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.

I tried replicating fully agentic coding on my laptop and I'm impressed! My setup - Qwen 27bn (4bit quant) - Pi coding agent - CCO sandboxing for yolo mode My Mac M3 has 36GB ram. It's surreal to see a local model read prompt, follow it flawlessly and then... show more

Paras Chopra

235,130 subscribers

105,616 views • 1 month ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

i tested a fully local ai coding setup: gemma4 from Google DeepMind running through LM Studio, paired with pi which is a minimal open source coding harness this is part 1 of a two part series. here we cover the why and the complete hands-on setup 0:00 - Running a coding agent fully local 0:47 - Why Pi as the coding agent harness 1:39 - Why Gemma 4 and which variant to pick 2:44 - Architecture: Pi, LM Studio and Gemma 4 3:45 - LM Studio setup and model download 5:01 - Starting the local server 5:19 - API sanity check with curl 6:08 - Installing the Pi coding agent 6:20 - Configuring models.json for local models 8:20 - First run: selecting the model in Pi 8:58 - Fixing the context length error 10:16 - Testing the working setup 10:50 - What is coming in Part 2

i tested a fully local ai coding setup: gemma4 from Google DeepMind running through LM Studio, paired with pi which is a minimal open source coding harness this is part 1 of a two part series. here we cover the why and the complete hands-on setup 0:00 - Running a coding agent fully local 0:47 - Why Pi as the coding agent harness 1:39 - Why Gemma 4 and which variant to pick 2:44 - Architecture: Pi, LM Studio and Gemma 4 3:45 - LM Studio setup and model download 5:01 - Starting the local server 5:19 - API sanity check with curl 6:08 - Installing the Pi coding agent 6:20 - Configuring models.json for local models 8:20 - First run: selecting the model in Pi 8:58 - Fixing the context length error 10:16 - Testing the working setup 10:50 - What is coming in Part 2

Nidhi Singh

14,526 views • 7 days ago

i gave a 9B model an agentic OS and told it to build Octopus Invaders from scratch. Qwen 3.5 9B running through Hermes Agent with full tool access on a single 3060 12GB. browser, file system, code execution, terminal. it reads the prompt, plans the architecture, writes every file, and serves the game. one prompt, zero steering, 11 minutes. i've been going back and forth with this model for days now. text, code, reasoning. it handles small chats, batching, bash scripting. at 9B it's fast enough to feel interactive and genuinely useful for local workflows where you'd normally reach for an API. but this is the real test. can it architect and build a full game autonomously without a single correction? it's coding right now. results coming next.

i gave a 9B model an agentic OS and told it to build Octopus Invaders from scratch. Qwen 3.5 9B running through Hermes Agent with full tool access on a single 3060 12GB. browser, file system, code execution, terminal. it reads the prompt, plans the architecture, writes every file, and serves the game. one prompt, zero steering, 11 minutes. i've been going back and forth with this model for days now. text, code, reasoning. it handles small chats, batching, bash scripting. at 9B it's fast enough to feel interactive and genuinely useful for local workflows where you'd normally reach for an API. but this is the real test. can it architect and build a full game autonomously without a single correction? it's coding right now. results coming next.

Sudo su

65,570 views • 3 months ago

Last week I spent $20,000 on Mac Studios so I could run OpenClaw locally Fully powered by local AI models running 24/7 Now my agent: • Is doing tasks 24/7/365 • Doesn't cost any tokens • Is fully private In this video I cover how it works and how you can do the same thing:

Last week I spent $20,000 on Mac Studios so I could run OpenClaw locally Fully powered by local AI models running 24/7 Now my agent: • Is doing tasks 24/7/365 • Doesn't cost any tokens • Is fully private In this video I cover how it works and how you can do the same thing:

Alex Finn

572,826 views • 4 months ago

Same Prompt, 3 vibe coding Platforms Goal: To build a fully functional on-chain dApp Are we cooked enough chat?

Same Prompt, 3 vibe coding Platforms Goal: To build a fully functional on-chain dApp Are we cooked enough chat?

CodeXero (vibecode/acc)

304,396 views • 5 months ago

I've spent a lot of time customizing my Pi setup It's quickly become my favorite coding agent, u just need to make it yours Made a vid on how (TL;DR, just tell it to change itself and it will):

I've spent a lot of time customizing my Pi setup It's quickly become my favorite coding agent, u just need to make it yours Made a vid on how (TL;DR, just tell it to change itself and it will):

Ben Davis

31,208 views • 1 month ago

I just watched an AI agent operate my Mac like a real human. This AI agent responded to candidates' emails and scheduled Zoom meetings, all from a plain English prompt. Skip the Zapier spaghetti. This is agentic AI; you need to know about:

I just watched an AI agent operate my Mac like a real human. This AI agent responded to candidates' emails and scheduled Zoom meetings, all from a plain English prompt. Skip the Zapier spaghetti. This is agentic AI; you need to know about:

Shruti

36,489 views • 11 months ago

I gave PewDiePie's Odysseus agent access to my browser... I gave it the setup prompt for browser-harness. > Controls my existing Chrome via CDP > Found his latest video and commented for me > Self-hosted & privacy-first Fully open source. Try it now ↓

I gave PewDiePie's Odysseus agent access to my browser... I gave it the setup prompt for browser-harness. > Controls my existing Chrome via CDP > Found his latest video and commented for me > Self-hosted & privacy-first Fully open source. Try it now ↓

shawn

94,898 views • 16 days ago

I got a fully maxed out MacBook, mostly so I can run local models fast. And omg here is mixtral running on ollama... almost cannot believe how fast it is. This is with no internet!! A model that beats GPT-3.5 running locally! What!

I got a fully maxed out MacBook, mostly so I can run local models fast. And omg here is mixtral running on ollama... almost cannot believe how fast it is. This is with no internet!! A model that beats GPT-3.5 running locally! What!

Charlie Holtz

196,035 views • 2 years ago

Here’s how to use OpenAI’s new o1 pro model to maximize coding productivity. I’ve used this workflow for the last 48hrs and I estimate it has 2x’d my output. Watch the full 19min tutorial. Prompt below.

Here’s how to use OpenAI’s new o1 pro model to maximize coding productivity. I’ve used this workflow for the last 48hrs and I estimate it has 2x’d my output. Watch the full 19min tutorial. Prompt below.

Mckay Wrigley

488,711 views • 1 year ago

Qwen 3.6 35B running at over 100 tokens per second on my $5,399 MacBook Pro M5 Max. This is the best local AI model I have ever run. 128GB of unified memory. No cloud. No API costs. No rate limits. Just raw local inference at speeds I didn't think were possible on a laptop. This model is more intelligent than GPT 5 on benchmarks. Running locally. On a MacBook. For free after the hardware cost. I said local AI would never compete with frontier. I'm starting to rethink that. The gap is closing faster than anyone expected.

Qwen 3.6 35B running at over 100 tokens per second on my $5,399 MacBook Pro M5 Max. This is the best local AI model I have ever run. 128GB of unified memory. No cloud. No API costs. No rate limits. Just raw local inference at speeds I didn't think were possible on a laptop. This model is more intelligent than GPT 5 on benchmarks. Running locally. On a MacBook. For free after the hardware cost. I said local AI would never compete with frontier. I'm starting to rethink that. The gap is closing faster than anyone expected.

BridgeMind

62,211 views • 23 days ago

I took delivery of my new Tesla Model Y on Thursday. Today, I tried Full Self-Driving (FSD) and it FLAWLESSLY drove a 32 minute trip from my home to my kids' school. I am absolutely BLOWN AWAY. How long has this been possible and why isn't everyone talking about it?!

I took delivery of my new Tesla Model Y on Thursday. Today, I tried Full Self-Driving (FSD) and it FLAWLESSLY drove a 32 minute trip from my home to my kids' school. I am absolutely BLOWN AWAY. How long has this been possible and why isn't everyone talking about it?!

Matt Van Swol

2,895,307 views • 1 year ago

Andrej Karpathy: “Vibe coding is incredible. But agentic engineering is the next level. 90% of my coding routine is automated by AI agents.” In this 30-minute talk, Andrej Karpathy explains how to build an AI agent workflow from scratch. Worth more than 500$ agentic engineering course on the internet. Watch it today, then read the article below.

Andrej Karpathy: “Vibe coding is incredible. But agentic engineering is the next level. 90% of my coding routine is automated by AI agents.” In this 30-minute talk, Andrej Karpathy explains how to build an AI agent workflow from scratch. Worth more than 500$ agentic engineering course on the internet. Watch it today, then read the article below.

Movez

172,857 views • 10 days ago

Bolt built this entire landing page from a single prompt 🤯 No Figma. No coding. Just one prompt and a clear flow Want the exact prompt I used? RT and follow. I’ll DM you the link directly.

Bolt built this entire landing page from a single prompt 🤯 No Figma. No coding. Just one prompt and a clear flow Want the exact prompt I used? RT and follow. I’ll DM you the link directly.

Prajwal Tomar

63,407 views • 1 year ago

This actually makes Gemma 4 26B-4A usable for a coding agent @ 72tk/s on my MacBook Pro M1 Max. This video is realtime, running completely locally.

This actually makes Gemma 4 26B-4A usable for a coding agent @ 72tk/s on my MacBook Pro M1 Max. This video is realtime, running completely locally.

Kyle Howells

117,577 views • 6 days ago

HERMES AGENT + QWEN 3.6 IS CURRENTLY THE STRONGEST LOCAL SETUP MOST PEOPLE CAN RUN. Even if frontier models stopped improving tomorrow, this stack would still cover the majority of real work. Qwen 3.6 (72B and 235B) is officially supported in Hermes and brings: → Strong coding and complex refactoring → Reliable tool calling and multi-step execution → Excellent long context (128k–1M tokens) → Good structured reasoning with /goal workflows → Solid memory and session continuity Paired with Hermes memory, skills, Kanban, cron and tools — you get a fully private, self-improving agent that codes, automates and runs 24/7 without sending data anywhere. You don’t need the latest closed model to build something powerful. This is one of the strongest fully local stacks available right now — and it runs on real hardware.

HERMES AGENT + QWEN 3.6 IS CURRENTLY THE STRONGEST LOCAL SETUP MOST PEOPLE CAN RUN. Even if frontier models stopped improving tomorrow, this stack would still cover the majority of real work. Qwen 3.6 (72B and 235B) is officially supported in Hermes and brings: → Strong coding and complex refactoring → Reliable tool calling and multi-step execution → Excellent long context (128k–1M tokens) → Good structured reasoning with /goal workflows → Solid memory and session continuity Paired with Hermes memory, skills, Kanban, cron and tools — you get a fully private, self-improving agent that codes, automates and runs 24/7 without sending data anywhere. You don’t need the latest closed model to build something powerful. This is one of the strongest fully local stacks available right now — and it runs on real hardware.

YanXbt

53,033 views • 13 days ago

The ultimate form of agentic coding will not be the terminal. This is an experiment. An ADE (Agentic Coding Environment), designed from the ground up to work with agentic coding tools. Right now, this only supports Claude Code and runs on a Mac.

The ultimate form of agentic coding will not be the terminal. This is an experiment. An ADE (Agentic Coding Environment), designed from the ground up to work with agentic coding tools. Right now, this only supports Claude Code and runs on a Mac.

Santiago

40,126 views • 4 months ago

Saw this on Twitter somewhere and I had to recreate it. This is my coding happy place. 🪷

Saw this on Twitter somewhere and I had to recreate it. This is my coding happy place. 🪷

Koen van Gilst

4,638,996 views • 2 years ago

I spent today turning a blank Hermes install into a sovereign local agent on my RTX 5090. always-on, reachable over telegram, fully local. here's everything it can do. it runs Qwen3.6-27B on the 5090 and answers from my phone over telegram. ~~~ I first made it faster. switched to the MTP build for self-speculative decoding: 62 > 115 tokens/sec. ~~~ it now benchmarks models on command. I ask it to speed-test a gguf and it stops its own model server to free the gpu, runs llama-bench, renders a card, sends it to my phone, then restarts itself. it's never left offline. ~~~ it also knows me very well. I pointed it to my private HF repo where I store all my AI traces since I started using it. I created a local markdown memory vault, seeded from my own history, with semantic search over it. ~~~ the whole stack stays home: weights on disk, inference on the 5090, the agent in my pocket. here is the video it created to showcase everything it has now.

I spent today turning a blank Hermes install into a sovereign local agent on my RTX 5090. always-on, reachable over telegram, fully local. here's everything it can do. it runs Qwen3.6-27B on the 5090 and answers from my phone over telegram. ~ I first made it faster. switched to the MTP build for self-speculative decoding: 62 > 115 tokens/sec. ~ it now benchmarks models on command. I ask it to speed-test a gguf and it stops its own model server to free the gpu, runs llama-bench, renders a card, sends it to my phone, then restarts itself. it's never left offline. ~ it also knows me very well. I pointed it to my private HF repo where I store all my AI traces since I started using it. I created a local markdown memory vault, seeded from my own history, with semantic search over it. ~ the whole stack stays home: weights on disk, inference on the 5090, the agent in my pocket. here is the video it created to showcase everything it has now.

witcheer

14,947 views • 17 days ago

Let's be honest Claude Code was not working good with local LLMs. So, I Tried using OpenCode with LM Studio using Qwen 3.5 9B model on my RTX 5080 GPU. It's very usable and much faster than Claude Code. I'm actually planning to use this setup to build an entire vibe coded SaaS

Let's be honest Claude Code was not working good with local LLMs. So, I Tried using OpenCode with LM Studio using Qwen 3.5 9B model on my RTX 5080 GPU. It's very usable and much faster than Claude Code. I'm actually planning to use this setup to build an entire vibe coded SaaS

Tushar Verma

137,477 views • 3 months ago

Nothing beats open-source! We now have a fully open-source coding agent that can compete with any proprietary solution out there: • 500+ available models • It doesn't train on your code • It doesn't charge a penny for tokens • It's open. You can change if you want. Kilo Code is the #1 app on OpenRouter right now, and the community is releasing new features on GitHub at rocket speed (about 20 releases in the last 30 days). I installed it in Visual Studio Code, but you can install it in pretty much any IDE. I need to spend more time with it, but here is a very interesting design choice: Most coding agents support two modes: an "agentic" mode for writing code and an "ask" mode for talking to the model without making any changes. Kilo Code supports 5 different modes: 1. Architect mode - Research, design, and planning 2. Debug mode - Problem solving and troubleshooting 3. Code mode - To write code. 4. Ask mode - To talk to the model. 5. Orchestrator mode - Combine every agent to solve problems. On paper, I really like this. I'll need more time to try out the specialized agents and see whether niching becomes an advantage. Here is the link to the website: Thanks to the Kilo for partnering with me on this post.

Nothing beats open-source! We now have a fully open-source coding agent that can compete with any proprietary solution out there: • 500+ available models • It doesn't train on your code • It doesn't charge a penny for tokens • It's open. You can change if you want. Kilo Code is the #1 app on OpenRouter right now, and the community is releasing new features on GitHub at rocket speed (about 20 releases in the last 30 days). I installed it in Visual Studio Code, but you can install it in pretty much any IDE. I need to spend more time with it, but here is a very interesting design choice: Most coding agents support two modes: an "agentic" mode for writing code and an "ask" mode for talking to the model without making any changes. Kilo Code supports 5 different modes: 1. Architect mode - Research, design, and planning 2. Debug mode - Problem solving and troubleshooting 3. Code mode - To write code. 4. Ask mode - To talk to the model. 5. Orchestrator mode - Combine every agent to solve problems. On paper, I really like this. I'll need more time to try out the specialized agents and see whether niching becomes an advantage. Here is the link to the website: Thanks to the Kilo for partnering with me on this post.

Santiago

73,062 views • 7 months ago