Glossary
Definitions of terms used in the curriculum.
Showing 521–560 of 902 terms in the glossary
Letter L5 terms
localhost:1337
- Concepts
- The host and port of Jan's local API server (shorthand without the http:// prefix); Jan's docs use 127.0.0.1:1337 as the canonical form, and you can change the port under Settings > Local API Server > Configuration.
Loop tool
- Features
- Tools
- A feature that extends a video by blending its start and end frames, creating a seamless loop ideal for background footage.
5 other definitions
Loop tool · Features
A function in Sora that extends a clip by smoothly joining its start and end frames for seamless background loops.Loop tool · Features
A utility that extends a video by smoothly joining its start and end frames for seamless background loops.Loop tool · Tools
A feature that extends a clip by blending its start and end frames to create a seamless repeating background video.Loop tool · Features
A function that extends a video by blending its start and end frames to create a seamless repeating clip, useful for background footage.Loop tool · Features
An option that extends a clip by smoothly joining its start and end frames, creating a seamless repeating video. Lovable Cloud
- Concepts
- Lovable's built-in full-stack platform that provides a database, user authentication, file storage, and edge functions without any manual setup.
LSP
- Concepts
- Language Server Protocol — a standard opencode uses to connect to language servers and receive diagnostics (errors, warnings) as feedback that helps the AI detect and fix code issues.
Letter M35 terms
Maia
- AI
- Make's AI assistant — it builds and troubleshoots scenarios from a plain-language description.
Make Code
- Advanced
- A module for running custom JavaScript or Python when no ready-made app module fits.
malloc
- Concepts
- A function that requests dynamic memory at runtime, which is discouraged in real‑time code because it can cause unpredictable delays.
Manager Surface
- Features
- The part of the Antigravity interface where you can launch, watch, and control several agents running different tasks at the same time.
Manual execution
- Concepts
- Running a workflow by clicking the Execute button yourself, used for testing before you switch the workflow on for automatic production runs.
Mark to edit
- Commands
- An instruction you give to an AI agent to modify a specific element in an image or slide, such as changing a jacket’s color.
Markdown
- Core
- A simple way to format plain text, for example # for a heading and * for a list item. AI tools often answer in Markdown, and many apps display it as formatted text.
Also known as: .md file, Markdown file
MCP
- Concepts
- Protocol
- Protocols
- Core
- Model Context Protocol: an open standard for connecting AI apps to outside tools and data, such as files, calendars or databases. A service that offers an MCP server can plug into any AI app that supports MCP.
Also known as: Model Context Protocol
8 other definitions
MCP · Concepts
Model Context Protocol — a standard way to connect external tools (databases, APIs, services) to an agent so it can use them during a task.MCP · Concepts
Model Context Protocol — a standard way to connect an agent to external systems like GitHub, a database, or Jira.MCP · Protocols
Short for Model Context Protocol, a standard way for language models to discover and call external APIs without custom code.MCP · Concepts
Model Context Protocol — an industry-standard interface that lets AI agents connect to external tools and data sources through a common, provider-maintained interface.MCP · Protocol
Short for Model Context Protocol, a standard way for language models to discover and call external tools.MCP · Concepts
Model Context Protocol — an open standard Onyx supports for connecting agents to external tools and data sources beyond its built-in connectors.MCP · Concepts
Short for Model Context Protocol, a standard that lets the agent discover and invoke external APIs without custom code.MCP · Concepts
Model Context Protocol — the open standard for connecting an agent to external systems (GitHub, a database, your calendar) so it can read real data and act. MCP (Model Context Protocol)
- Concepts
- Protocols
- A standard way for language models to discover, validate, and call external tools over HTTP.
1 other definition
MCP (Model Context Protocol) · Protocols
A standard way for language models to discover and call external APIs without custom code. MCP integrations
- Features
- Connections to external tools and data sources (such as databases, APIs, and services like Stripe or Neon) that v0's AI automatically considers when generating responses, allowing it to incorporate real external context.
MCP server
- Concepts
- An external tool server that connects to opencode via the Model Context Protocol, giving the AI access to additional capabilities such as searching documentation or querying a database.
1 other definition
MCP server · Concepts
A small program that exposes one external system over MCP; you connect it to your agent to give it that tool. media plan
- Features
- An outline generated by the AI that lists each scene, its length, camera moves, text and music before making a video.
Media tab
- Interface
- The panel on the right side of the editor used for entering natural‑language action descriptions.
Memory
- Concepts
- Features
- Core
- A feature that lets a chat assistant remember facts about you across conversations. Check what it has stored, and switch it off for sensitive work.
Also known as: memory feature, chat memory
4 other definitions
Memory · Features
A feature where ChatGPT saves useful facts you share across conversations (like dietary preferences or your job) so future chats feel more personalised; you can view, edit, or delete saved memories at any time.Memory · Concepts
An optional capability where Claude builds a running summary of your role and ongoing work so new chats start already informed about you.Memory · Features
A component that stores previous conversation messages so the AI can refer back to earlier exchanges within the same chat session.Memory · Features
An optional setting where Gemini learns details from your past conversations and uses that context to give more personalized answers in future sessions. memory.md
- Files
- A mutable markdown file where an agent writes facts it learns so those preferences can be recalled in later sessions.
Metanode
- Features
- A group of nodes collapsed into one box purely to keep the canvas tidy; unlike a Component it cannot be shared or given a custom dialog.
method
- Concepts
- A function that belongs to an object or class — for example,
.mean()is a method on a pandas DataFrame that calculates the average of a column. mini models
- Features
- Low‑cost versions of big language models that run without using your credit balance.
mintplexlabs/anythingllm
- Files & config
- The official Docker Hub image name for AnythingLLM, which you reference when running the app inside a container on your own machine or server.
mistral
- Models
- Mistral AI's 7B open-weight language model, available through Ollama and distributed under the Apache license.
MIT license
- Concepts
- An open‑source legal notice that lets anyone use, modify, and share the code freely with minimal restrictions.
model
- API Request Fields
- Concepts
- Models
- Core
- The trained program that does the actual work inside an AI tool. The app you type into is only the interface; the model behind it decides how good, fast and expensive the answers are.
Also known as: AI model
4 other definitions
model · Models
The specific trained AI system (such as “Firefly commercial safe”) that creates the output.model · Concepts
A field in an API request body that tells the server which AI model to use; when talking to Jan you set this to the model ID shown in Jan's model list.model · Concepts
The specific AI brain opencode uses to answer your questions and write code (for example claude-sonnet-4-5 or gpt-4o); you can switch models mid-session.model · API Request Fields
A key in the JSON request body that tells OpenRouter which AI model to use for your request, specified as a provider/model-name string such as google/gemma-4-31b-it:free. Model Council
- Features
- A premium feature that runs your query through three AI models simultaneously, then uses a fourth 'chair' model to synthesize their responses into one combined answer — available to Max subscribers.
model dropdown
- Interface
- The menu in Langdock where you pick which AI model (like Claude or GPT‑4) will answer your query.
model ID
- Core
- The exact name you give a tool or an API to choose a model, often with a version or date in it. Using the exact ID means you know which model you are getting.
Also known as: model identifier, model name
model picker
- Concepts
- The dropdown that lets you switch which model handles a request (Claude, GPT, Gemini, or Auto) on a per-task basis.
Model Port
- Concepts
- A port that passes a trained machine-learning model from one node (e.g. a trainer) to another (e.g. a predictor).
Model Selection
- Tool Settings
- A dropdown that lets you choose which underlying language model (e.g., GPT‑4, Claude) will answer a specific query.
model swap regression check
- Process
- Running the same test suite on a different language‑model version to spot any new failures caused by the change.
Model‑Context Protocol (MCP)
- Concepts
- A standard that converts natural‑language requests from a language model into API calls for external tools like Gmail or Calendar.
model: haiku
- Files & config
- A settings key that pins the AI model to Haiku (a faster, lower-cost Claude model) for a project or session.
Module
- Workflows
- A single step in a scenario, representing one app action — read a row, send an email, call an API.
ModuleNotFoundError
- Concepts
- A Python error meaning a required package is not installed; in Agent mode Cursor can detect this and install the missing package automatically.
MoE
- How models are built
- Mixture of Experts — an architecture that activates only a slice of the model's parameters per token, so a huge model can run at the cost of a much smaller one (e.g. DeepSeek, GLM, MiniMax).