AI

Three tiers of AI development: inline completions for flow, agent sprints for features, and overnight batch runs. Route each task to the right one.

Build a private AI search engine with SearXNG and RAG. Runs on single machine with 12 GB VRAM, delivering cited answers without external queries.

Explore Claude Code's 1,340+ agentic skills ecosystem: major repositories, top skills by category, building custom skills, and future directions.

Coordinate multiple AI coding agents in parallel using file ownership, iteration caps, and review gates to beat single-agent throughput on real work.

Unify access to Ollama, vLLM, OpenAI, Anthropic, and Google models behind one endpoint. Routing, load balancing, and rate limiting with LiteLLM.

Gemma 4, Qwen 3.5, and Llama 4 compared on benchmarks, licensing, speed, and hardware needs so you can pick the right open model for your work fast.