Aider Configuration Template

A comprehensive configuration template for Aider AI pair programming tool. This template covers all available configuration options including model selection, API settings, git integration, output customization, and workflow preferences.

What This Does

Provides a complete `.aider.conf.yml` configuration file template that can be placed in your home directory or at the root of your git repository. Includes settings for:

Instructions

1. **Identify the configuration location**

- For global settings: `~/.aider.conf.yml`

- For project-specific settings: `.aider.conf.yml` at git repository root

2. **Create the base configuration file** with this template:

```yaml

##########################################################

Aider Configuration

Place in home dir or at the root of your git repo

##########################################################

#############

Main model:

Specify the model to use for the main chat

model: openrouter/openai/gpt-4.1

########################

API Keys and settings:

Specify the OpenAI API key

#openai-api-key: xxx

Specify the Anthropic API key

#anthropic-api-key: xxx

Specify the api base url

#openai-api-base: xxx

Set an environment variable (to control API settings, can be used multiple times)

#set-env:

- KEY=value

Set an API key for a provider (eg: --api-key provider=<key> sets PROVIDER_API_KEY=<key>)

#api-key:

- provider=key

#################

Model settings:

Specify a file with aider model settings for unknown models

#model-settings-file: .aider.model.settings.yml

Specify a file with context window and costs for unknown models

#model-metadata-file: .aider.model.metadata.json

Add a model alias (can be used multiple times)

#alias:

- short-name=full-model-name

Set the reasoning_effort API parameter (default: not set)

#reasoning-effort: medium

Verify the SSL cert when connecting to models (default: True)

#verify-ssl: true

Timeout in seconds for API calls (default: None)

#timeout: 120

Specify what edit format the LLM should use (default depends on model)

#edit-format: diff

Use architect edit format for the main chat

#architect: false

Specify the model to use for commit messages and chat history summarization

#weak-model: gpt-4o-mini

Specify the model to use for editor tasks

#editor-model: gpt-4o

#################

Cache settings:

Enable caching of prompts (default: False)

#cache-prompts: false

Number of times to ping at 5min intervals to keep prompt cache warm

#cache-keepalive-pings: 0

###################

Repomap settings:

Suggested number of tokens to use for repo map, use 0 to disable

#map-tokens: 1024

Control how often the repo map is refreshed

Options: auto, always, files, manual (default: auto)

#map-refresh: auto

Multiplier for map tokens when no files are specified

#map-multiplier-no-files: 2

################

History Files:

Specify the chat input history file

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

Specify the chat history file

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

Restore the previous chat history messages

#restore-chat-history: false

Log the conversation with the LLM to this file

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

##################

Output settings:

Use colors suitable for a dark terminal background

#dark-mode: false

Use colors suitable for a light terminal background

#light-mode: false

Enable/disable pretty, colorized output (default: True)

#pretty: true

Enable/disable streaming responses (default: True)

#stream: true

Set the color for user input

#user-input-color: "#00cc00"

Set the color for assistant output

#assistant-output-color: "#0088ff"

Set the markdown code theme

Options: default, monokai, solarized-dark, solarized-light

#code-theme: default

Show diffs when committing changes

#show-diffs: false

###############

Git settings:

Enable/disable looking for a git repo (default: True)

#git: true

Enable/disable adding .aider* to .gitignore (default: True)

#gitignore: true

Specify the aider ignore file

#aiderignore: .aiderignore

Only consider files in the current subtree of the git repository

subtree-only: true

Enable/disable auto commit of LLM changes (default: True)

#auto-commits: true

Enable/disable commits when repo is found dirty (default: True)

#dirty-commits: true

Attribute aider code changes in the git author name

#attribute-author: true

Attribute aider commits in the git committer name

#attribute-committer: true

Attribute aider edits using Co-authored-by trailer

#attribute-co-authored-by: true

Prefix commit messages with 'aider: '

#attribute-commit-message-author: false

Enable/disable git pre-commit hooks with --no-verify

#git-commit-verify: false

Specify a custom prompt for generating commit messages

#commit-prompt: "Write a concise commit message"

########################

Fixing and committing:

Specify lint commands to run for different languages

#lint-cmd:

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

- "javascript: eslint"

Enable/disable automatic linting after changes (default: True)

#auto-lint: true

Specify command to run tests

#test-cmd: pytest

Enable/disable automatic testing after changes

#auto-test: false

############

Analytics:

Permanently disable analytics

#analytics-disable: false

############

Upgrading:

Check for new aider versions on launch

#check-update: true

#################

Voice settings:

Audio format for voice recording (default: wav)

#voice-format: wav

Specify the language for voice using ISO 639-1 code

#voice-language: en

#################

Other settings:

Use VI editing mode in the terminal

vim: true

Specify the language to use in the chat

#chat-language: en

Always say yes to every confirmation

#yes-always: false

Enable verbose output

#verbose: false

Specify the encoding for input and output

#encoding: utf-8

Line endings to use when writing files

Options: platform, unix, dos

#line-endings: platform

Specify the .env file to load

#env-file: .env

Enable/disable suggesting shell commands (default: True)

#suggest-shell-commands: true

Enable/disable fancy input with history and completion

#fancy-input: true

Enable/disable multi-line input mode

#multiline: false

Enable/disable terminal bell notifications

#notifications: false

Enable/disable detection and offering to add URLs to chat

#detect-urls: true

Specify which editor to use for the /editor command

#editor: vim

```

3. **Customize key settings** based on your needs:

**For model selection:**

- Set `model:` to your preferred AI model

- Configure `weak-model:` for faster operations

- Set `editor-model:` for code editing tasks

**For API authentication:**

- Add API keys directly or use environment variables

- Configure `openai-api-base:` for custom endpoints

- Use `api-key:` for provider-specific keys

**For git integration:**

- Enable/disable `auto-commits` for automatic commits

- Configure `attribute-author` and `attribute-committer`

- Set `subtree-only: true` to limit scope to current directory

**For linting and testing:**

- Define `lint-cmd:` for your languages

- Set `test-cmd:` for your test runner

- Enable `auto-lint` and `auto-test` as needed

4. **Set up environment variables** (optional)

- Create a `.env` file in your git root for API keys

- Reference it with `env-file: .env`

- Use `set-env:` to configure API settings

5. **Test the configuration**

- Run `aider` in your project directory

- Verify settings with `aider --verbose`

- Check model selection with `/model`

Examples

**Minimal configuration for OpenRouter:**

```yaml

model: openrouter/anthropic/claude-3.5-sonnet

subtree-only: true

auto-commits: true

vim: true

```

**Configuration for team projects:**

```yaml

model: gpt-4o

weak-model: gpt-4o-mini

auto-lint: true

lint-cmd:

- "python: ruff check --fix"

- "typescript: eslint --fix"

test-cmd: npm test

auto-test: false

attribute-co-authored-by: true

```

**Configuration with custom colors:**

```yaml

model: claude-3-5-sonnet-20241022

dark-mode: true

user-input-color: "#00ff00"

assistant-output-color: "#00aaff"

code-theme: monokai

show-diffs: true

```

Important Notes

Configuration Validation

After creating your config file:

1. Run `aider --verbose` to see which settings are active

2. Use `aider --show-prompts` to verify model configuration

3. Check `aider --help` to see all available options

Constraints