Aider Configuration

Comprehensive configuration for Aider, an AI pair programming tool that helps you edit code in your local git repository. This configuration covers all available settings including model selection, API configuration, git integration, output customization, and advanced features.

What This Does

This skill provides a complete `.aider.conf.yml` configuration file that can be placed in your home directory or at the root of your git repository. It includes settings for:

Instructions

1. Model Configuration

**Main Chat Model:**

```yaml

model: gpt-4.1-mini

```

**Specialized Models:**

```yaml

For commit messages and summarization

weak-model: gpt-3.5-turbo

For editor tasks

editor-model: gpt-4.1-mini

editor-edit-format: whole

```

**Edit Format:**

```yaml

Use architect mode for complex refactoring

architect: false

auto-accept-architect: true

edit-format: diff # Options: diff, whole, udiff, etc.

```

2. API Configuration

**API Keys (store sensitive keys in .env file instead):**

```yaml

Use set-env for non-OpenAI/Anthropic providers

set-env:

- PROVIDER_API_KEY=xxx

api-key:

- provider=your_key_here

```

**API Settings:**

```yaml

verify-ssl: true

timeout: 120

openai-api-base: https://api.openai.com/v1

```

3. Repository Mapping

**Control context sent to LLM:**

```yaml

map-tokens: 1024 # Suggested token limit for repo map, 0 to disable

map-refresh: auto # Options: auto, always, files, manual

map-multiplier-no-files: 2 # Increase map size when no files specified

```

4. Git Integration

**Auto-commit Behavior:**

```yaml

git: true

auto-commits: true

dirty-commits: true

attribute-author: true

attribute-committer: true

attribute-commit-message-author: false

gitignore: true

```

**Custom Commit Prompts:**

```yaml

commit-prompt: "Write a concise commit message following conventional commits format"

```

5. Automatic Linting and Testing

**Linting:**

```yaml

auto-lint: true

lint-cmd:

- "python: flake8 --select=E,W,F"

- "javascript: eslint --fix"

- "go: golangci-lint run"

```

**Testing:**

```yaml

auto-test: false

test-cmd: pytest tests/

```

6. Output Customization

**Theme Settings:**

```yaml

dark-mode: true

light-mode: false

pretty: true

stream: true

code-theme: monokai # Options: default, monokai, solarized-dark, solarized-light

```

**Color Customization:**

```yaml

user-input-color: "#00cc00"

assistant-output-color: "#0088ff"

tool-error-color: "#FF2222"

tool-warning-color: "#FFA500"

completion-menu-color: "#FFFFFF"

completion-menu-bg-color: "#1E1E1E"

```

7. Caching Configuration

**Enable prompt caching for faster responses:**

```yaml

cache-prompts: true

cache-keepalive-pings: 12 # Ping every 5min, 12 times = 1 hour

```

8. History and Logging

**History Files:**

```yaml

input-history-file: .aider.input.history

chat-history-file: .aider.chat.history.md

restore-chat-history: true

llm-history-file: .aider.llm.history

```

9. Advanced Features

**Voice Input:**

```yaml

voice-format: wav # Options: wav, webm, mp3 (requires ffmpeg)

voice-language: en

```

**Shell Commands:**

```yaml

suggest-shell-commands: true

detect-urls: true

```

**Editor Integration:**

```yaml

editor: vim

vim: true

fancy-input: true

multiline: false

```

**Notifications:**

```yaml

notifications: true

notifications-command: "osascript -e 'display notification \"Aider ready\" with title \"Aider\"'"

```

10. Model Aliases

**Create shortcuts for frequently used models:**

```yaml

alias:

- "fast=gpt-4.1-mini"

- "smart=gpt-4o"

- "cheap=gpt-3.5-turbo"

```

11. Advanced Model Settings

**For reasoning models:**

```yaml

reasoning-effort: medium # For o1 models

thinking-tokens: 10000 # Budget for thinking tokens

```

**Token Limits:**

```yaml

max-chat-history-tokens: 4096 # Soft limit before summarization

```

12. File Management

**Specify files at launch:**

```yaml

file:

- src/main.py

- tests/test_main.py

read:

- README.md

- CONTRIBUTING.md

```

Usage Examples

Basic Configuration

Minimal setup for getting started:

```yaml

model: gpt-4.1-mini

dark-mode: true

auto-commits: true

auto-lint: true

```

Performance-Optimized

Fast responses with caching:

```yaml

model: gpt-4.1-mini

cache-prompts: true

cache-keepalive-pings: 12

map-tokens: 512

stream: true

```

Team Configuration

Standardized settings for a development team:

```yaml

model: gpt-4o

weak-model: gpt-4.1-mini

auto-commits: true

attribute-commit-message-committer: true

auto-lint: true

lint-cmd:

- "python: black . && flake8"

- "javascript: prettier --write . && eslint --fix ."

test-cmd: npm test

auto-test: false

code-theme: monokai

dark-mode: true

```

Architect Mode

For large refactoring tasks:

```yaml

model: gpt-4o

architect: true

auto-accept-architect: false # Review changes manually

map-tokens: 2048

show-diffs: true

```

Important Notes

Constraints