Playbooks·Build, with consequences

The tools we wished existed.

Setup guides, tests and benchmarks from our test stack, with the commands and the numbers.

Playbook · Tools

How to Set Up OpenCode With a Local Model, No Terminal

An OpenCode setup with a local model: a coding agent that runs as a normal desktop app, pointed at a model on…

11 min
Playbook · Tools

How to Install Ollama on a Mac (Apple Silicon) the Right Way

Install Ollama on a Mac the clean way. The setup for Apple Silicon, plus the handful of settings that save you grief…

9 min
Playbook · Tools

Run a Local ChatGPT With Open WebUI and Ollama

An Open WebUI setup guide: a private chat app that looks and works like ChatGPT, answered by a model on your own…

10 min
Playbook · Tools

Local AI Autocomplete in VS Code With Continue.dev

Continue.dev with Ollama is GitHub Copilot, except that the model lives on your laptop, you pick which one, and no line of…

10 min
Playbook · Workflow

Aider: AI Pair-Programming in Your Terminal With a Local Model

Aider with a local model reads your repo, edits files, runs commands, and commits with clean messages, all from a chat prompt…

11 min
Playbook · Process

Build Your Own Local AI Stack (Compute, Model, Tools)

A local AI stack is three choices stacked in order: the compute, the model engine, then the tools you actually touch. How…

12 min
Playbook · Tools

Local Transcription That Beats the Paid Apps: WhisperX

A WhisperX setup guide. Whisper turns audio into text, and WhisperX tells you who said what, with timestamps, running entirely on your…

11 min
Playbook · Research

Chat With Your Documents Locally (RAG) With AnythingLLM

An AnythingLLM setup guide: drag in a PDF, ask a question, and get an answer with source citations, all running on your…

11 min
Playbook · Tools

ComfyUI Beginner Guide: Generate Images Locally

A ComfyUI beginner guide. It looks intimidating because it shows every step of image generation as a node you wire together. That…

11 min
Playbook · Research

Local LLM RAM Requirements: A Sizing Guide

Local LLM RAM requirements, explained. The commonest mistake is pulling a model your machine cannot hold. How to size a model to…

10 min
Playbook · Research

Local Deep Research: A Fully Private, Free Engine

Local deep research that searches, reads and writes a cited report with nothing leaving your machine: a model on Ollama plus a…

12 min
Playbook · Workflow

Migrate Off Paid AI Tools to Open-Source: A Step-by-Step

You do not have to cancel everything at once. The calm way to replace paid AI tools with open source: inventory, map…

11 min
Playbook · Workflow

AI Coding Agent Permissions: Safe File Access

An AI coding agent that can edit files and run commands is useful and, handled carelessly, risky. How we set coding agent…

10 min
Playbook · Tools

Piper TTS Setup: Local Text-to-Speech on Any CPU

A Piper TTS setup guide: a lightweight engine that turns text into a WAV file in under a second, on a plain…

9 min
Playbook · Tools

Marker: Convert PDF to Clean Markdown Locally

PDFs are built for printing, not machines. Marker converts PDF to Markdown with layout detection, keeping tables and equations intact, on your…

10 min
Playbook · coding-agents

OpenCode with a local model: set up an offline AI coding agent

Point OpenCode at a local model and code with no internet and no API key. The setup, the config, and the trade-offs…

7 min
Playbook · benchmarks

Best Local LLMs for Coding on a Mac in 2026: Benchmarked and Ranked

We benchmarked and ranked the best local LLMs for coding on a Mac in 2026, on real refactors, with speed, memory and…

6 min
Playbook · coding-agents

How to Set Up a Local AI Coding Agent on a Mac

A step by step setup for a local AI coding agent on a Mac. No rate limits, no credits, no cloud. Which…

8 min
Playbook · comfyui

ComfyUI with local LLMs: a practical Mac workflow

Wire local LLMs into ComfyUI to write better prompts. The nodes, the model, the memory cost on a Mac, and the ComfyUI…

7 min
Playbook · assistant

OpenClaw with a local model: a private AI assistant

Run OpenClaw with a local model and keep a persistent AI assistant on your own machine. Onboarding, memory, tools, and what it…

7 min
Playbook · gemma

How to run Gemma 4 12B locally on a Mac with Ollama

How to run Gemma 4 12B locally on a Mac with Ollama: the pull command, the memory it needs, the context you…

8 min
Playbook · benchmarks

Local LLM benchmarks on M4 Pro: Gemma, Qwen, Llama speeds

Local LLM benchmarks on an M4 Pro. Gemma, Qwen and Llama measured on tokens per second, memory used, and the point where…

7 min
Playbook · coding-agents

Local AI coding agent setup with OpenCode and Ollama

Set up a local AI coding agent with OpenCode and Ollama. No API key, no subscription. The install, the model choice, and…

7 min
Playbook · Gemma 4

Set up local LLM tool calling in Hermes and OpenCode on a Mac

We set up local LLM tool calling in Hermes and OpenCode on a 48 GB Mac mini. Why small models drop tool…

5 min
Playbook · coding-agents

Set up a brand voice across OpenCode, Hermes, and Pi

One brand voice spec, wired into three agents. How we point OpenCode, Hermes, and Pi at the same voice files through AGENTS.md…

7 min
Playbook · apple-silicon

How to build a private, always-on AI assistant on your Mac with Hermes Agent and LM Studio

How to build a private AI assistant on Mac with Hermes Agent and LM Studio, running on an M4 Pro. Voice notes…

5 min
Playbook · local-ai

OpenJarvis on a Mac: we retested Stanford’s local AI agent

We reinstalled OpenJarvis on a Mac, captured its telemetry with a local sink, and found the undocumented off switch. What it sends,…

9 min
Playbook · automation

Local AI agent for morning routine automation: setting up Hermes Agent

Learn how to set up Hermes Agent for morning routine automation. Use local AI to synthesize calendars, goals, and weather into a…

7 min
Playbook · automation

How to keep a background AI agent from failing silently

A background AI agent silent failure hides in plain sight. A heartbeat, a cron wrapper, and a watchdog make a dead scheduled…

6 min
Playbook · 1-bit LLM

Bonsai 27B 1-bit on a Mac: a 27B model in 3.8 GB

Most 27-billion-parameter models arrive as a download you plan an evening around. The Bonsai 27B 1-bit build from PrismML lands in 3.80…

8 min
Playbook · 1-bit LLM

Bonsai 27B vs Gemma 4 31B on a Mac: which local model to run

Two models sat loaded in the same copy of LM Studio this week, and one of them was a fifth the size…

6 min
Playbook

MoE on a Mac: 4 to 5 times faster, and bigger in memory than the dense model it beats

A 26B MoE decodes 4 to 5 times faster than a dense model on a Mac and can still take more RAM…

10 min
Playbook

Ollama MTP: the speculative decoding that is already on, and the DRAFT command nobody documented

Ollama MTP has been on by default since v0.31.1, roughly 90% faster on Gemma 4. What multi-token prediction does, and the DRAFT…

8 min
Playbook

Bonsai 27B in a coding agent: a 1-bit model that calls tools cleanly and misses the line number

We put Bonsai 27B, a 1-bit model in 3.8 GB, behind the Pi coding agent. Tool calls came back clean on the…

8 min
Playbook

Run an NVFP4 model in Ollama on a Mac: tags, commands, gotchas

How to run an Ollama NVFP4 model on a Mac: the tags that exist, the version you need, and four gotchas including…

6 min
Playbook · arc-agi-3

ARC-AGI-3 local model test: what one move costs

We ran the MIT licensed ARC-AGI-3 toolkit on a 48 GB M4 Pro with a local model, measured what a single move…

10 min
Playbook · Gemma 4

LM Studio empty response: when reasoning eats the answer

A local model returned nothing four times in a row. What an LM Studio empty response means, why a bigger max_tokens will…

8 min
Playbook · arc-agi-3

ARC-AGI-3 offline mode: run the games with no API key

ARC-AGI-3 offline mode runs the public games from disk with no key and no network. The four operation modes read from source,…

6 min
Playbook · arc-agi-3

Why GameAction(1) fails in the ARC-AGI-3 toolkit

GameAction(1) raises ValueError in the ARC-AGI-3 toolkit though ACTION1.value is 1. Why the GameAction enum rejects its own value, and the lookups…

6 min
Playbook · agents

A random agent on all 25 ARC-AGI-3 games: 12 clears, no score

An ARC-AGI-3 random agent ran 60,000 actions on all 25 public games: twelve first levels cleared, two second levels, about two points…

5 min
Playbook · agents

Write your first ARC-AGI-3 agent in 40 lines of Python

A 40 line ARC-AGI-3 agent in Python that survives resets, converts action ids, handles clicks and scores locally. Every guard was paid…

6 min
Playbook · arc-agi-3

Build your own ARC-AGI-3 game with arcengine in 13 lines

A working ARC-AGI-3 game in 13 lines of Python on arcengine: the class, the camera, two levels, step(), the on-disk layout the…

6 min
Playbook · api

What the anonymous ARC-AGI-3 API key gets you

The ARC-AGI-3 API key you get without asking: what the anonymous key can do, what registering adds, and the 600 requests a…

5 min
Playbook · arc-agi-3

ARC-AGI-3 recordings: what save_recording writes, and how big it gets

ARC-AGI-3 recordings are one argument to make(). What each JSONL line holds, why frames make the file forty times bigger, and how…

5 min
Playbook · arc-agi-3

Score an ARC-AGI-3 run locally: the scorecard without the API

The ARC-AGI-3 scorecard is computed locally and offline by the package that plays the game. What get_scorecard returns, how it is weighted,…

5 min
Playbook · LM Studio

Grid to text for a local model: four lines of numpy, measured

Grid to text for a local model, measured: raw hex costs 442.7s a move, a four line numpy colour summary 89.2s. The…

5 min
Playbook · LM Studio

Debug a local model with a four call control ladder

Four calls, from a trivial reply to the real input, to debug a local model in minutes. What each rung proves, how…

6 min
Playbook · Gemma 4

LM Studio reasoning effort, temperature and schemas: what changes the thinking

LM Studio reasoning effort, temperature, JSON schemas and tool calls measured on one board: low effort thought most, a schema halved the…

6 min
Playbook · LM Studio

How to set max_tokens for a reasoning model, from measurement

max_tokens for a reasoning model is a measurement, not a guess: run the largest input once at a huge cap, read the…

5 min
Playbook · arc prize

Enter ARC Prize 2026 with a local model: the Kaggle track, from a Mac

ARC Prize 2026 pays $700,000 for 100 percent; its first milestone went to local open weight models. The prizes, the open source…

5 min
Playbook · Apple Silicon

ARC-AGI-3 on a Mac: what a 48 GB M4 Pro can and cannot do

ARC-AGI-3 on a Mac, measured on a 48 GB M4 Pro: the toolkit does 4,000 actions a second, a 31B reasons at…

5 min
Playbook · agents

A local model agent on one ARC-AGI-3 level: 40 moves, 230 minutes, nothing

A local model agent played 40 moves of one ARC-AGI-3 level in 230 minutes, 154,673 reasoning tokens, and cleared nothing. A human…

5 min
Playbook · Gemma 4

Image vs text for a local vision model: one board, two costs

Image vs text for a local vision model, measured: the same 64x64 board cost 4,179 prompt tokens as hex and 187 as…

5 min
Playbook · agents

A REPL agent in its smallest form: one model call writes the player

A REPL agent in its smallest form: one local model call wrote a 44 line policy that played 60,000 ARC-AGI-3 actions in…

5 min
Playbook · agents

Two agents on one LM Studio endpoint: what concurrent requests cost

Two identical LM Studio concurrent requests to a 31B on a 48 GB Mac: each ran at half speed and the combined…

5 min
Playbook · benchmarks

Why your local model stops at exactly 8,192 tokens

Twelve of thirty six local model runs stopped at exactly 8,192 tokens with a 16,384 cap. The LM Studio context length default,…

6 min
Playbook · Hermes Agent

Hermes Agent local models on a Mac: setup, file locations and the button that changes your default

Set up Hermes Agent local models on a Mac: install the llama.cpp runtime, where downloads go, which button changes your default, and…

6 min
Playbook · agent skills

Share Claude Code skills with OpenCode, Hermes Agent and Pi from one folder

Share Claude Code skills with OpenCode, Hermes Agent and Pi: where each agent looks, the one folder OpenCode already reads, and 106…

6 min
Playbook · kokoro tts

Kokoro TTS on a Mac: install, speed on an M4 Pro, and automatic article narration

Run Kokoro TTS on a Mac with no ffmpeg: install, a measured 7.1x real time on an M4 Pro, text cleaning, and…

5 min
Playbook · Apple Silicon

Install and run MuJoCo on Mac: tested on an M4 Pro

MuJoCo on Mac, tested on an M4 Pro: pip install in 4.9 seconds, the fix for the mjpython viewer error and permission…

6 min