Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

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...

nidhisinghattri's profile picture

Nidhi Singh

5,040 subscribers

16,289 görüntüleme • 4 ay önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

The easiest way to run your agent harnesses using local models: Whether you're using Claude Code, Codex, OpenCode, or Pi, the local setup itself isn't really the hard part. The harder problem is figuring out which local model your machine can actually handle well. You have to think about RAM, model size, quantization, context length, KV cache, speed, accuracy, and a bunch of other trade-offs before you even start. Magnitude is an open-source solution that removes all of that guesswork for you. It profiles your machine, benchmarks what it can realistically run, recommends the best models for your hardware, and then lets you connect them to your preferred agent harness. The entire setup takes just two commands. In this video, I walk through the full process from hardware profiling to running a harness on a local model. Chapters: 00:00 Intro 00:17 What Magnitude is 00:45 Setup in two commands 01:29 Why picking a local model gets confusing fast 02:11 Hardware profiling + model recommendations 02:59 Choosing your harness 03:22 Connecting a harness that's already running 04:18 Outro Get started: (don't forget to star 🌟)
4:29

The easiest way to run your agent harnesses using local models: Whether you're using Claude Code, Codex, OpenCode, or Pi, the local setup itself isn't really the hard part. The harder problem is figuring out which local model your machine can actually handle well. You have to think about RAM, model size, quantization, context length, KV cache, speed, accuracy, and a bunch of other trade-offs before you even start. Magnitude is an open-source solution that removes all of that guesswork for you. It profiles your machine, benchmarks what it can realistically run, recommends the best models for your hardware, and then lets you connect them to your preferred agent harness. The entire setup takes just two commands. In this video, I walk through the full process from hardware profiling to running a harness on a local model. Chapters: 00:00 Intro 00:17 What Magnitude is 00:45 Setup in two commands 01:29 Why picking a local model gets confusing fast 02:11 Hardware profiling + model recommendations 02:59 Choosing your harness 03:22 Connecting a harness that's already running 04:18 Outro Get started: (don't forget to star 🌟)

Akshay 🚀

18,722 görüntüleme • 1 ay önce

People of pi. Welcome to the meta coding agent harness 0.50.0. npm install -g @mariozechner/pi-coding-agent - Bundle your extensions, skills, prompt templates, and skills as pi packages, distribute via NPM or git - Hot-reload everything via /reload A 🧵 of possibilities (1/x)
0:25

People of pi. Welcome to the meta coding agent harness 0.50.0. npm install -g @mariozechner/pi-coding-agent - Bundle your extensions, skills, prompt templates, and skills as pi packages, distribute via NPM or git - Hot-reload everything via /reload A 🧵 of possibilities (1/x)

Mario Zechner

36,105 görüntüleme • 9 ay önce

You can run a free and open-source alternative to Claude Code locally on your laptop! - Local AI model w/ Qwen3 Coder - Runs on your machine w/ LM Studio - Open-source VS Code extension w/ Cline Completely private (offline) and unlimited Setup and how it works: 00:00 Intro 01:11 LM Studio 02:10 Local AI model 03:38 Load the model 05:09 Start the server 05:33 Setup Cline 07:20 Prompt & example 09:02 Developer logs 10:12 Result reveal
11:34

You can run a free and open-source alternative to Claude Code locally on your laptop! - Local AI model w/ Qwen3 Coder - Runs on your machine w/ LM Studio - Open-source VS Code extension w/ Cline Completely private (offline) and unlimited Setup and how it works: 00:00 Intro 01:11 LM Studio 02:10 Local AI model 03:38 Load the model 05:09 Start the server 05:33 Setup Cline 07:20 Prompt & example 09:02 Developer logs 10:12 Result reveal

Paul Couvert

72,498 görüntüleme • 1 yıl önce

why Mario Zechner built an opinionated ai coding agent - the pi agent father pod
0:40

why Mario Zechner built an opinionated ai coding agent - the pi agent father pod

Mayank Gupta🧑🏻‍💻

30,578 görüntüleme • 7 ay önce

i tested Qwen3.8 27B locally on my M4 Pro to see how it behaves as a coding agent inside my project showing step-by-step the full guide on how you can run it, perfect for your first local model 00:00 Why I’m testing Qwen3.8 00:49 What Qwen3.8 includes 00:59 Qwen3.8 Max vs 27B 01:14 Qwen3.8 Max explained 02:13 Qwen’s benchmark claims 02:31 Its autonomous coding project 03:18 Qwen3.8 27B explained 04:30 Why I’m testing it locally 05:05 Download Qwen 3.8 in LM Studio 06:00 Pick the Q4 model 06:41 Run it as a local server 07:33 How fast is it? 08:36 Set up OpenCode 09:33 Connect LM Studio to OpenCode 10:03 Add Qwen 3.8 to OpenCode 11:34 Match the context settings 15:00 Give Qwen a real coding task 15:49 A mistake I caught live: session compaction 18:00 Review the code 19:30 My verdict
21:02

i tested Qwen3.8 27B locally on my M4 Pro to see how it behaves as a coding agent inside my project showing step-by-step the full guide on how you can run it, perfect for your first local model 00:00 Why I’m testing Qwen3.8 00:49 What Qwen3.8 includes 00:59 Qwen3.8 Max vs 27B 01:14 Qwen3.8 Max explained 02:13 Qwen’s benchmark claims 02:31 Its autonomous coding project 03:18 Qwen3.8 27B explained 04:30 Why I’m testing it locally 05:05 Download Qwen 3.8 in LM Studio 06:00 Pick the Q4 model 06:41 Run it as a local server 07:33 How fast is it? 08:36 Set up OpenCode 09:33 Connect LM Studio to OpenCode 10:03 Add Qwen 3.8 to OpenCode 11:34 Match the context settings 15:00 Give Qwen a real coding task 15:49 A mistake I caught live: session compaction 18:00 Review the code 19:30 My verdict

Nidhi Singh

43,169 görüntüleme • 2 ay önce

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 build a fully self-contained html/css page with zero errors. I got about ~20 tokens/second, and on this prompt quality similar to Haiku! But... this is running locally :)
0:43

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 build a fully self-contained html/css page with zero errors. I got about ~20 tokens/second, and on this prompt quality similar to Haiku! But... this is running locally :)

Paras Chopra

107,538 görüntüleme • 6 ay önce

Shopify CEO Tobi Lütke called Pi "the most interesting agent harness" - a tiny, open-source framework built by a single developer that powers OpenClaw and is changing how builders think about AI agents. In this clip, Dave Killeen (Field CPO at Pendo) breaks down why Pi matters, how it compares to Manus, and why the real magic in AI isn't the language model itself - it's the orchestration layer around it. Pi is a lightweight agent harness that lets developers build smarter AI experiences by leveraging models like Claude, GPT, and Gemini through better orchestration, not bigger models. If you're building AI products, coding agents, or exploring the new world of harness engineering, this is essential context. We discuss why Manus gave users a far better experience than talking directly to an LLM, and why open-source tools like Pi could be the future of agent development.
0:47

Shopify CEO Tobi Lütke called Pi "the most interesting agent harness" - a tiny, open-source framework built by a single developer that powers OpenClaw and is changing how builders think about AI agents. In this clip, Dave Killeen (Field CPO at Pendo) breaks down why Pi matters, how it compares to Manus, and why the real magic in AI isn't the language model itself - it's the orchestration layer around it. Pi is a lightweight agent harness that lets developers build smarter AI experiences by leveraging models like Claude, GPT, and Gemini through better orchestration, not bigger models. If you're building AI products, coding agents, or exploring the new world of harness engineering, this is essential context. We discuss why Manus gave users a far better experience than talking directly to an LLM, and why open-source tools like Pi could be the future of agent development.

Aakash Gupta

10,774 görüntüleme • 1 ay önce

I lied. pi 0.37.8 is my final holiday gift. npm install -g @mariozechner/pi-coding-agent git clone pi -r pi-doom /doom Enjoy DOOM in your coding harness* *terminals with Kitty keyboard protocol support only
1:10

I lied. pi 0.37.8 is my final holiday gift. npm install -g @mariozechner/pi-coding-agent git clone pi -r pi-doom /doom Enjoy DOOM in your coding harness* *terminals with Kitty keyboard protocol support only

Mario Zechner

11,234 görüntüleme • 10 ay önce

I burned a shitload of compute so you don't have to. Releasing the Harness Leaderboard. Which harness should you run your open model in? I ran 28,849 trials to find out. The leaderboard compares nine coding-agent harnesses on open models. In each comparison only the harness changes: the model, provider and reasoning effort stay fixed, and every task gets three attempts. The trials ran GLM-5.3-Flash, DeepSeek-V4.1-Flash and Flint on Terminal-Bench 2.1 and DeepSWE, for $4,746 of inference. Averaged over the three models, mini-swe-agent (Kilian Lieret), a bash-only agent, solves 51.4% of tasks and OpenClaw🦞 27.3%. Four others are statistically tied with mini-swe-agent. One of them is Pi (Pi), at 49.4% for $0.29 per solved task, about 45% less than mini-swe-agent's $0.53. The best harness depends on the model: mini-swe-agent on GLM-5.3-Flash, Hermes Agent (Nous Research) on DeepSeek-V4.1-Flash and Kimi Code (Kimi.ai) on Flint. OpenCode costs $3.35 per solved task, 11.7 times as much as Pi. See Harness Hub's Harness Lens for what the nine harnesses do differently. It documents the prompts, tools and compaction of 34 coding-agent harnesses and links every claim to its source. Leaderboard: Harness Lens:
0:29

I burned a shitload of compute so you don't have to. Releasing the Harness Leaderboard. Which harness should you run your open model in? I ran 28,849 trials to find out. The leaderboard compares nine coding-agent harnesses on open models. In each comparison only the harness changes: the model, provider and reasoning effort stay fixed, and every task gets three attempts. The trials ran GLM-5.3-Flash, DeepSeek-V4.1-Flash and Flint on Terminal-Bench 2.1 and DeepSWE, for $4,746 of inference. Averaged over the three models, mini-swe-agent (Kilian Lieret), a bash-only agent, solves 51.4% of tasks and OpenClaw🦞 27.3%. Four others are statistically tied with mini-swe-agent. One of them is Pi (Pi), at 49.4% for $0.29 per solved task, about 45% less than mini-swe-agent's $0.53. The best harness depends on the model: mini-swe-agent on GLM-5.3-Flash, Hermes Agent (Nous Research) on DeepSeek-V4.1-Flash and Kimi Code (Kimi.ai) on Flint. OpenCode costs $3.35 per solved task, 11.7 times as much as Pi. See Harness Hub's Harness Lens for what the nine harnesses do differently. It documents the prompts, tools and compaction of 34 coding-agent harnesses and links every claim to its source. Leaderboard: Harness Lens:

Joël Niklaus

218,063 görüntüleme • 1 gün önce

DeepSeek-V4-Flash-Spark and Spark-Mini were born today. 1 command setup to Pi / vllm-studio / docker deployment. All this is running local on a single DGX Spark.
3:57

DeepSeek-V4-Flash-Spark and Spark-Mini were born today. 1 command setup to Pi / vllm-studio / docker deployment. All this is running local on a single DGX Spark.

0xSero

20,019 görüntüleme • 5 ay önce

PI NEWORK BRINGS VIBE CODING TO APP STUDIO Pi Network (Pi Network) announced a new Pi App Studio update, which enables "Vibe Coders" to onboard AI-generated applications to its 60M+ user base. Builders using OpenAI Codex, Anthropic Claude Code, and Replit can now utilize tailored prompts to integrate the Pi SDK and payments in as little as two minutes. The initiative establishes Pi as a primary distribution network for the massive surge of software generated by the 2026 AI-assisted economy.
0:30

PI NEWORK BRINGS VIBE CODING TO APP STUDIO Pi Network (Pi Network) announced a new Pi App Studio update, which enables "Vibe Coders" to onboard AI-generated applications to its 60M+ user base. Builders using OpenAI Codex, Anthropic Claude Code, and Replit can now utilize tailored prompts to integrate the Pi SDK and payments in as little as two minutes. The initiative establishes Pi as a primary distribution network for the massive surge of software generated by the 2026 AI-assisted economy.

BSCN

19,442 görüntüleme • 5 ay önce

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
1:29

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 görüntüleme • 7 gün önce

Sidequest for Pi is a context aware side channel for coding agent tangents: It's better /btw. Ask questions grounded in your active Pi session, and keep the main conversation focused. Hit the ~ key to show/hide the threaded conversation UI. > pi install npm:pi-sidequest
1:39

Sidequest for Pi is a context aware side channel for coding agent tangents: It's better /btw. Ask questions grounded in your active Pi session, and keep the main conversation focused. Hit the ~ key to show/hide the threaded conversation UI. > pi install npm:pi-sidequest

Peter Pistorius

25,782 görüntüleme • 4 ay önce

I rebuilt Posia using the Pi Agent SDK. The core agent is ~15 lines of code, and the harness is so flexible and hackable. Recorded a 17-min walkthrough on: - Pi’s extension system + how to build your own - extensions that cut tool tokens by 80–96% - the core Pi SDK, step by step - building hosted agents with it Adding my Pi extensions setup in AI Builder Club repo here:
17:22

I rebuilt Posia using the Pi Agent SDK. The core agent is ~15 lines of code, and the harness is so flexible and hackable. Recorded a 17-min walkthrough on: - Pi’s extension system + how to build your own - extensions that cut tool tokens by 80–96% - the core Pi SDK, step by step - building hosted agents with it Adding my Pi extensions setup in AI Builder Club repo here:

Jason Zhou

66,979 görüntüleme • 4 ay önce

Ollama can now launch Pi, a minimal coding agent which you can customize for your workflow ollama launch pi You can even ask pi to write extensions for itself
0:20

Ollama can now launch Pi, a minimal coding agent which you can customize for your workflow ollama launch pi You can even ask pi to write extensions for itself

ollama

191,330 görüntüleme • 8 ay önce

A fully offline translator, built with Google Gemma 4, Google Antigravity, and a Raspberry Pi 5. 🛠️ The Gemma Translator is a portable AI experiment with a custom interface, printed case, and wired electronics, powered by the smallest Gemma model. Build your own →
1:14

A fully offline translator, built with Google Gemma 4, Google Antigravity, and a Raspberry Pi 5. 🛠️ The Gemma Translator is a portable AI experiment with a custom interface, printed case, and wired electronics, powered by the smallest Gemma model. Build your own →

Google for Developers

79,219 görüntüleme • 2 ay önce

pi-web-access is an extension that provides web search (and more) for Pi coding agent. The latest update introduces a new UX pattern: you can hit `Ctrl+S` to intercept agent searches mid-flight to inspect and curate exactly what makes it into the agent conversation. pi install npm:pi-web-access
0:34

pi-web-access is an extension that provides web search (and more) for Pi coding agent. The latest update introduces a new UX pattern: you can hit `Ctrl+S` to intercept agent searches mid-flight to inspect and curate exactly what makes it into the agent conversation. pi install npm:pi-web-access

Nico Bailon

29,352 görüntüleme • 8 ay önce

Gemma 4 + Ollama + Claude Code = A FREE local coding agent setup 🔥 Full Tutorial: You can run agentic workflows in your terminal with no API limits, no cloud dependency, and full control over your stack. Claude Code plus Ollama with Anthropic API compatibility.
0:43

Gemma 4 + Ollama + Claude Code = A FREE local coding agent setup 🔥 Full Tutorial: You can run agentic workflows in your terminal with no API limits, no cloud dependency, and full control over your stack. Claude Code plus Ollama with Anthropic API compatibility.

WorldofAI

26,283 görüntüleme • 6 ay önce

this is pure f*cking gold for anyone running coding agents Jev founder Diogo Amogo wrote a PDF on building a Jev harness the promise: > 200x faster > 400x cheaper the model hasn't been the slow part for a while the speed and the cost sit in the harness wrapped around it • how to use it > drop this PDF and the article below into Claude Code or Codex > let it rebuild its own setup one evening of setup and your agent starts next week on a harness most teams still don't have
0:24

this is pure f*cking gold for anyone running coding agents Jev founder Diogo Amogo wrote a PDF on building a Jev harness the promise: > 200x faster > 400x cheaper the model hasn't been the slow part for a while the speed and the cost sit in the harness wrapped around it • how to use it > drop this PDF and the article below into Claude Code or Codex > let it rebuild its own setup one evening of setup and your agent starts next week on a harness most teams still don't have

Mr. Buzzoni

80,191 görüntüleme • 20 gün önce

this is pure f*cking gold for anyone running coding agents Jev founder Diogo Amogo wrote a PDF on building a Jev harness the promise: > 200x faster > 400x cheaper the model hasn't been the slow part for a while the speed and the cost sit in the harness wrapped around it • how to use it > drop this PDF and the article below into Claude Code or Codex > let it rebuild its own setup one evening of setup and your agent starts next week on a harness most teams still don't have 👇
0:24

this is pure f*cking gold for anyone running coding agents Jev founder Diogo Amogo wrote a PDF on building a Jev harness the promise: > 200x faster > 400x cheaper the model hasn't been the slow part for a while the speed and the cost sit in the harness wrapped around it • how to use it > drop this PDF and the article below into Claude Code or Codex > let it rebuild its own setup one evening of setup and your agent starts next week on a harness most teams still don't have 👇

Mr. Buzzoni

128,732 görüntüleme • 1 ay önce