Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

We shipped an OSS 'vibe coding platform' (like v0) built with Vercel AI SDK, Gateway and Sandbox. We worked with @openai to tune the GPT-5 agent loop. It can write/read files, run commands, install packages, autofix errors… Demo oneshotting a multiplayer Pong in Go ↓

rauchg's profile picture

Guillermo Rauch

853,321 subscribers

794,422 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Check out the OSS Coding Agent template, powered by AI SDK, Vercel AI Gateway and Sandbox. We now have open source, BYO-model versions of both v0 and Vercel Agent 😲
0:25

Check out the OSS Coding Agent template, powered by AI SDK, Vercel AI Gateway and Sandbox. We now have open source, BYO-model versions of both v0 and Vercel Agent 😲

Guillermo Rauch

65,851 Aufrufe • vor 1 Jahr

v0 can now run terminal commands, which means it can: • Spin up a browser session to test interactions • Look through your commit history to understand past changes • Write and run unit tests • Use CLIs to interact with platforms like Vercel and GitHub
0:31

v0 can now run terminal commands, which means it can: • Spin up a browser session to test interactions • Look through your commit history to understand past changes • Write and run unit tests • Use CLIs to interact with platforms like Vercel and GitHub

v0

30,445 Aufrufe • vor 4 Monaten

$ aix built a CLI with AI SDK/Vercel AI Gateway ▪️ Thinking text animation in ANSI ✨ ▪️ Set `AI_GATEWAY_API_KEY` and works ▪️ 100s of models (e.g.: `-m openai/gpt-4o`) It's like a mini-`claude`, purpose built for quickly running commands. Has some nice safety measures built-in. Used this as my learning exercise for the AI Gateway, which was absolutely delightful… I'm a fan 😁
0:52

$ aix built a CLI with AI SDK/Vercel AI Gateway ▪️ Thinking text animation in ANSI ✨ ▪️ Set `AI_GATEWAY_API_KEY` and works ▪️ 100s of models (e.g.: `-m openai/gpt-4o`) It's like a mini-`claude`, purpose built for quickly running commands. Has some nice safety measures built-in. Used this as my learning exercise for the AI Gateway, which was absolutely delightful… I'm a fan 😁

Guillermo Rauch

53,688 Aufrufe • vor 1 Jahr

We built MiniMax a CLI coding agent like Claude Code, powered by MiniMax M3. It can: → Read files → Write code → Run shell commands autonomously → Understand large codebases with long-context reasoning → Handle real multi-file engineering tasks → Work entirely inside your terminal And it's fully hackable. Swap prompts. Add tools. Customize workflows. Make it your own. No GUI. Just code. Built for developers who live in the terminal.
1:07

We built MiniMax a CLI coding agent like Claude Code, powered by MiniMax M3. It can: → Read files → Write code → Run shell commands autonomously → Understand large codebases with long-context reasoning → Handle real multi-file engineering tasks → Work entirely inside your terminal And it's fully hackable. Swap prompts. Add tools. Customize workflows. Make it your own. No GUI. Just code. Built for developers who live in the terminal.

Darshal Jaitwar

18,861 Aufrufe • vor 3 Monaten

Introducing DeepSeek based AI Agents! We built an Executive AI Assistant that can, - Listen to incoming emails - Fetch all your unread emails and summarize the important ones - Draft and Send reply emails Connect with Gmail, Calendar, Slack and more with Frontend designed with Vercel v0 Use Deepseek and other LLMs with Groq Inc with AI SDK code:
0:40

Introducing DeepSeek based AI Agents! We built an Executive AI Assistant that can, - Listen to incoming emails - Fetch all your unread emails and summarize the important ones - Draft and Send reply emails Connect with Gmail, Calendar, Slack and more with Frontend designed with Vercel v0 Use Deepseek and other LLMs with Groq Inc with AI SDK code:

Karan Vaidya

81,149 Aufrufe • vor 1 Jahr

We worked with OpenAI to build a native integration for the OpenAI Agents SDK. Today, we are very excited to launch as a tracing processor. With just a few lines of code, you can trace all your agent workflows and debug them much faster. Check out this quick demo to get started:
0:49

We worked with OpenAI to build a native integration for the OpenAI Agents SDK. Today, we are very excited to launch as a tracing processor. With just a few lines of code, you can trace all your agent workflows and debug them much faster. Check out this quick demo to get started:

Respan

58,163 Aufrufe • vor 1 Jahr

Here is the tutorial of how I vibe coded Remy's Kitchen, an app where you upload a picture of your fridge and it gives you recipe suggestions of what to cook! Here is what I used to build this: - v0 -Supabase -OpenAI GPT-4o mini -Grok -Google AI Mixboard - Vercel AI Gateway
14:07

Here is the tutorial of how I vibe coded Remy's Kitchen, an app where you upload a picture of your fridge and it gives you recipe suggestions of what to cook! Here is what I used to build this: - v0 -Supabase -OpenAI GPT-4o mini -Grok -Google AI Mixboard - Vercel AI Gateway

Safinaz Elhadary

38,459 Aufrufe • vor 10 Monaten

We worked with Ginkgo Bioworks to connect GPT-5 to an autonomous lab, so it could propose experiments, run them at scale, learn from the results, and decide what to try next. That closed loop brought protein production cost down by 40%.
0:21

We worked with Ginkgo Bioworks to connect GPT-5 to an autonomous lab, so it could propose experiments, run them at scale, learn from the results, and decide what to try next. That closed loop brought protein production cost down by 40%.

OpenAI

3,155,750 Aufrufe • vor 7 Monaten

Errors!! That's the most stressful part about AI coding We lose 40% credits in debugging code We tried to solve it with CodeGuide Debug Agent Just screenshot your error message and upload/paste it The Agent will write a detailed debug prompt Copy & paste it. Error solved.
0:43

Errors!! That's the most stressful part about AI coding We lose 40% credits in debugging code We tried to solve it with CodeGuide Debug Agent Just screenshot your error message and upload/paste it The Agent will write a detailed debug prompt Copy & paste it. Error solved.

CJ Zafir

12,554 Aufrufe • vor 1 Jahr

You wanted shadcn — so we built the heinous infra to make it work. Introducing Agent Arena, starting with the best: Claude Code by Anthropic Codex 5 by OpenAI Cursor Agent by Cursor Devin by Cognition Gemini CLI by Google DeepMind Grok Code Fast 1 by xAI 1/ Your prompt launches a containerized agent inside a fresh GitHub repo 2/ The agent can install packages, make tool calls, and write multi-file code 3/ The repo is deployed to Vercel *by the agent*, clonable to your heart's desire
0:25

You wanted shadcn — so we built the heinous infra to make it work. Introducing Agent Arena, starting with the best: Claude Code by Anthropic Codex 5 by OpenAI Cursor Agent by Cursor Devin by Cognition Gemini CLI by Google DeepMind Grok Code Fast 1 by xAI 1/ Your prompt launches a containerized agent inside a fresh GitHub repo 2/ The agent can install packages, make tool calls, and write multi-file code 3/ The repo is deployed to Vercel *by the agent*, clonable to your heart's desire

Grace Li

169,041 Aufrufe • vor 11 Monaten

what happens if you let a crowd control what gets built, and let an ai handle how it’s built? i built vibe arena - twitch plays pokemon, but for actual software - in 2 hours using Convex, Modal and Cursor's sdk a real-time multiplayer coding arena where people submit commands and an ai agent executes the winning move live - powered by cursor's composer-1 model. demo and notes below: eric zakariasson Lee Robinson Wayne Sutton Akshat Bubna
3:08

what happens if you let a crowd control what gets built, and let an ai handle how it’s built? i built vibe arena - twitch plays pokemon, but for actual software - in 2 hours using Convex, Modal and Cursor's sdk a real-time multiplayer coding arena where people submit commands and an ai agent executes the winning move live - powered by cursor's composer-1 model. demo and notes below: eric zakariasson Lee Robinson Wayne Sutton Akshat Bubna

agrim singh

19,568 Aufrufe • vor 8 Monaten

Introducing Based Agent: create AI agents with full onchain functionality on Base in less than 3 minutes. The era of Autonomous Onchain Agents is here Built with Coinbase Developer Platform🛡️ SDK, OpenAI , and Replit ⠕ oh, and you can make it an X bot too 😉
1:04

Introducing Based Agent: create AI agents with full onchain functionality on Base in less than 3 minutes. The era of Autonomous Onchain Agents is here Built with Coinbase Developer Platform🛡️ SDK, OpenAI , and Replit ⠕ oh, and you can make it an X bot too 😉

lincoln.base.eth

731,758 Aufrufe • vor 1 Jahr

Create an AI Agent with a crypto wallet and onchain functionality in less than 5 minutes with Coinbase Developer Platform🛡️ SDK, OpenAI Swarm, and Cursor There is limitless potential for these agents and their integrations. Leave your ETH Address/Basename in a reply for the next demo 👀
3:29

Create an AI Agent with a crypto wallet and onchain functionality in less than 5 minutes with Coinbase Developer Platform🛡️ SDK, OpenAI Swarm, and Cursor There is limitless potential for these agents and their integrations. Leave your ETH Address/Basename in a reply for the next demo 👀

lincoln.base.eth

31,755 Aufrufe • vor 1 Jahr

🔗 Announcing LangChain OSS Skills LangChain has the most popular frameworks for building AI agents — and now your coding agent can be an expert in it. We're excited to release the first iteration of LangChain OSS Skills, giving your agent expertise in our open source frameworks. The skills include guidance on how to use langchain, langgraph, and deepagents to effectively build agents. ➡️ Install our OSS skills for your coding agent here: ➡️ Read more:
0:43

🔗 Announcing LangChain OSS Skills LangChain has the most popular frameworks for building AI agents — and now your coding agent can be an expert in it. We're excited to release the first iteration of LangChain OSS Skills, giving your agent expertise in our open source frameworks. The skills include guidance on how to use langchain, langgraph, and deepagents to effectively build agents. ➡️ Install our OSS skills for your coding agent here: ➡️ Read more:

LangChain OSS

65,840 Aufrufe • vor 6 Monaten

If you have an application using AI, you should try out Cloudflare AI Gateway. I'd say go into debt if you have to, but it's free. In a couple of minutes we add AI Gateway to an existing application that uses the OpenAI SDK. Check it out!
4:25

If you have an application using AI, you should try out Cloudflare AI Gateway. I'd say go into debt if you have to, but it's free. In a couple of minutes we add AI Gateway to an existing application that uses the OpenAI SDK. Check it out!

Jilles Soeters

24,238 Aufrufe • vor 4 Monaten

We just updated Junie and the Codex integration in JetBrains AI! Now you can use OpenAI GPT 5.5 in all JetBrains IDEs. We ran various tests with this model but have a look yourself at one of the demo projects we built (🔊 on)
0:46

We just updated Junie and the Codex integration in JetBrains AI! Now you can use OpenAI GPT 5.5 in all JetBrains IDEs. We ran various tests with this model but have a look yourself at one of the demo projects we built (🔊 on)

JetBrains

10,966 Aufrufe • vor 4 Monaten

putting the Claude Agent SDK to the test with an Ad Agent - finds competitors, learns from their ads - prompts and generates on brand creatives - packages it in a shareable report I can run this autonomously or with a prompt. no node based workflows needed
17:45

putting the Claude Agent SDK to the test with an Ad Agent - finds competitors, learns from their ads - prompts and generates on brand creatives - packages it in a shareable report I can run this autonomously or with a prompt. no node based workflows needed

The Boring Marketer

77,600 Aufrufe • vor 8 Monaten

Excited to release our agent team Magentic-One! Magentic-One can browse the web, files, write and execute code & supports a human-in-the-loop. Built by Microsoft Research AI Frontiers with @pyautogen. My favorite task:
1:07

Excited to release our agent team Magentic-One! Magentic-One can browse the web, files, write and execute code & supports a human-in-the-loop. Built by Microsoft Research AI Frontiers with @pyautogen. My favorite task:

Hussein Mozannar

164,311 Aufrufe • vor 1 Jahr