Glossary

AI Coding Agent

An AI program that autonomously reads, writes, and runs code to complete development tasks.

An AI coding agent is software that uses a large language model to perform development tasks end to end — understanding a request, exploring the codebase, making edits, running commands, and iterating. Popular terminal-native agents include Claude Code, Codex CLI, Gemini CLI, and Aider.

Agents differ from inline assistants in autonomy: they take multi-step actions rather than only completing the current line. Running them effectively benefits from a terminal designed to host, observe, and orchestrate agents.

Learn more

Related guides on the Agents UI blog and related terms in this glossary.

Try Agents UI

A native terminal for AI coding agents with persistent sessions, SSH workflows, and built-in editing.

Download View on GitHub

Related

Agentic Coding

A workflow where an autonomous AI agent plans and executes multi-step coding tasks, not just single completions.

Multi-Agent Orchestration

Coordinating several AI agents toward one goal by splitting it into tasks across parallel sessions.

Model Context Protocol (MCP)

An open standard that lets AI agents connect to tools, data sources, and actions through a common interface.

Best Terminal For Ai Coding Agents

Read the guide →

Agentic Coding Developers Guide Autonomous Ai Agents

Read the guide →