Running a 4-agent AI software engineering team on a $35 Raspberry Pi 4 without GPU or API calls, using local models and orchestration.
Learn how to run local AI models for Copilot tasks using Ollama, Foundry, and Azure OpenAI proxies in VS Code.
Building a multi-agent website builder entirely on a laptop CPU using local models, no cloud, GPU, or API keys.
A technical guide to running open-source AI models locally, covering hardware, tools like Ollama and Hermes Agent, and privacy benefits.
Guide to configuring Hermes AI agent with Gemma 4 for research, including Ollama and Hermes settings to prevent hallucinations.
Testing GitHub Copilot CLI offline with local AI models on CPU-only hardware, evaluating performance for .NET development tasks.
ElBruno.OllamaMonitor is a Windows system tray app that monitors local Ollama runtime, showing CPU, RAM, GPU usage, and model status in real-time.
Guide to optimizing Gemma 4 and Claude CLI on Macbook PRO M2-M5 with Flash Attention and KV Cache quantization for local AI coding.
A daily tech reading list covering AI agents, security, open-source tools, developer workflows, and industry news.
A technical architect explores using local LLMs as junior developers for a blog migration, analyzing their strengths and common pitfalls.
A tutorial on building a local AI agent with vision and function calling using Microsoft Agent Framework and Ollama in C#.
Guide to running OpenAI's Codex CLI with a self-hosted LLM on an NVIDIA DGX Spark via Tailscale for remote coding assistance.
A guide to using a PowerShell script with Ollama and the Qwen 2.5 model to perform AI-assisted code reviews on PostgreSQL database migration scripts.
Explains how to integrate local AI (Ollama) with PowerShell to automate SQL code reviews and checks in DataOps pipelines using tools like Flyway.
Explains why standard language model benchmarks are insufficient and how to build custom benchmarks for specific application needs.
A developer recounts deployment challenges with Docker and begins exploring AI frameworks with Ollama for a SaaS project.
A tutorial on installing and running the Mistral AI large language model locally on a Linux system using the Ollama platform.
A tutorial on installing the Deepseek AI model locally on a Linux machine using the Ollama platform.
A technical guide providing a bash script workaround to fix Ollama model download failures and connection resets.
A guide on using LLMs like Llama 3.2 Vision with .NET to automatically generate descriptive alt text for images, improving web accessibility.
