Loading video...

Video Failed to Load

Go Home

i built a very fast, virtualized filesystem for ai agents built with Redis, Vercel AI SDK and just-bash agents can search and grep files really fast because it's all in redis memory

joshtriedcoding's profile picture

Josh tried coding

22,815 subscribers

72,964 views • 4 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

how I run Vercel AI SDK agents in a cloud sandbox agents have full filesystem, bash and git access takes 2 minutes
1:58

how I run Vercel AI SDK agents in a cloud sandbox agents have full filesystem, bash and git access takes 2 minutes

Josh tried coding

24,697 views • 4 months ago

i built a very fast virtual filesystem for ai agents NEW: it’s now fast af even on huge codebases i see a lot of potential for this 👀
1:43

i built a very fast virtual filesystem for ai agents NEW: it’s now fast af even on huge codebases i see a lot of potential for this 👀

Josh tried coding

39,582 views • 3 months ago

Agents, AI SDK, and the AI Cloud. Ship AI is here. Join us Oct 23. Live in SF and streaming online. The first developer event built for shipping AI at scale. Lock in →
0:24

Agents, AI SDK, and the AI Cloud. Ship AI is here. Join us Oct 23. Live in SF and streaming online. The first developer event built for shipping AI at scale. Lock in →

Vercel

540,816 views • 10 months ago

Big news: Upstash Redis Search is now generally available! 🎉 ◆ Superfast™ full-text search built in Rust ◆ Clean & 100% type-safe TypeScript APIs ◆ Works with any Upstash Redis database Add fast search to React, Next.js and more 👇
1:00

Big news: Upstash Redis Search is now generally available! 🎉 ◆ Superfast™ full-text search built in Rust ◆ Clean & 100% type-safe TypeScript APIs ◆ Works with any Upstash Redis database Add fast search to React, Next.js and more 👇

Upstash

35,985 views • 1 month ago

I built a Deep Research AI Agent team using OpenAI Agents SDK and Firecrawl. It combines multiple AI agents that can autonomously search the web, extract content, and generate detailed reports with enhanced analysis. 100% Opensource Code with step-by-step tutorials.
1:29

I built a Deep Research AI Agent team using OpenAI Agents SDK and Firecrawl. It combines multiple AI agents that can autonomously search the web, extract content, and generate detailed reports with enhanced analysis. 100% Opensource Code with step-by-step tutorials.

Shubham Saboo

50,831 views • 1 year ago

Bash is all you need! Which is why I'm introducing my holiday project: just-bash just-bash is a pretty complete implementation of bash in TypeScript designed to be used as a bash tool by AI agents. Because it turns out agents love exploring data via shell scripts, even beyond coding. It comes with grep, sed, awk and the 99th percentile features that an agent like Claude Code or Cursor would use. In fact, Claude Code can use it for secure bash execution. In the package - A bash-tool for AI SDK - A binary for use by yourself or your coding agents - An overlay filesystem to feed files to your agent securely - A Vercel Sandbox compatible API, so you can quickly upgrade to a real VM if you need to run binaries - An example AI agent that explores the just-bash code base using just-bash - I imported the Oils shell bash compatibility suite and just-bash passes a very good chunk What is interesting about this codebase: It was essentially entirely written by Opus 4.5. Coding agents love bash and they are good at reproducing it. They are also great at text-book recursive descent parsers and AST tweet-walk interpreters. That said, it is, like, a lot of code and I didn't read it all 😅. This is very much a hack, but it also seems to be _really_ useful. I haven't really found anything agents want to use that it doesn't support and it's fast and secure (caveats apply). It doesn't have write access to your computer and the filesystem is given a root that the agent cannot escape from. Find it at Related: Our recent blog post how we migrated our data analysis agent to bash tools and achieved incredible quality improvements The video shows the example agent investigating the just-bash code base
1:47

Bash is all you need! Which is why I'm introducing my holiday project: just-bash just-bash is a pretty complete implementation of bash in TypeScript designed to be used as a bash tool by AI agents. Because it turns out agents love exploring data via shell scripts, even beyond coding. It comes with grep, sed, awk and the 99th percentile features that an agent like Claude Code or Cursor would use. In fact, Claude Code can use it for secure bash execution. In the package - A bash-tool for AI SDK - A binary for use by yourself or your coding agents - An overlay filesystem to feed files to your agent securely - A Vercel Sandbox compatible API, so you can quickly upgrade to a real VM if you need to run binaries - An example AI agent that explores the just-bash code base using just-bash - I imported the Oils shell bash compatibility suite and just-bash passes a very good chunk What is interesting about this codebase: It was essentially entirely written by Opus 4.5. Coding agents love bash and they are good at reproducing it. They are also great at text-book recursive descent parsers and AST tweet-walk interpreters. That said, it is, like, a lot of code and I didn't read it all 😅. This is very much a hack, but it also seems to be _really_ useful. I haven't really found anything agents want to use that it doesn't support and it's fast and secure (caveats apply). It doesn't have write access to your computer and the filesystem is given a root that the agent cannot escape from. Find it at Related: Our recent blog post how we migrated our data analysis agent to bash tools and achieved incredible quality improvements The video shows the example agent investigating the just-bash code base

Malte Ubl

125,326 views • 7 months ago

👉👈 Say hello to Linear Coding Agent Built with @ActorCore_org Agents × Vercel AI SDK I couldn't wait for this launch, so I hacked together a little something in an evening. I honestly don't believe I could've ship it this fast without Actors. Source code below ⬇️
2:29

👉👈 Say hello to Linear Coding Agent Built with @ActorCore_org Agents × Vercel AI SDK I couldn't wait for this launch, so I hacked together a little something in an evening. I honestly don't believe I could've ship it this fast without Actors. Source code below ⬇️

Nathan Flurry 🔩

17,965 views • 1 year ago

I built the best memory for voice agents while sponsoring Y Combinator hackathon. Introducing: Voice AI + Memory! We built a deep supermemory integration for Pipecat AI, so now even your agents have great memory With user profiles, these are almost-instant latency as well :)
2:11

I built the best memory for voice agents while sponsoring Y Combinator hackathon. Introducing: Voice AI + Memory! We built a deep supermemory integration for Pipecat AI, so now even your agents have great memory With user profiles, these are almost-instant latency as well :)

Dhravya Shah

83,207 views • 5 months ago

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 views • 1 year ago

Voice agents, now on Vercel. Realtime, speech and transcription are now live on AI Gateway. Build with 𝚞𝚜𝚎𝚁𝚎𝚊𝚕𝚝𝚒𝚖𝚎, 𝚐𝚎𝚗𝚎𝚛𝚊𝚝𝚎𝚂𝚙𝚎𝚎𝚌𝚑 & 𝚝𝚛𝚊𝚗𝚜𝚌𝚛𝚒𝚋𝚎 on AI SDK 7.
0:57

Voice agents, now on Vercel. Realtime, speech and transcription are now live on AI Gateway. Build with 𝚞𝚜𝚎𝚁𝚎𝚊𝚕𝚝𝚒𝚖𝚎, 𝚐𝚎𝚗𝚎𝚛𝚊𝚝𝚎𝚂𝚙𝚎𝚎𝚌𝚑 & 𝚝𝚛𝚊𝚗𝚜𝚌𝚛𝚒𝚋𝚎 on AI SDK 7.

Vercel

653,710 views • 1 month ago

Agora is an AI-native ecommerce search engine that indexes over 200M products from Shopify & Woo. Built on Vercel — it's quite fast:
0:20

Agora is an AI-native ecommerce search engine that indexes over 200M products from Shopify & Woo. Built on Vercel — it's quite fast:

Guillermo Rauch

144,233 views • 1 year ago

Today CoPlane is releasing Localsandbox: a lightweight library to give your agents a sandboxed filesystem with safe bash and code execution. It's built on top of Turso's incredible AgentFS project, Vercel's just-bash library, and Pyodide. Try it out today! 👇
0:28

Today CoPlane is releasing Localsandbox: a lightweight library to give your agents a sandboxed filesystem with safe bash and code execution. It's built on top of Turso's incredible AgentFS project, Vercel's just-bash library, and Pyodide. Try it out today! 👇

Victor Mota

145,767 views • 6 months ago

Say goodbye to the ugly chat UI of your AI Agents! 👋 I've built a workflow with instructions to give all your n8n AI Agents a ChatGPT-like chat interface. Download the workflow, required files, and instructions for free (link in comment).
1:20

Say goodbye to the ugly chat UI of your AI Agents! 👋 I've built a workflow with instructions to give all your n8n AI Agents a ChatGPT-like chat interface. Download the workflow, required files, and instructions for free (link in comment).

Victor

27,101 views • 1 year ago

Introducing Upstash AI Agents! 🎉 ◆ Build production-ready AI workflows in minutes ◆ Specialize agents with tools (research, writing, analysis) ◆ Works with Vercel AI SDK, Langchain and more The best way to write AI agent workflows, fully customizable 👇🏻
1:57

Introducing Upstash AI Agents! 🎉 ◆ Build production-ready AI workflows in minutes ◆ Specialize agents with tools (research, writing, analysis) ◆ Works with Vercel AI SDK, Langchain and more The best way to write AI agent workflows, fully customizable 👇🏻

Upstash

39,117 views • 1 year ago

Just open sourced a template for using the new Grok Voice Agents in Expo ⬦ Dynamic Rive animations from Vercel AI Elements ⬦ AI SDK v7 and Tailwind ⬦ Custom Grok voices and personalities Source below ↓
0:34

Just open sourced a template for using the new Grok Voice Agents in Expo ⬦ Dynamic Rive animations from Vercel AI Elements ⬦ AI SDK v7 and Tailwind ⬦ Custom Grok voices and personalities Source below ↓

Evan Bacon 🥓

63,644 views • 1 month ago

Parallel Search + Extract tools in the @Vercel AI SDK make it easier than ever to give AI agents, apps, and workflows access to the most accurate and token-efficient web context. Here's our very own Manvesh demoing a simple implementation of the tools in an AI project.
2:06

Parallel Search + Extract tools in the @Vercel AI SDK make it easier than ever to give AI agents, apps, and workflows access to the most accurate and token-efficient web context. Here's our very own Manvesh demoing a simple implementation of the tools in an AI project.

Parallel Web Systems

21,913 views • 8 months ago

With the Agents SDK and @Vercel Sandbox, agents can execute work in isolated environments while keeping credentials separate from the harness.
1:02

With the Agents SDK and @Vercel Sandbox, agents can execute work in isolated environments while keeping credentials separate from the harness.

OpenAI Developers

49,642 views • 3 months ago

Meet your new teammates 🤝 AI agents like Wordsmith AI, Cursor, and Anthropic now work directly in Slack. They’re grounded in your real conversations, files, and context—all with enterprise-grade security built in.
0:20

Meet your new teammates 🤝 AI agents like Wordsmith AI, Cursor, and Anthropic now work directly in Slack. They’re grounded in your real conversations, files, and context—all with enterprise-grade security built in.

Slack

20,277 views • 5 months ago

Today, we’re launching the Parallel Search API, the most accurate web search for AI agents, built using our proprietary web index and retrieval infrastructure. Traditional search ranks URLs for humans to click. AI search needs something different: the right tokens in their context window. Parallel’s Search API is built from the ground up for AI agents, resulting in higher accuracy, lower costs, and lower latency for end-to-end agentic workflows.
1:20

Today, we’re launching the Parallel Search API, the most accurate web search for AI agents, built using our proprietary web index and retrieval infrastructure. Traditional search ranks URLs for humans to click. AI search needs something different: the right tokens in their context window. Parallel’s Search API is built from the ground up for AI agents, resulting in higher accuracy, lower costs, and lower latency for end-to-end agentic workflows.

Parallel Web Systems

669,725 views • 9 months ago