Tutorial on setting up a local coding agent using open-weight LLMs and open-source tools as an alternative to Claude Code and Codex.
Testing local open-weight LLMs like Qwen-Code and Codex in coding harnesses, comparing token use and task success.
Building a multi-agent website builder entirely on a laptop CPU using local models, no cloud, GPU, or API keys.
![Handing over to the AI for a day [blog]](https://crawljobs-blogs-media.s3.us-east-1.amazonaws.com/alldevblogs/thumbs/article-0f6a1d5ed8f9-full-87a279d1.webp)
A developer's personal experiment with AI-driven software development using local LLMs, detailing setup, challenges, and initial impressions.
A technical guide on setting up secure HTTPS access to a local LLM web interface using Tailscale and a Go proxy.
A Chrome extension that uses local AI to detect clickbait headlines, score websites, and suggest alternative titles, built for the Google Chrome Built-in AI Challenge.
Guide to running local LLMs like Llama3 and Phi-3 on a Raspberry Pi 5 using Ollama for private, cost-effective AI.
A technical guide on how to run the Mistral 7B Instruct large language model locally on a Macbook using llama.cpp and HuggingFace.
A technical guide on running the Mistral 8x7B Mixture of Experts AI model locally on a MacBook, including setup steps and performance notes.
