DeveloperHA / AI agents / Aider
Terminal pair-programming tool · CLI agents

Aider

Aider is a useful comparison point because it emphasizes a Git-aware pair-programming workflow and model choice rather than a single provider surface.

Made by Aider projectSeparate agent guideReviewed 2026-09-26Model ≠ harness ≠ orchestrator
Scope note This is an independent guide to a third-party project or a developer concept. Installation commands, feature boundaries, plans, model availability and security defaults change. Follow the official source links before using it with private code, credentials or automation.

What it is and who makes it

A terminal-first AI pair-programming tool that works with Git repositories and a range of hosted or local models.

Maker or project: Aider project. Classification: Terminal pair-programming tool; this page treats the surrounding context, tools, permissions and verification as the relevant harness boundary.

1
Start Aider from a repository and select the model/provider.

Start Aider from a repository and select the model/provider.

2
Add the files that belong in the current conversation or task.

Add the files that belong in the current conversation or task.

3
The tool proposes edits and can run configured checks.

The tool proposes edits and can run configured checks.

4
Use Git diff and history as the review and undo boundary.

Use Git diff and history as the review and undo boundary.

Who it may fit

Pick an agent by its control surface and trust boundary, not only by its model label.

Useful scenarios

  • Developers who want Git-visible edits
  • Terminal pair programming across different model providers
  • Small, reviewable changes in an existing repository

Trade-offs and checks

  • Automatic commits are helpful only when you inspect them; they are not a substitute for review.
  • Model provider keys and repository context still follow the provider's data policy.
  • Do not run broad auto-approve settings in a repository containing production credentials.

Interactive vs headless and CI

These modes change the approval, identity and observability boundary.

The terminal prompt is interactive and pair-programming oriented. One-shot messages and configured test/lint commands can support automation, but disable broad auto-approval and make Git diff/commit handling an explicit CI step.

Request-to-verification workflow

Use this mental model when debugging a surprising edit, tool call or cost.

Input

Intent + context

Your prompt, repository instructions, selected files, history and environment become model context.

Action

Tool + permission

The harness proposes a read, edit, shell, web, MCP or other action; policy decides whether it can run.

Feedback

Result + verification

Command output, compiler errors, tests and your review return to the loop before acceptance.

Setup outline

Start with the smallest safe experiment, then follow the current official documentation for the real installation.

1
Follow the current Aider installation guide.
2
Run it inside a clean Git branch or worktree.
3
Add only the files needed for the task and establish the test command.
4
Review the Git diff and commits before moving the work elsewhere.
Illustrative workflow
python -m pip install aider-install
aider-install

cd your-project
aider

# Start with a bounded request:
# Add tests for the null response path; do not change the API contract.

Instructions, skills, MCP and hooks

These surfaces can shape context or add actions; they are part of the trust boundary.

Aider emphasizes explicit file context, repository mapping, Git and configuration files such as its documented config options. It is not safe to assume that instruction files, MCP or plugin conventions from another agent automatically apply.

Security and isolation checklist Use a disposable branch or worktree; keep secrets outside the readable path; require approval for writes, shell, network and deployment actions; inspect commands before allowing them; constrain server bindings; review MCP servers, plugins, skills, hooks and instruction files; and run tests independently of the agent's own summary.

Official sources

Use these sources for current installation, capabilities, plans, releases and security notices.

Reviewed 2026-09-26. This date is a change-tracking note, not a promise that the product remains unchanged.

Related learning

Related agent guides

Want the foundations behind the workflow?

Study AI fundamentals, prompt design, AI-assisted development, agents and MCP without a forced linear course.

Open AI learningAI tools