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 Robo Use: API to physical worlds for agents One interface, 32 embodiments, 100+ scenarios, and 11 agents and models We aggregated all academic simulator scenarios and ran 2500+ trials with initial results. Preview them or try it yourself 🧵

Xiangyi Li

9,230 subscribers

43,620 views • 20 days ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

26 Comments

Xiangyi Li20 days ago

Every command on screen is the agent's own, from real trials replayed in high resolution.

Xiangyi Li20 days ago

32 robots, one interface. Five LLM agents and a VLA policy drive them. Clips marked “not on are unpublished trials, and a few robots are not in the released package yet.

Xiangyi Li20 days ago

Leaderboard: Opus 5.5 on Claude Code ranks first overall, 306 of 342. The lead comes from refusing harmful requests; on the 292 other shared tasks GPT-6 Astra leads, 269 to 262.

Xiangyi Li20 days ago

Try it on macOS (Apple silicon) or Linux arm64: pip install robouse

Alexandru- Andrei Rotaru19 days ago

I might have some bad news if you aggregated LIBERO data points; they may have counterproductive sequences ...

Xiangyi Li19 days ago

why's that 👀

Alexandru- Andrei Rotaru19 days ago

The why is the why, but we went to the trouble of manually inspecting episodes, and like 15% of the time they have sequences of objects being dropped or grab misses, etc..

jia20 days ago

amazing!

Xiangyi Li19 days ago

Yayy

Henry Ventura19 days ago

sir pls

Xiangyi Li19 days ago

Lfg

sarat kumar19 days ago

Only 100+ scenarios in reals it's like trilions+ scenarios

Hubert Thieblot20 days ago

epic

Xiangyi Li20 days ago

let's go

Arjun Subramaniam20 days ago

Hell yeah!

Xiangyi Li20 days ago

lfg

Aayushman Singh19 days ago

Cross embodiment action spaces are the tax ngl

Xiangyi Li19 days ago

Say more! 👂

Xuhong Huang19 days ago

How can I have a Try?

Xiangyi Li19 days ago

Yes! Pip install robouse

Xuhong Huang19 days ago

API? need money or not bro

Marc19 days ago

Can I use my own robot and agent ?

Xiangyi Li19 days ago

Yes! Happy to chat

Tatul Danielyan19 days ago

was this tested on a real robot? e.g. so-101 tier

karthik vetrivel20 days ago

how did you structure the compute for running 2500+ trials?

Xiangyi Li19 days ago

Neocloud+subs

Related Videos

Introducing the Gemini API CLI, now live in preview! 🚀 The easiest way for your agents to generate images, videos, music, text-to-speech or use managed agents. A fast and efficient way to get access to all the goodness of the Gemini API. 🧵👇

Introducing the Gemini API CLI, now live in preview! 🚀 The easiest way for your agents to generate images, videos, music, text-to-speech or use managed agents. A fast and efficient way to get access to all the goodness of the Gemini API. 🧵👇

Jack Wotherspoon

22,684 views • 11 days ago

Introducing GLM-5V-Turbo: Vision Coding Model - Native Multimodal Coding: Natively understands multimodal inputs including images, videos, design drafts, and document layouts. - Balanced Visual and Programming Capabilities: Achieves leading performance across core benchmarks for multimodal coding, tool use, and GUI Agents. - Deep Adaptation for Claude Code and Claw Scenarios: Works in deep synergy with Agents like Claude Code and OpenClaw. Try it now: API: Coding Plan trial applications:

Introducing GLM-5V-Turbo: Vision Coding Model - Native Multimodal Coding: Natively understands multimodal inputs including images, videos, design drafts, and document layouts. - Balanced Visual and Programming Capabilities: Achieves leading performance across core benchmarks for multimodal coding, tool use, and GUI Agents. - Deep Adaptation for Claude Code and Claw Scenarios: Works in deep synergy with Agents like Claude Code and OpenClaw. Try it now: API: Coding Plan trial applications:

Z.ai

1,971,041 views • 7 months ago

Train Once, Earn Limitless. Introducing Moonbase Your All-in-one AI Model Marketplace, only on FLock. Train AI models, create AI agents with standard API, and earn when AI agents use your models. Coming soon. Join the waitlist:

Train Once, Earn Limitless. Introducing Moonbase Your All-in-one AI Model Marketplace, only on FLock. Train AI models, create AI agents with standard API, and earn when AI agents use your models. Coming soon. Join the waitlist:

FLock.io

277,215 views • 1 year ago

Introducing Voxtral 3: state-of-the-art Transcribe and Speech models powering Mistral’s new voice agents API. 🧵

Introducing Voxtral 3: state-of-the-art Transcribe and Speech models powering Mistral’s new voice agents API. 🧵

Mistral AI

281,172 views • 13 days ago

introducing ghosthand it lets your agents use a real iPhone plugged into your Mac. for agents & humans the agent sees the screen over USB and taps, swipes and types over Bluetooth, so it can use any app on the phone, even the ones with no API try it at

introducing ghosthand it lets your agents use a real iPhone plugged into your Mac. for agents & humans the agent sees the screen over USB and taps, swipes and types over Bluetooth, so it can use any app on the phone, even the ones with no API try it at

Tommy D. Rossi

48,523 views • 7 days ago

Today we are launching Mireye (YCS26) with Y Combinator The easiest way to build agentic applications for the physical world. AI agents are starting to act in the real world, but they can't reliably understand it. Mireye is one API and MCP that connects agents to the physical world: data, enrichment, tools, and signals that power them to make decisions. One line of code to make your agents street smart.

Today we are launching Mireye (YCS26) with Y Combinator The easiest way to build agentic applications for the physical world. AI agents are starting to act in the real world, but they can't reliably understand it. Mireye is one API and MCP that connects agents to the physical world: data, enrichment, tools, and signals that power them to make decisions. One line of code to make your agents street smart.

Ansh

33,951 views • 3 months ago

Introducing /search - the simplest way for agents and devs to discover the web 👀 Our #1 most requested endpoint is finally here. Search the web AND scrape all results in an LLM-ready format with one API call. Now live on our API, MCP, and all integrations 🔥

Introducing /search - the simplest way for agents and devs to discover the web 👀 Our #1 most requested endpoint is finally here. Search the web AND scrape all results in an LLM-ready format with one API call. Now live on our API, MCP, and all integrations 🔥

Firecrawl

390,902 views • 1 year ago

Introducing Public Agents It’s the easiest way to share an agent you’ve built, or install one someone else made Teams are already using agents to: - audit and secure apps - run interviews/screen candidates - run operations for businesses - and 100+ examples Try it now for $0

Introducing Public Agents It’s the easiest way to share an agent you’ve built, or install one someone else made Teams are already using agents to: - audit and secure apps - run interviews/screen candidates - run operations for businesses - and 100+ examples Try it now for $0

Nebula

44,723 views • 6 months ago

Your agent should meet its adversary before it meets your customers or partners. Introducing Adversarial Agents: AI-powered mock users that try to break your agent by simulating hypothetical hostile scenarios to cover all possible 'unhappy' paths. Prompt injection. Topic derailing. Instruction overrides. Every angle that a bad actor or a frustrated caller might try or edge cases that may come up - test any and all possible scenarios before the agent goes live. Plus, get a full audit report measured against expected behavior showing exactly what held and what broke, with correction suggestions for each failure, so you can deploy with confidence. Red-team your AI agents before you ship them.

Your agent should meet its adversary before it meets your customers or partners. Introducing Adversarial Agents: AI-powered mock users that try to break your agent by simulating hypothetical hostile scenarios to cover all possible 'unhappy' paths. Prompt injection. Topic derailing. Instruction overrides. Every angle that a bad actor or a frustrated caller might try or edge cases that may come up - test any and all possible scenarios before the agent goes live. Plus, get a full audit report measured against expected behavior showing exactly what held and what broke, with correction suggestions for each failure, so you can deploy with confidence. Red-team your AI agents before you ship them.

HappyRobot

10,867 views • 4 months ago

introducing Pinterest in Krea Agent. now you can bring all your pins and boards into the tool and use them as context for your agents. try it now at krea . ai / agent

introducing Pinterest in Krea Agent. now you can bring all your pins and boards into the tool and use them as context for your agents. try it now at krea . ai / agent

Krea

15,409 views • 1 month ago

Introducing the Notion Skills API. Edit your team’s skills in Notion. Use them in ChatGPT, Claude, and all of your agents. Here’s what’s new:

Introducing the Notion Skills API. Edit your team’s skills in Notion. Use them in ChatGPT, Claude, and all of your agents. Here’s what’s new:

Notion

316,376 views • 1 month ago

Introducing Neural Interface on Chromia | Power to the Public A starting point for crypto and AI developers to build AI agents with their own onchain AI “Brain” 👇🧵

Introducing Neural Interface on Chromia | Power to the Public A starting point for crypto and AI developers to build AI agents with their own onchain AI “Brain” 👇🧵

superoo7

24,442 views • 1 year ago

Introducing container use for agents. Go from babysitting one agent at a time to enabling many agents to work safely and independently with your preferred stack.

Introducing container use for agents. Go from babysitting one agent at a time to enabling many agents to work safely and independently with your preferred stack.

Dagger

30,379 views • 1 year ago

TL;DR: We bring coding agents to the physical world. Introducing Thea, a harness for embodied agents: one agentic loop drives a robot the way it drives a coding agent — every capability is a callable tool, and long-horizon behavior emerges from composing them. ▶️ For example: "Grab me a water." 🧵 (1/5)

TL;DR: We bring coding agents to the physical world. Introducing Thea, a harness for embodied agents: one agentic loop drives a robot the way it drives a coding agent — every capability is a callable tool, and long-horizon behavior emerges from composing them. ▶️ For example: "Grab me a water." 🧵 (1/5)

Wentao Zhu

37,813 views • 2 months ago

What if robots, humans, and video models could all describe action in the same language? Introducing Hydra-0🐍: a generalist world model that represents robot actions as action flow. One interface. Many embodiments, tasks, and environments. 🧵1/7

What if robots, humans, and video models could all describe action in the same language? Introducing Hydra-0🐍: a generalist world model that represents robot actions as action flow. One interface. Many embodiments, tasks, and environments. 🧵1/7

Hongyu Li

82,800 views • 2 months ago

Agents are getting complex to manage: models, skills, automations, permissions, cloud environments, orchestration patterns... So, we built the Terraform for agents: one repository that configures all of your agents as code. The Warp Factories configuration spec defines: - Agents and orchestration: how work gets routed and which models agents use - Automations: the events and schedules that kick off work - Access and environments: repositories, secrets, MCP servers, and runners - Measurement: scorers and benchmarks for understanding and improving performance Because it’s all code, both engineers and agents can propose changes to the factory itself. That makes it possible to test new configurations, benchmark them, and even have your factory propose improvements as PRs.

Agents are getting complex to manage: models, skills, automations, permissions, cloud environments, orchestration patterns... So, we built the Terraform for agents: one repository that configures all of your agents as code. The Warp Factories configuration spec defines: - Agents and orchestration: how work gets routed and which models agents use - Automations: the events and schedules that kick off work - Access and environments: repositories, secrets, MCP servers, and runners - Measurement: scorers and benchmarks for understanding and improving performance Because it’s all code, both engineers and agents can propose changes to the factory itself. That makes it possible to test new configurations, benchmark them, and even have your factory propose improvements as PRs.

Warp

756,814 views • 1 month ago

We just killed every single web search API you're using. We are excited to announce our partnership with parse[dot]bot to let agents use any site on the internet via API. Parse turns any website into a typed API and Locus puts all of the endpoints on one prepaid balance with our other providers. Travel, e-commerce, finance and more. Turn on the ones you want, and let your agents or platform call them by use. Live now!

We just killed every single web search API you're using. We are excited to announce our partnership with parse[dot]bot to let agents use any site on the internet via API. Parse turns any website into a typed API and Locus puts all of the endpoints on one prepaid balance with our other providers. Travel, e-commerce, finance and more. Turn on the ones you want, and let your agents or platform call them by use. Live now!

cole

10,793 views • 2 months ago

Excited to introduce micro1 Cortex, a contextual evaluation, visibility, and improvement platform for enterprise AI agents. Foundational models are trained for general intelligence, but enterprises need agents that perform reliably inside their unique context: workflows, policies, data environments, and edge cases. Cortex brings trust to enterprise AI by leveraging domain experts and real-world scenarios for any use case to test, diagnose, and improve how agents behave in production.

Excited to introduce micro1 Cortex, a contextual evaluation, visibility, and improvement platform for enterprise AI agents. Foundational models are trained for general intelligence, but enterprises need agents that perform reliably inside their unique context: workflows, policies, data environments, and edge cases. Cortex brings trust to enterprise AI by leveraging domain experts and real-world scenarios for any use case to test, diagnose, and improve how agents behave in production.

Ali Ansari

118,934 views • 8 months ago

Introducing Cline Desktop - a native interface for working with open weights models. Use with ClinePass and all our free models like DeepSeek-V4.1-Flash, Musespark-1.3, or BYOK with any provider!

Introducing Cline Desktop - a native interface for working with open weights models. Use with ClinePass and all our free models like DeepSeek-V4.1-Flash, Musespark-1.3, or BYOK with any provider!

Cline

1,023,648 views • 1 month ago