Local LLMs
Running models on your own hardware: Ollama, llama.cpp, quantization, front-ends, and memory sizing.
Agents & MCP
Agent SDKs, MCP servers and debugging tools, and code sandboxes, compared and tested.
LLM Ops & Costs
Tracing and evaluation tools, vector databases, and what LLM workloads cost to run.
Featured
Tested guides and calculators, with the commands, versions and numbers to reproduce them.