Practical guides to Git, CI/CD, Ollama, and Azure
MCP vs A2A vs AG-UI is the comparison chart making the rounds right now, and the framing is right — these are three different, complementary layers, not competing standards. But a couple of its headline numbers are either stale or… Read moreMCP vs A2A vs AG-UI: The Protocol Stack, Fact-Checked
The macOS 27 fm CLI gives every Mac a free language model in the terminal. It needs no account, no API key and no download, and you can point any OpenAI-style client at it. It also has a hard 4,096-token… Read moremacOS 27 fm CLI: What Apple’s Built-In Model Can Do
YAML vs JSON for LLMs isn’t just a style preference — it changes how many tokens you pay for on every request. I ran both formats through a real tokenizer on identical data instead of repeating the “20-ish percent” figures… Read moreYAML vs JSON for LLMs: Real Token Counts, Real Gotchas
Ollama vs vLLM vs llama.cpp comes down to one question: how many people will hit the model at once? For one developer on a laptop, pick Ollama or llama.cpp. For a GPU server with many concurrent users, pick vLLM. Below,… Read moreOllama vs vLLM vs llama.cpp: Which Local LLM Engine?
Cursor pricing lists four plans — Hobby, Pro, Pro+, and Ultra. Only one number on the page is real: the price. Pro costs $20 a month for “extended limits on Agent.” Pro+ costs $60 for “3x Pro limits.” Ultra costs… Read moreCursor Pricing: What the Plans Actually Give You
Ollama production deployment means three things the official docs don’t cover: the default systemd unit runs Ollama unsandboxed, the reverse-proxy example in Ollama’s own FAQ has no TLS and no auth, and there’s no built-in authentication at all — anyone… Read moreOllama Production Deployment: systemd, TLS, and API Auth
AI agents explained in one sentence: software where an LLM decides what to do next, based on the result of what it just did, in a loop, instead of following a script you wrote in advance. It picks which tool… Read moreAI Agents Explained: How They Actually Work
What is RAG, in one sentence? A way to make an LLM answer questions using documents it was never trained on. It searches those documents for relevant passages, then hands the model the results as context before generating a response…. Read moreWhat Is RAG? Retrieval-Augmented Generation Explained
What is an LLM, in one sentence? A model that has one job: given the text so far, predict the next token, append it, and repeat. That’s it. Everything else — chat interfaces, coding assistants, agents that call tools —… Read moreWhat Is an LLM? A Working Model for Engineers
The official MCP registry is the closest thing the Model Context Protocol has to an app store. So we pulled every entry from its API and counted what’s actually in there. The short version: 30,375 servers as of September 10,… Read moreThe MCP Registry, By the Numbers