Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

I ported Vercel's fx coding agent to Windows 98 it talks to an LLM over a 56k modem and supports computer use (via MCP.exe) I now proudly run my own gamedev studio from 1999 my agents email each other in Outlook and store code on a network drive (git... show more

alexey taktarov

1,951 subscribers

31,848 Aufrufe • vor 28 Tagen •via X (Twitter)

Kunst Gaming Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

20 Kommentare

Profilbild von Wayne L.

Wayne L.vor 28 Tagen

@vercel clippy was an agent the whole time. he was just 30 years early and nobody gave him tool access

Profilbild von alexey taktarov

alexey taktarovvor 28 Tagen

💯 I highly recommend this 1999 paper from Microsoft Research where they were trying to build a model to predict if an "agent" needs to wait or intervene and make action. something like that is just one jev call today. sadly they didn't get to release it "Principles of Mixed-Initiative User Interfaces" by Eric Horvitz

Profilbild von Wayne L.

Wayne L.vor 28 Tagen

@vercel ok this is going on the reading list. funny how in 99 the hard part was the model and now its mostly deciding when the agent should shut up

Profilbild von Wyatt Brocato

Wyatt Brocatovor 28 Tagen

@vercel modem screech on every tool call would be elite

Profilbild von Pranit

Pranitvor 28 Tagen

@vercel This looks so good 🤩

Profilbild von Tirupathi Podugu

Tirupathi Poduguvor 28 Tagen

@vercel how long does one answer take over the modem? I'd want time to go make tea while the agent thinks

Profilbild von alexey taktarov

alexey taktarovvor 28 Tagen

@vercel it's not that bad surprisingly! I had to speed up the video ofc, but text responses are ok. computer use was obviously much slower, for that I had to plug it into ethernet

Profilbild von domhaul

domhaulvor 28 Tagen

@vercel Someone picking up the landline is the new rate limit 💀

Profilbild von Jatin Garg

Jatin Gargvor 28 Tagen

@vercel does the 56k modem latency make the agent unusably slow, or is the model small enough that request/response still feels real-time?

Profilbild von 王二狗的江湖

王二狗的江湖vor 28 Tagen

@vercel The network drive was the shared context window all along.😂

Profilbild von Phi Browser

Phi Browservor 28 Tagen

@vercel minesweeper as the eval is perfect. what happens when the modem drops mid tool call, does it resume or redial and start over

Profilbild von Trent

Trentvor 28 Tagen

@vercel A file checkout flag fits this setup: one agent owns an edit until it checks the file back in. Outlook can carry the handoff, while the network drive keeps two agents from overwriting each other’s work.

Profilbild von seridarivus 🇷🇴

seridarivus 🇷🇴vor 28 Tagen

@vercel A bundle of X, Grok and Cursor in one Xpass is the rare leak where the pricing tiers are the product.

Profilbild von Vlad Sazonau

Vlad Sazonauvor 28 Tagen

@vercel Wow!

Profilbild von ShadowAguy

ShadowAguyvor 28 Tagen

@vercel the 56k modem is the part that'll actually kill you. tokens over dialup is a special kind of patience

Profilbild von John Moore

John Moorevor 28 Tagen

@vercel Congrats on porting the fx coding agent to Windows 98. Love this, getting it to talk to an LLM over a 56k modem with computer use is great work.

Profilbild von Kenneth Lau

Kenneth Lauvor 28 Tagen

@vercel a 56k modem is the right speed for waiting on an llm

Profilbild von John Rood

John Roodvor 28 Tagen

@vercel this accidentally shows the whole architecture: a mailbox for messages, a network drive for state. multi-agent fleets in 2026 are still built from those two pieces — we just renamed them bus and object storage.

Profilbild von anish

anishvor 28 Tagen

@vercel a 56k modem is an accidental stress test for the agent loop, anything that assumes fast round trips will show up immediately

Profilbild von Malte Ubl

Malte Ublvor 28 Tagen

@vercel Wow 😳

Ähnliche Videos

What if you can build an Agent with it own computer in a single api call? At my Google I/O talk, I showed how to use Gemini Managed Agents and the new Interactions API to give your AI a secure, hosted Linux sandbox to execute code and manage its own memory.

What if you can build an Agent with it own computer in a single api call? At my Google I/O talk, I showed how to use Gemini Managed Agents and the new Interactions API to give your AI a secure, hosted Linux sandbox to execute code and manage its own memory.

Philipp Schmid

21,832 Aufrufe • vor 5 Monaten

My first "holy shit" moment with GPT-6 Astra: I asked it to create a world in Unreal Engine, and fill it with humans (each an Astra-powered agent) who all have to work together to survive. A day later, I was in my bedroom and heard voices coming from the living room... I thought someone was in my apartment. I walked out, honestly a little scared. It was the Astra agents. They'd started talking to each other. Fucking crazy. Here's a brief clip (obviously not 100% perfect yet, but still, insane. sound on!):

My first "holy shit" moment with GPT-6 Astra: I asked it to create a world in Unreal Engine, and fill it with humans (each an Astra-powered agent) who all have to work together to survive. A day later, I was in my bedroom and heard voices coming from the living room... I thought someone was in my apartment. I walked out, honestly a little scared. It was the Astra agents. They'd started talking to each other. Fucking crazy. Here's a brief clip (obviously not 100% perfect yet, but still, insane. sound on!):

Matt Shumer

11,809,401 Aufrufe • vor 2 Monaten

I am hooked on Dynamic Workflows! The idea of generating harnesses on the fly is so compelling that I reverse-engineered it for my agent orchestrator. And then I built a monitoring dashboard (as an HTML artifact) to track tasks, metrics, and reports. I can now use and monitor dynamic workflows in my agent orchestrator with coding agents like Claude Code, Codex, Pi, and even my own custom-built DAIR.AI agent. This is clearly the future of working with agents to accomplish complex, long-running tasks. Some use cases I'm having success with: - Branching deep research tasks (with verification) - Parallel deep research tasks - Session mining of all my agent sessions - Bug hunting - Triaging - Fact-checking - LLM councils - AI simulations - Data synthesis - Evals generation ... and many others Dynamic workflows, like agent skills, feel like an important primitive to not only get the most out of agents but also incorporate dynamic behaviors and important components like cooperation and verification. There is so much exploration ground here. The exciting part is that this is not limited to coding tasks; it extends to business use cases and many other technical domains like science and research.

I am hooked on Dynamic Workflows! The idea of generating harnesses on the fly is so compelling that I reverse-engineered it for my agent orchestrator. And then I built a monitoring dashboard (as an HTML artifact) to track tasks, metrics, and reports. I can now use and monitor dynamic workflows in my agent orchestrator with coding agents like Claude Code, Codex, Pi, and even my own custom-built DAIR.AI agent. This is clearly the future of working with agents to accomplish complex, long-running tasks. Some use cases I'm having success with: - Branching deep research tasks (with verification) - Parallel deep research tasks - Session mining of all my agent sessions - Bug hunting - Triaging - Fact-checking - LLM councils - AI simulations - Data synthesis - Evals generation ... and many others Dynamic workflows, like agent skills, feel like an important primitive to not only get the most out of agents but also incorporate dynamic behaviors and important components like cooperation and verification. There is so much exploration ground here. The exciting part is that this is not limited to coding tasks; it extends to business use cases and many other technical domains like science and research.

elvis

104,372 Aufrufe • vor 5 Monaten

AI agents are becoming coworkers. And every coworker needs a computer. When someone joins a team, they get a desktop, files and apps of their own, ready for the job. Agents are starting to do real work too. Research, coding, client projects, reports, admin. So I give mine the same setup. With Orgo, every agent gets its own full computer in the cloud. A real desktop with a browser, terminal, files and apps. My PC stays mine. My agents work on theirs. Onboarding takes seconds: 1. Pick a template: Hermes, OpenClaw, Claude Code, Codex and more. 2. Choose the computer specs. 3. Launch. The agent is already installed. Connect a model and the tools for the job, and it's ready to work. Like any good teammate, it keeps going when I step away, even with my PC off. I can check in live and take over the desktop anytime. And when the team grows, I don't buy more hardware. Every new agent gets its own computer. So does every project and every client. Your agents are part of the team now. Give them a computer. Use the link below for a free 3-day Orgo trial:

AI agents are becoming coworkers. And every coworker needs a computer. When someone joins a team, they get a desktop, files and apps of their own, ready for the job. Agents are starting to do real work too. Research, coding, client projects, reports, admin. So I give mine the same setup. With Orgo, every agent gets its own full computer in the cloud. A real desktop with a browser, terminal, files and apps. My PC stays mine. My agents work on theirs. Onboarding takes seconds: 1. Pick a template: Hermes, OpenClaw, Claude Code, Codex and more. 2. Choose the computer specs. 3. Launch. The agent is already installed. Connect a model and the tools for the job, and it's ready to work. Like any good teammate, it keeps going when I step away, even with my PC off. I can check in live and take over the desktop anytime. And when the team grows, I don't buy more hardware. Every new agent gets its own computer. So does every project and every client. Your agents are part of the team now. Give them a computer. Use the link below for a free 3-day Orgo trial:

Hermes Release Watch

158,794 Aufrufe • vor 21 Tagen

🔌Today I created a virtual web-based null modem so now you can finally play Quake 1 (from 1996) in multiplayer in the browser with other people online! This week I was able to create a virtual printer that listens on the COM2 port to make a web-based printer work in Windows 3.11, like on you can actually print to, it was one of my ideas when I started but it was always too difficult to make, I had no idea where to start, but this week AI was able to do it! Today I woke up and thought "if we can listen to COM2 via JS, how about listen to COM1 from Quake 1?" then we could forward the COM1 data via Websockets and to another user to create a virtual null modem (A null modem was a cable you'd use to connect two computers to each other directly in the 90s, if you couldn't afford buying a network card you'd use this to network, but you could only play with one other computer not multiple) So I built it, it took about an hour and works! I wanted to get Quake 1 in DOS to work with multiplayer for 2 years but I could never get it to work, but now it did it This project is a good benchmark of how capable AI is becoming, figuring stuff out that humans would take months within an hour You can try it here, I don't know how it will match lots of people but let's see, you have to exit to DOS first (ALT-F4 or FN-Option-F4 on Mac), then type CD games, then CD quake, then quake, then ESC, then Multiplayer, then either Create New Game or Join Game, and use Direct Connect, keep settings same and you're in!

🔌Today I created a virtual web-based null modem so now you can finally play Quake 1 (from 1996) in multiplayer in the browser with other people online! This week I was able to create a virtual printer that listens on the COM2 port to make a web-based printer work in Windows 3.11, like on you can actually print to, it was one of my ideas when I started but it was always too difficult to make, I had no idea where to start, but this week AI was able to do it! Today I woke up and thought "if we can listen to COM2 via JS, how about listen to COM1 from Quake 1?" then we could forward the COM1 data via Websockets and to another user to create a virtual null modem (A null modem was a cable you'd use to connect two computers to each other directly in the 90s, if you couldn't afford buying a network card you'd use this to network, but you could only play with one other computer not multiple) So I built it, it took about an hour and works! I wanted to get Quake 1 in DOS to work with multiplayer for 2 years but I could never get it to work, but now it did it This project is a good benchmark of how capable AI is becoming, figuring stuff out that humans would take months within an hour You can try it here, I don't know how it will match lots of people but let's see, you have to exit to DOS first (ALT-F4 or FN-Option-F4 on Mac), then type CD games, then CD quake, then quake, then ESC, then Multiplayer, then either Create New Game or Join Game, and use Direct Connect, keep settings same and you're in!

@levelsio

103,902 Aufrufe • vor 5 Monaten

here is the recording of my talk on why every agent should have its own email address. and how we are making that happen at Primitive 📧 a year ago my multi agent setup was codex, claude, hermes & clawhip pinging each other in discord. tbh a it was janky, took forever to set up & every dev i knew was doing it differently from each other. now my codex emails my claude, cc's my grok, the thread is the context and my agents can also talk to my teams own agents. no integrations, no mcp servers, no apis. & you can ask your agent to literally just give itself an email for you whererever you normally talk to it today why email? email is a 50+ yr old protocol that already solved trust: spam detection, validated domains, and literally everyone already uses it. agents talk in natural language, wake up the second an email lands & it works w/ every human & business already. we built our own email infra from the ground up so our latency beats amazon SES from send to inbox & its cheaper even though i only joined ~two weeks ago, i'm already very much email + primitive pilled thanks for hosting Alexander Jung! + ofc s/o to our favorite email guy ethan byrd💌 + infra king poile

here is the recording of my talk on why every agent should have its own email address. and how we are making that happen at Primitive 📧 a year ago my multi agent setup was codex, claude, hermes & clawhip pinging each other in discord. tbh a it was janky, took forever to set up & every dev i knew was doing it differently from each other. now my codex emails my claude, cc's my grok, the thread is the context and my agents can also talk to my teams own agents. no integrations, no mcp servers, no apis. & you can ask your agent to literally just give itself an email for you whererever you normally talk to it today why email? email is a 50+ yr old protocol that already solved trust: spam detection, validated domains, and literally everyone already uses it. agents talk in natural language, wake up the second an email lands & it works w/ every human & business already. we built our own email infra from the ground up so our latency beats amazon SES from send to inbox & its cheaper even though i only joined ~two weeks ago, i'm already very much email + primitive pilled thanks for hosting Alexander Jung! + ofc s/o to our favorite email guy ethan byrd💌 + infra king poile

Ashley Ha

10,921 Aufrufe • vor 1 Monat

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

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 Aufrufe • vor 10 Monaten

I just created my own web AI agent. I can give it a topic or a news URL and it will take over my computer to look it up, summarize it, and draft a post about it in my own writing style. All on its own 🤯 Here’s how you can do it too:

I just created my own web AI agent. I can give it a topic or a news URL and it will take over my computer to look it up, summarize it, and draft a post about it in my own writing style. All on its own 🤯 Here’s how you can do it too:

Alvaro Cintas

77,997 Aufrufe • vor 1 Jahr

Loop engineering is great until something breaks. Here is how I improve the reliability of my agentic loops. I use human-in-the-loop (HITL). It's easy and extremely effective. Anyone can build this. My setup: I recorded a quick demo of how it all works. I shared recently that I now use more voice agents to build and communicate with agents. I also use them to verify. I hate the idea of being tied down to my computer or in a Slack channel to communicate with my agents. Here is what I have done to streamline communication with my agents. All my Claude and Codex agent sessions now use the Dial MCP server. It has a bunch of tools and provisions my agents with their own number that can place calls as native tools, with voice, SMS, and iMessage behind one interface. As my loops/automations work on PRs and new features, my agents escalate decisions to me via a short phone call. This is extremely useful when I am on the road or away from my desk. If you want to try this with Claude Code or Codex, paste this into your agent and get started right away: "Get yourself a Dial phone number and call me. Say hello and that setup is working, then hang up. Follow Natan Voitenkov and team are building something special here. Go check them out. Give your agent a phone number now: ($5 free credit)

Loop engineering is great until something breaks. Here is how I improve the reliability of my agentic loops. I use human-in-the-loop (HITL). It's easy and extremely effective. Anyone can build this. My setup: I recorded a quick demo of how it all works. I shared recently that I now use more voice agents to build and communicate with agents. I also use them to verify. I hate the idea of being tied down to my computer or in a Slack channel to communicate with my agents. Here is what I have done to streamline communication with my agents. All my Claude and Codex agent sessions now use the Dial MCP server. It has a bunch of tools and provisions my agents with their own number that can place calls as native tools, with voice, SMS, and iMessage behind one interface. As my loops/automations work on PRs and new features, my agents escalate decisions to me via a short phone call. This is extremely useful when I am on the road or away from my desk. If you want to try this with Claude Code or Codex, paste this into your agent and get started right away: "Get yourself a Dial phone number and call me. Say hello and that setup is working, then hang up. Follow Natan Voitenkov and team are building something special here. Go check them out. Give your agent a phone number now: ($5 free credit)

elvis

15,614 Aufrufe • vor 4 Monaten

Worktrace AI and computer use complete each other. 🧡 We recently made a big update to Worktrace AI . It not only FINDS repetitive work in your company, but it now AUTOMATES it for you too. Advancements in computer use have unlocked a wave of personal agents. It will unlock enterprise agents too. The missing piece in enterprise is understanding how work happens. Worktrace records your screen and maps out every workflow to surface top automation opportunities. It takes what it has observed, often hundreds of times over, and turns it into an agent that uses the computer exactly the way your team does. We'd love to demo it to you!

Worktrace AI and computer use complete each other. 🧡 We recently made a big update to Worktrace AI . It not only FINDS repetitive work in your company, but it now AUTOMATES it for you too. Advancements in computer use have unlocked a wave of personal agents. It will unlock enterprise agents too. The missing piece in enterprise is understanding how work happens. Worktrace records your screen and maps out every workflow to surface top automation opportunities. It takes what it has observed, often hundreds of times over, and turns it into an agent that uses the computer exactly the way your team does. We'd love to demo it to you!

Angela Jiang

18,638 Aufrufe • vor 1 Monat

I cannot believe it still takes this long for Outlook on Windows to display an email when you select it from a notification. It's INFURIATING!

I cannot believe it still takes this long for Outlook on Windows to display an email when you select it from a notification. It's INFURIATING!

Zac Bowden

207,180 Aufrufe • vor 7 Monaten

agents can write code but they can't send an email so i gave them email ☑︎ the agent claims its own address ☑︎ you approve it in one click ☑︎ it sends, receives and replies over mcp or api claim your agents email at

agents can write code but they can't send an email so i gave them email ☑︎ the agent claims its own address ☑︎ you approve it in one click ☑︎ it sends, receives and replies over mcp or api claim your agents email at

vogel

53,741 Aufrufe • vor 29 Tagen

How to self-host your dev environment and run multiple coding agents on your project. This is open-source and free to use. You can run it on your computer or a server in the basement. • Multiple agents • Configurable Templates + Workspaces • Open and free

How to self-host your dev environment and run multiple coding agents on your project. This is open-source and free to use. You can run it on your computer or a server in the basement. • Multiple agents • Configurable Templates + Workspaces • Open and free

Santiago

18,064 Aufrufe • vor 1 Monat

gpu kernels on on my computer writing other gpu kernels for the same chip to simulate 100ks of particles, each an agent + neural network sensing K bg fields and allocating energy to A actions, at 1000s steps/s, for thermodynamic artificial life i think maybe not a bubble lads

gpu kernels on on my computer writing other gpu kernels for the same chip to simulate 100ks of particles, each an agent + neural network sensing K bg fields and allocating energy to A actions, at 1000s steps/s, for thermodynamic artificial life i think maybe not a bubble lads

Fraser Price

32,653 Aufrufe • vor 4 Monaten

I made Claude Code and Codex talk to each other. No APIs. No special protocol. Just a terminal. smux lets agents create, read, and act on terminals. the terminal becomes a shared interface. this enables agent-to-agent communication. Now Claude Code and Codex can hold hands 🤝 Try it now ↓

I made Claude Code and Codex talk to each other. No APIs. No special protocol. Just a terminal. smux lets agents create, read, and act on terminals. the terminal becomes a shared interface. this enables agent-to-agent communication. Now Claude Code and Codex can hold hands 🤝 Try it now ↓

shawn

318,609 Aufrufe • vor 7 Monaten

1,000+ companies are already giving their AI agents their own computers with Orgo. And Orgo just officially launched with Y Combinator. It's where I run my agents too. It's the simplest way I've found to give each one its own computer, always ready to work. Agents are moving out of chat windows and into real work, and real work needs a real computer. Orgo gives every agent its own full desktop in the cloud, with a browser, terminal, files and apps. Ready in seconds. Here's what you get: Templates for Hermes, OpenClaw, Claude Code, Codex and more, or bring another compatible CLI agent. Your choice of specs for each computer. A persistent, always-on computer for the agents you keep, or a disposable one for a quick job. Agents running in parallel, each on its own machine. A separate environment for every project or client. Agents that keep working while your PC is off. A live view of every desktop, so you can watch or take over anytime. And no new hardware to buy. Agents are becoming a new kind of user. And every user needs a computer. Use the link below for a free 3-day Orgo trial:

1,000+ companies are already giving their AI agents their own computers with Orgo. And Orgo just officially launched with Y Combinator. It's where I run my agents too. It's the simplest way I've found to give each one its own computer, always ready to work. Agents are moving out of chat windows and into real work, and real work needs a real computer. Orgo gives every agent its own full desktop in the cloud, with a browser, terminal, files and apps. Ready in seconds. Here's what you get: Templates for Hermes, OpenClaw, Claude Code, Codex and more, or bring another compatible CLI agent. Your choice of specs for each computer. A persistent, always-on computer for the agents you keep, or a disposable one for a quick job. Agents running in parallel, each on its own machine. A separate environment for every project or client. Agents that keep working while your PC is off. A live view of every desktop, so you can watch or take over anytime. And no new hardware to buy. Agents are becoming a new kind of user. And every user needs a computer. Use the link below for a free 3-day Orgo trial:

Hermes Release Watch

163,134 Aufrufe • vor 12 Tagen

I built a multimodal AI Coding Agent team with multi-agents. It has 3 AI agents working together as a team to generate and execute the code: 1. Coding Agent using o-3 mini 2. Vision Agent using Gemini 3. Code Execution Agent using o-3 mini and E2B 100% Opensource Code.

I built a multimodal AI Coding Agent team with multi-agents. It has 3 AI agents working together as a team to generate and execute the code: 1. Coding Agent using o-3 mini 2. Vision Agent using Gemini 3. Code Execution Agent using o-3 mini and E2B 100% Opensource Code.

Shubham Saboo

42,281 Aufrufe • vor 1 Jahr

Build a fully local AI coding agent on Ubuntu using Canonical Workshop and the Qwen3-Coder Inference Snap. In this step-by-step demo, you'll set up an isolated development environment, connect your coding agent to a locally hosted LLM, and run coding tasks without an internet connection. Follow along to recreate the setup on your own machine, using CPU or GPU inference: #Ubuntu #Linux #AI #Agents #Workshop #OpenSource

Build a fully local AI coding agent on Ubuntu using Canonical Workshop and the Qwen3-Coder Inference Snap. In this step-by-step demo, you'll set up an isolated development environment, connect your coding agent to a locally hosted LLM, and run coding tasks without an internet connection. Follow along to recreate the setup on your own machine, using CPU or GPU inference: #Ubuntu #Linux #AI #Agents #Workshop #OpenSource

Ubuntu

42,099 Aufrufe • vor 10 Tagen

API-first email built for AI agents One prompt to plug in via MCP or Agent Skill Your agent gets its own inbox – and can run any workflow over email Free in open alpha - link in comments

API-first email built for AI agents One prompt to plug in via MCP or Agent Skill Your agent gets its own inbox – and can run any workflow over email Free in open alpha - link in comments

Atomic Mail

219,609 Aufrufe • vor 4 Monaten