hugo Mercier

11,226 次观看 • 8 个月前

Auto-discover and connect to your running Chrome with agent-browser agent-browser --auto-connect open <url> Or via environment variable: AGENT_BROWSER_AUTO_CONNECT=1

Auto-discover and connect to your running Chrome with agent-browser agent-browser --auto-connect open <url> Or via environment variable: AGENT_BROWSER_AUTO_CONNECT=1

Chris Tate

142,722 次观看 • 7 个月前

Tired of managing your LinkedIn presence? Check out today’s spotlight: the LinkedIn Agent on ASI:One.⚡ This agent automatically creates stunning posts, manages your content, and pulls your profile info, all with simple commands. Forget logging in. Just chat, and the agent does the work. Try now on Link to agent: Watch👇

Fetch.ai

24,855 次观看 • 1 年前