By Adam Jenner, 10+ years building automation for ASIC, Westpac, and Australia's major banks. Founder of Phoenix AI. · github.com/adamjen · adamjenner.com.au
Build Your Local
AI Agent Team
What's inside: A step-by-step video series and complete config bundle to run a multi-agent AI coding harness entirely on your own hardware.
Four years ago I was learning coding with ChatGPT, asking questions, then copying and pasting code locally, all manually. Two years ago, things changed. I started running AI locally: Ollama, LM Studio, Cline. I no longer needed to copy and paste code; I could do it all in one place. My goal was always the same: get to the point where local models actually work, and can also do the work, with no subscriptions, no API keys, no monthly bills. Four months of deep work building the Pi harness means you can skip the painful trial and error. You get something that works from day one. The agent files aren't generic prompts. They're refined from hundreds of real sessions.
Give the harness a complex task and walk away. Even if it's slow, it's running on your machine, your data never leaves, and you can come back later to see what it built.
From Zero to a Working
Multi-Agent Team
Install Pi from Scratch
Set up the Pi harness on Linux, Windows (WSL2), or Mac (Apple Silicon), understand the ~/.pi/ folder structure, and run your first session with a cloud provider.
Compile & Run llama.cpp with CUDA
Build the local inference engine from source, load a GGUF model, and get your first local AI response on NVIDIA CUDA, Apple Metal, or CPU.
Manage 14 Models with llama-swap
Configure the reverse proxy that loads, unloads, and routes requests across multiple models, so you're not limited to one model at a time.
Wire the Backend End-to-End
Connect llama-swap to Pi via settings.json and models.json, understand the three config files that make the system work, and know why each model was chosen.
Deploy Agents, Skills & Extensions
Set up 13 specialized agent definitions, load ~93 skill references on demand, and hot-reload 6 extensions without forking.
Run a Live Multi-Agent Project
Watch the orchestrator delegate, researchers gather context, debuggers diagnose and fix, and coders implement, all locally, all in real time, from prompt to finished product.
Everything You Need
to Go Local
6-Video Series
From zero to a working multi-agent harness. Each video is 8-15 minutes of hands-on, screen-shared walkthroughs, no fluff, no slides.
Training Guide Ebook
The Local LLM Agent Harness, Second Edition: a complete PDF reference with annotated configs and decision trees.
Ready-to-Run Configs
settings.json, models.json, AGENTS.md, and 5 agent definitions (Starter) or all 13 (full bundle), drop into your ~/.pi/ and go.
Skills & Extensions
3 skills (pipeline orchestration, goal pipeline, librarian) and 3 extensions (subagents, VCC, web access) in the Starter Bundle. The full bundle unlocks ~93 skill references and 6 extensions via the video series.
llama.cpp MTP Setup Guide
Step-by-step build instructions for multi-token prediction support, tested on RTX 3090 (24GB), 16GB cards, and Apple Silicon (Metal). Works on Linux, Windows (WSL2), and Mac. This customised setup gives you a speed boost over standard inference.
From Early Adopters
[PLACEHOLDER: Adam — add a buyer quote here. E.g., "Got this running on my RTX 3080 in an afternoon. The config files alone saved me days of trial and error."]
[PLACEHOLDER: Adam — add a second buyer quote. Focus on the multi-agent workflow or privacy angle.]
[PLACEHOLDER: Adam — add a third buyer quote. E.g., someone who replaced their API usage entirely.]
Pick Your Tier
Available Now
Ebook & configs, buy today, start building.
Runs on any modern PC. NVIDIA GPU (6GB+ VRAM) recommended. Apple Silicon and CPU-only also supported. See FAQ for details.
Ebook Only
$29 USD / €29 EUR / $29 AUD
The training guide PDF: the complete reference with annotated configs and decision trees.
- Training guide ebook (PDF)
- Second Edition: complete reference
- Annotated config walkthroughs
- Model selection decision trees
Includes a discount code toward the full bundle when it launches.
Starter Bundle
$39 USD / €39 EUR / $39 AUD
PDF + configs + agent definitions + skills. +$10 for everything that runs.
- Training guide ebook (PDF)
- Ready-to-run config bundle
- 5 agent definitions & 3 skills
- Optimized llama.cpp fork
- 3 core extensions
- Tokyo Night theme
Includes a discount code toward the full bundle when it launches.
Coming Soon: Video Series
Full bundle with 6-video training series, launching soon.
Student
$49 USD / €49 EUR / $49 AUD
For students & hobbyists. Full access to the complete bundle: videos, ebook, configs, and community.
- 6-video training series
- Training guide ebook (PDF)
- Ready-to-run config bundle
- 13 agent definitions & ~93 skill references
- 6 extensions (subagents, VCC, web access, hypa, compact-fast, trace)
- 2 themes (Tokyo Night, Deep Space)
- Optimized llama.cpp fork
- Private Discord community
Valid .edu or .edu.au email required at checkout.
Core
$149 USD / €149 EUR / $149 AUD
For individual developers. Everything in Student plus a full commercial license for your projects.
- Everything in Student
- Full commercial license
- Use in client projects
- Priority Discord support
- Future config updates included
Pro
$399 USD / €399 EUR / $399 AUD
For teams & tech leads. Full bundle with hands-on architecture review and direct access.
- Everything in Core
- Private Discord / Q&A channel
- 1-on-1 Harness Architecture Review
- Team deployment guidance
- Custom model selection advice
- Direct Slack access to Adam
Get Notified When
the Video Series Launches
Watch the teaser below. Join the waitlist for early access and launch-day discounts.
Common Questions
NVIDIA GPU (CUDA): RTX 3090 (24GB VRAM) is the sweet spot. All 27B models fit entirely in VRAM at 35+ tokens/sec. A 16GB card like the RTX 4060 Ti works with partial CPU offloading at ~18-20 tok/s. Even 12GB or CPU-only runs at ~10 tok/s. Apple Silicon (Metal): unified memory handles 27B models on 32GB+ Macs. CPU-only: works at ~10 tok/s. The bundle includes guidance for each tier.
You don't need VRAM for all 14 models simultaneously; llama-swap loads one model at a time. The largest models (35B MoE) need ~30GB, which partially offloads to RAM on 24GB cards. The 27B models fit entirely in 24GB VRAM. Minimum: 6GB VRAM for the smallest models. Apple Silicon: unified memory counts as VRAM. A Mac with 32GB unified memory handles the 27B models comfortably. 16GB Macs work with the smaller models (7B and under) at good speed.
Starter Bundle ($39): PDF training guide, config files (settings.json, models.json, AGENTS.md), 5 agent definitions (orchestrator, researcher, debugger, coder, worker), 3 skills (pipeline orchestration, goal pipeline, librarian), 3 core extensions (pi-subagents, pi-vcc, pi-web-access), and a modified llama.cpp fork with MTP support.
Full Bundle (video series): Everything above plus 6 training videos, all 13 agent definitions, ~93 skill references, 6 extensions, 2 themes, and access to a private Discord community.
Basic command-line comfort is expected, whether that's Linux, macOS Terminal, or Windows WSL2. No prior LLM experience required; the series starts from a clean install and walks through every step. If you can run git clone and cmake, you're ready. The bundle covers build instructions for all three platforms.
Linux: primary platform, fully tested on Ubuntu/Debian. Windows: works via WSL2. Mac (Apple Silicon): fully supported via llama.cpp's Metal backend. The MTP (multi-token prediction) features work across all three platforms. NVIDIA GPUs (CUDA) give the best throughput, but Apple Silicon M-series chips deliver excellent performance through Metal; models that fit in unified memory run smoothly.
Full refund within 7 days of purchase. If the bundle doesn't meet your expectations, reach out via the contact form below and we'll process your refund through Stripe. After 7 days, all sales are final for digital products.
Six videos, 8-15 minutes each. Total runtime: ~60-75 minutes. No fluff, no slides; screen-shared walkthroughs the entire time.
Bundle buyers get access to a private Discord community for questions, troubleshooting, and updates. The config files and extensions are updated as Pi evolves.
Contact
Questions, requests, or just want to say hi?
More Products
Phoenix AI
The AI chat widget for Australian businesses. Runs locally, answers visitors 24/7, data stays in Australia. From $29/month.
Visit Phoenix AI →pi-docker
Free demo project built in 10 minutes with the PI Agent Harness. Sandboxed, isolated, fully local.
View on GitHub →