A fast, no-nonsense toolbox for developers: format, convert, decode, and learn, all in one place. Every tool runs entirely in your browser, so nothing you paste is ever uploaded or tracked.
Context windows, MCP, RAG, embeddings & more, explained clearly, with tools.
Everything runs in your browser. Nothing leaves your device.
No signups. No tracking. No data collection. Ever.
Instant results. Works offline. Always available.
Clean UI, keyboard-friendly, and zero fluff.
The infrastructure of modern AI, from context windows to agents.
The model's working memory, tokens, what fills it, why it runs out, and how to manage it.
Read more →The open standard for connecting AI apps to tools and data, the 'USB-C for AI tools.'
Read more →Grounding a model in your own documents at query time, embeddings, retrieval, and why it beats fine-tuning for facts.
Read more →How content becomes a vector that captures meaning, the engine behind semantic search, RAG, and recommendations.
Read more →How a model decides to call a function, returns structured arguments, and your code runs it, the basis of agents.
Read more →Making a model return JSON that matches a schema every time, vs JSON mode, and why it powers extraction and tool calls.
Read more →Pull up a chair. One genuinely useful tool, reference, or idea, brewed fresh every Friday. No spam, just the good stuff.
Star us on GitHub and share with a friend.