AI agent
An LLM-powered program that pursues a goal over multiple steps by calling tools, observing results, and replanning. Agents differ from single-turn chatbots in that they can take real actions (run shell commands, edit files, hit APIs) and iterate without human intervention between steps.
Background
An AI agent is an LLM driving a loop of `reason → act → observe → reason` until a goal is reached or a stop condition is hit. The reasoning is performed by the model; the actions are tool calls (function calling, MCP tools, browser actions). Agent quality depends on the model's tool-use accuracy, the breadth of available tools, and the prompt scaffolding (often called "the harness"). Coding agents are a specialisation where the tools include filesystem, terminal, and git operations.
Tools that use it
- 01→OpenHands
Open-source autonomous coding agent platform, formerly OpenDevin, by All Hands AI.
- 02→Devin
Cognition's autonomous software engineer — runs tasks in a managed cloud sandbox with browser, terminal, and editor.
- 03→Cline
Open-source autonomous coding agent for VS Code, formerly known as Claude Dev.
- 04→Aider
Open-source CLI coding agent that pair-programs in your terminal and commits to git automatically.
- 05→Claude Code
Anthropic's official CLI agent for Claude — runs in the terminal, edits files, executes commands, and ships PRs.