A practical knowledge base for AI protocols, agents, core concepts, frameworks, and tools.
Learn what Agent Memory means and how it is used. Agent memory is the machinery that lets an agent persist information outside the context window and retrieve it on demand. The problem it solves isn't "the window is too small" but "remember the right things across sessions, days, and tasks — and update them when facts change"
Learn what AGENTS.md means and how it is used. AGENTS.md is a Markdown file at a repository's root written specifically for AI coding agents, covering build commands, how to run tests, and project conventions. Multiple vendors standardized it as an open format, and in December 2025 the specification was donated to the Linux Foundation's Agentic AI Foundation
Learn what AGI (Artificial General Intelligence) means and how it is used. AGI refers to an AI system that matches or exceeds human performance across most economically valuable cognitive tasks. It still has no agreed definition or acceptance test, and different organizations set wildly different bars, so arguments about when AGI arrives are often arguments about definitions
Learn what AI Observability means and how it is used. AI observability means recording model calls, tool executions, and agent decisions as queryable trace data so you can answer why it did what it did. Traditional monitoring only asks whether the service is up, while most AI failures return a 200 with a wrong answer
Learn what AI Video Generation means and how it is used. AI video generation uses diffusion models that denoise across space and time together, producing coherent video from a prompt or a reference image. Single-shot image quality is already high, so the real competition has moved to cross-shot character consistency, controllable camera work, and native audio sync
Learn what Attention (Mechanism) means and how it is used. An attention mechanism lets a model decide, while processing one position, which other positions of the input to draw information from and how heavily to weight each. It is the core component of the Transformer and the common origin of context windows, long-input cost, and KV caching
Learn what Chain of Thought means and how it is used. Chain of thought means having a model write out its intermediate reasoning steps before giving an answer. It began as a prompting technique and was later trained directly into reasoning models, becoming the mechanism behind today's "thinking…" interactions
Learn what Diffusion Model means and how it is used. A diffusion model is trained by gradually adding noise to real data until it becomes pure static, then learning to run that process backwards. To generate, it starts from random noise and denoises step by step according to a prompt, arriving at an image, video, or audio clip
Learn what Embodied AI means and how it is used. Embodied AI is AI with a physical body: it senses a real environment through sensors, changes it through actuators, and learns from the results. Compared with pure software models it has one extra thing — a real world with no undo — which is why data, real-time control, and safety are its three hard limits
Learn what GraphRAG means and how it is used. GraphRAG layers a knowledge graph on top of ordinary RAG: entities and relationships are extracted from documents into a graph, and retrieval traverses relationships rather than only matching semantically similar passages. It excels at questions requiring multi-document chaining or a global summary
Learn what LoRA (Low-Rank Adaptation) means and how it is used. LoRA is a parameter-efficient fine-tuning method: freeze the original model weights and train only a small pair of low-rank matrices alongside them. Training cost drops to a fraction of full fine-tuning, and the resulting adapter file is usually only tens of megabytes, so it can be attached and swapped at will
Learn what Open Weights means and how it is used. Open weights means a model's trained parameters are published for anyone to download, self-host, and fine-tune. People call these "open source models," but most don't meet the full open source definition — training data and training code usually stay private, and licenses may restrict use
Showing 12 of 79 entries
Every entry grouped by topic — one click straight to the explanation.
