### Install Aider with pip

Source: https://aider.chat/docs/install.html

Standard pip installation, recommended for use within a virtual environment.

```bash
python -m pip install -U --upgrade-strategy only-if-needed aider-chat
```

--------------------------------

### Install Aider via one-liner scripts

Source: https://aider.chat/docs/install.html

Quick installation for Mac, Linux, and Windows using shell or PowerShell scripts.

```bash
curl -LsSf https://aider.chat/install.sh | sh
```

```bash
wget -qO- https://aider.chat/install.sh | sh
```

```powershell
powershell -ExecutionPolicy ByPass -c "irm https://aider.chat/install.ps1 | iex"
```

--------------------------------

### Start Aider with LM Studio Model

Source: https://aider.chat/docs/llms/lm-studio.html

Navigate to your project directory and start Aider, specifying the LM Studio model to use.

```bash
# Change directory into your codebase
cd /to/your/project

```

```bash
aider --model lm_studio/<your-model-name>

```

--------------------------------

### Quick Start Aider with Copilot

Source: https://aider.chat/docs/llms/github.html

Navigate to your project directory and start Aider, specifying a Copilot model like 'openai/gpt-4o'.

```bash
# change into your project
cd /to/your/project

# talk to Copilot
aider --model openai/gpt-4o
```

--------------------------------

### Install Aider Locally from Source

Source: https://aider.chat/docs/faq.html

Clone the repository, navigate to the directory, create a virtual environment, and install aider in editable mode to run from the latest source files.

```bash
# Clone the repository
git clone git@github.com:Aider-AI/aider.git

# Navigate to the project directory
cd aider

# It's recommended to make a virtual environment

# Install aider in editable/development mode, 
# so it runs from the latest copy of these source files
python -m pip install -e .

# Run the local version of aider
python -m aider
```

--------------------------------

### Start Ollama Server and Aider

Source: https://aider.chat/docs/llms/ollama.html

Commands to pull a model, start the Ollama server with an increased context length, and then start Aider in your project directory using an Ollama model.

```bash
# Pull the model
ollama pull <model>
```

```bash
# Start your ollama server, increasing the context window to 8k tokens
OLLAMA_CONTEXT_LENGTH=8192 ollama serve
```

```bash
# In another terminal window, change directory into your codebase
cd /to/your/project
```

```bash
aider --model ollama_chat/<model>
```

--------------------------------

### Install Aider

Source: https://aider.chat/docs/llms/deepseek.html

Install the aider package using pip. This is the first step before configuring API keys.

```bash
python -m pip install aider-install
aider-install

```

--------------------------------

### Start Aider with OpenAI Compatible API

Source: https://aider.chat/docs/llms/openai-compat.html

Navigate to your project directory and start aider, prefixing the model name with openai/. This command initiates a session with your configured API.

```bash
# Change directory into your codebase
cd /to/your/project

# Prefix the model name with openai/
aider --model openai/<model-name>

```

--------------------------------

### Install and Launch Aider Browser UI

Source: https://aider.chat/docs/usage/browser.html

Install the aider-chat package and set your API key before launching the browser UI. Ensure you restart your shell after setting the API key on Windows.

```bash
python -m pip install -U aider-chat
```

```bash
export OPENAI_API_KEY=<key> # Mac/Linux
```

```bash
setx   OPENAI_API_KEY <key> # Windows, restart shell after setx
```

```bash
aider --browser
```

--------------------------------

### Install Aider

Source: https://aider.chat/docs/llms/gemini.html

Install the Aider package using pip.

```bash
python -m pip install aider-install
aider-install
```

--------------------------------

### Install Aider with pipx

Source: https://aider.chat/docs/install.html

Use pipx to install Aider in an isolated environment.

```bash
python -m pip install pipx  # If you need to install pipx
pipx install aider-chat
```

--------------------------------

### Ask/Code Workflow Example

Source: https://aider.chat/docs/usage/modes.html

Demonstrates a typical ask/code workflow where initial discussion and planning occur in ask mode, followed by code edits in code mode. The example shows two interactions in ask mode to refine a print statement, followed by two terse commands in code mode to apply the changes.

```bash
> /ask What's the best thing to print if we're making a quick little demo program?

It sounds like you'd like to write a "Hello, world!" program. That's a very
popular phrase to use for small demo programs.

> /ask Yes, that's the idea. What are some more creative options?

1. "Greetings, Earthlings!"
2. "Beep boop, I am a computer!"
3. "To code, or not to code, that is the question."
4. "I think, therefore I print."
5. "01001000 01101001!" (Binary for "Hi!")

> do 4

hello.py
>>>>>>> SEARCH
=======
def main():
    print("I think, therefore I print.")
<<<<<<< REPLACE

> ALL CAPS!

hello.py
>>>>>>> SEARCH
    print("I think, therefore I print.")
=======
    print("I THINK, THEREFORE I PRINT!")
<<<<<<< REPLACE

```

--------------------------------

### Start Aider with Grok 3 Models

Source: https://aider.chat/docs/llms/xai.html

Navigate to your project directory and start Aider using different xAI Grok 3 models. Choose the model that best suits your needs for speed and cost.

```bash
# Change directory into your codebase
cd /to/your/project

# Grok 3
aider --model xai/grok-3-beta

# Grok 3 fast (faster, more expensive)
aider --model xai/grok-3-fast-beta

# Grok 3 Mini
aider --model xai/grok-3-mini-beta

# Grok 3 Mini fast (faster, more expensive)
aider --model xai/grok-3-mini-fast-beta

```

--------------------------------

### Start Aider with OpenRouter Model

Source: https://aider.chat/docs/llms/openrouter.html

Navigate to your project directory and start aider using an OpenRouter model. You can specify a provider and model, or list available models.

```bash
# Change directory into your codebase
cd /to/your/project

```

```bash
# Or any other open router model
aider --model openrouter/<provider>/<model>

```

```bash
# List models available from OpenRouter
aider --list-models openrouter/

```

--------------------------------

### Update Markdown Documentation

Source: https://aider.chat/docs/usage/not-code.html

Add an installation section to a README file.

```markdown
+ ## Installation
+ ```
+ # Homebrew
+ brew install cool-app-10k
+ 
+ # PyPI
+ pipx install cool-app-10k
+ ```
```

--------------------------------

### Install Aider with uv

Source: https://aider.chat/docs/install.html

Use the uv tool manager to install Aider with a specific Python version.

```bash
python -m pip install uv  # If you need to install uv
uv tool install --force --python python3.12 --with pip aider-chat@latest
```

--------------------------------

### Install Aider

Source: https://aider.chat/docs/llms/cohere.html

Install the aider package using pip. This command is used to set up the aider tool for your project.

```bash
python -m pip install aider-install

```

```bash
aider-install

```

--------------------------------

### Start Aider with DeepSeek Chat v3

Source: https://aider.chat/docs/llms/deepseek.html

Navigate to your project directory and start Aider, specifying the DeepSeek Chat v3 model using the --model flag.

```bash
# Change directory into your codebase
cd /to/your/project

# Use DeepSeek Chat v3
aider --model deepseek/deepseek-chat

```

--------------------------------

### Install Boto3 Dependency

Source: https://aider.chat/docs/llms/bedrock.html

Install the required boto3 package using various package managers.

```bash
# If you installed with aider-install or `uv tool`
uv tool run --from aider-chat pip install boto3

# Or with pipx...
pipx inject aider-chat boto3

# Or with pip
pip install -U boto3
```

--------------------------------

### Install Aider with Pipx on Replit

Source: https://aider.chat/docs/troubleshooting/imports.html

Use these commands to install and run Aider with pipx in a Replit environment. This helps manage dependencies separately.

```bash
pip install pipx
pipx run aider-chat ...normal aider args...

```

--------------------------------

### Start Aider with Cohere

Source: https://aider.chat/docs/llms/cohere.html

Begin using Aider with the Cohere Command-R+ model. Navigate to your project directory first. This command initializes Aider for your codebase.

```bash
# Change directory into your codebase
cd /to/your/project

```

```bash
aider --model command-r-plus-08-2024

```

--------------------------------

### Start Aider with specific models

Source: https://aider.chat/docs/install.html

Initialize Aider within a project directory using specific AI models and API keys.

```bash
# Change directory into your codebase
cd /to/your/project

# DeepSeek
aider --model deepseek --api-key deepseek=<key>

# Claude 3.7 Sonnet
aider --model sonnet --api-key anthropic=<key>

# o3-mini
aider --model o3-mini --api-key openai=<key>
```

--------------------------------

### Start Aider with Groq Llama 3 70B

Source: https://aider.chat/docs/llms/groq.html

Begin an aider session using the Groq Llama 3 70B model. Ensure you are in your project's root directory before running this command.

```bash
# Change directory into your codebase
cd /to/your/project

aider --model groq/llama3-70b-8192

```

--------------------------------

### Install and Run Aider with Pipx on Replit

Source: https://aider.chat/docs/install/replit.html

Use these commands in the Replit shell to install pipx and then run Aider Chat. Ensure you replace '...normal aider args...' with your specific Aider arguments.

```bash
pip install pipx
pipx run aider-chat ...normal aider args...
```

--------------------------------

### Configure Anthropic API Key

Source: https://aider.chat/docs/llms/anthropic.html

Environment variable setup for Mac/Linux and Windows systems.

```bash
export ANTHROPIC_API_KEY=<key> # Mac/Linux
setx   ANTHROPIC_API_KEY <key> # Windows, restart shell after setx
```

--------------------------------

### Configure Azure o3-mini Model Settings

Source: https://aider.chat/docs/config/reasoning.html

This example shows how to configure Aider to use 'o3-mini' via Azure. It includes settings for `use_temperature: false`, which is often a requirement for reasoning models. The configuration also specifies `weak_model_name`, `editor_model_name`, and other provider-specific details.

```yaml
- name: azure/o3-mini
  edit_format: diff
  weak_model_name: azure/gpt-4o-mini
  use_repo_map: true
  use_temperature: false             # <--- 
  editor_model_name: azure/gpt-4o
  editor_edit_format: editor-diff
  accepts_settings: ["reasoning_effort"]

```

--------------------------------

### Run Aider with Gemini Models

Source: https://aider.chat/docs/llms/gemini.html

Commands to start Aider with specific Gemini models or list available models.

```bash
# Change directory into your codebase
cd /to/your/project

# You can run the Gemini 2.5 Pro model with this shortcut:
aider --model gemini

# You can run the Gemini 2.5 Pro Exp for free, with usage limits:
aider --model gemini-exp

# List models available from Gemini
aider --list-models gemini/
```

--------------------------------

### Example Source Code

Source: https://aider.chat/docs/unified-diffs.html

This is the original source code before any edits are applied. It includes a function with a comment and a print statement.

```python
import sys

def main(args):
    # show a greeting
    print("Hello!")
    return

main(sys.argv[1:])

```

--------------------------------

### Example Repository Map Structure

Source: https://aider.chat/docs/repomap.html

A partial representation of a repository map showing class and method signatures for specific files.

```text
aider/coders/base_coder.py:
⋮...
│class Coder:
│    abs_fnames = None
⋮...
│    @classmethod
│    def create(
│        self,
│        main_model,
│        edit_format,
│        io,
│        skip_model_availabily_check=False,
│        **kwargs,
⋮...
│    def abs_root_path(self, path):
⋮...
│    def run(self, with_message=None):
⋮...

aider/commands.py:
⋮...
│class Commands:
│    voice = None
│
⋮...
│    def get_commands(self):
⋮...
│    def get_command_completions(self, cmd_name, partial):
⋮...
│    def run(self, inp):
⋮...
```

--------------------------------

### Start Aider and Request Code Changes

Source: https://aider.chat/docs/usage.html

Initiate an Aider session by providing a source file. Aider will then prompt you to describe the code changes you need.

```bash
$ aider factorial.py

Aider v0.37.1-dev
Models: gpt-4o with diff edit format, weak model gpt-3.5-turbo
Git repo: .git with 258 files
Repo-map: using 1024 tokens
Use /help to see in-chat commands, run with --help to see cmd line args
───────────────────────────────────────────────────────────────────────
> Make a program that asks for a number and prints its factorial

...
```

--------------------------------

### Example of Reasoning Tagged Output

Source: https://aider.chat/docs/config/reasoning.html

Illustrates how a model's reasoning output is wrapped in a specified XML tag, like '<think>', and how Aider processes it separately from other output.

```xml
<think>
The user wants me to greet them!
</think>

Hello!

```

--------------------------------

### Pip Dependency Conflict Example

Source: https://aider.chat/docs/troubleshooting/imports.html

This is an example of a dependency conflict message that may appear when installing packages with pip.

```text
aider-chat 0.23.0 requires somepackage==X.Y.Z, but you have somepackage U.W.V which is incompatible.

```

--------------------------------

### AI Comment for Refactoring a Function

Source: https://aider.chat/docs/usage/watch.html

This example demonstrates using 'ai refactor...' comments to guide the LLM in refactoring existing code into a new function.

```python
# ai refactor...
```

```python
# ... to compute_factorial() ai!
```

--------------------------------

### AI Comment Syntax Examples

Source: https://aider.chat/docs/usage/watch.html

Examples of one-liner comments that Aider monitors for instructions.

```text
# Make a snake game. AI!
# What is the purpose of this method AI?
```

```text
// Write a protein folding prediction engine. AI!
```

--------------------------------

### Run Aider with Qwen2.5 Coder 14B Instruct (Whole)

Source: https://aider.chat/docs/leaderboards/edit.html

Execute Aider with the 'openai/Qwen2.5-Coder-14B-Instruct' model, which uses the 'whole' edit format.

```bash
aider --model openai/Qwen2.5-Coder-14B-Instruct
```

--------------------------------

### Display Aider startup information

Source: https://aider.chat/docs/troubleshooting.html

Use the output printed at startup to provide version and model details when reporting issues.

```text
Aider v0.37.1-dev
Models: gpt-4o with diff edit format, weak model gpt-3.5-turbo
Git repo: .git with 243 files
Repo-map: using 1024 tokens
```

--------------------------------

### Example Shared Chat URL

Source: https://aider.chat/docs/faq.html

An example of a complete URL that displays an Aider chat history in a web format.

```markdown
https://aider.chat/share/?mdurl=https://gist.github.com/Aider-AI/2087ab8b64034a078c0a209440ac8be0
```

--------------------------------

### Install PortAudio on Mac

Source: https://aider.chat/docs/install/optional.html

Install the PortAudio library on macOS using Homebrew for Aider's voice coding feature.

```bash
brew install portaudio
```

--------------------------------

### Run Aider with Qwen2.5 Coder 7B Instruct (Whole)

Source: https://aider.chat/docs/leaderboards/edit.html

This command launches Aider with the 'openai/Qwen2.5-Coder-7B-Instruct' model, configured for the 'whole' edit format.

```bash
aider --model openai/Qwen2.5-Coder-7B-Instruct
```

--------------------------------

### Install Playwright Chromium

Source: https://aider.chat/docs/install/optional.html

Install Playwright's Chromium browser and its dependencies to enable Aider to scrape all web pages effectively, especially those relying on JavaScript.

```bash
playwright install --with-deps chromium
```

--------------------------------

### Configure Aider with Reasoning Models

Source: https://aider.chat/docs/config/reasoning.html

Use command-line arguments to specify the model and its reasoning parameters like thinking tokens or effort.

```bash
# Sonnet uses a thinking token budget
aider --model sonnet --thinking-tokens 8k

# o3-mini uses low/medium/high reasoning effort
aider --model o3-mini --reasoning-effort high

# R1 doesn't have configurable thinking/reasoning
aider --model r1

```

--------------------------------

### Run Aider with Azure Models

Source: https://aider.chat/docs/llms/azure.html

Initialize Aider in a project directory and list available Azure models.

```bash
# Change directory into your codebase
cd /to/your/project

aider --model azure/<your_model_deployment_name>

# List models available from Azure
aider --list-models azure/
```

--------------------------------

### Configure Aider IO for Python

Source: https://aider.chat/docs/scripting.html

Use the InputOutput class to configure settings like automatic confirmation.

```python
from aider.io import InputOutput
io = InputOutput(yes=True)
# ...
coder = Coder.create(model=model, fnames=fnames, io=io)
```

--------------------------------

### Sample .env File Configuration for Aider

Source: https://aider.chat/docs/config/dotenv.html

This sample .env file demonstrates how to configure various aspects of aider, including LLM parameters, API keys, model settings, cache, repomap, and history files. Place this file at the root of your git repository or specify its location using the --env-file parameter.

```dotenv
##########################################################
# Sample aider .env file.
# Place at the root of your git repo.
# Or use `aider --env <fname>` to specify.
##########################################################

#################
# LLM parameters:
#
# Include xxx_API_KEY parameters and other params needed for your LLMs.
# See https://aider.chat/docs/llms.html for details.

## OpenAI
#OPENAI_API_KEY=

## Anthropic
#ANTHROPIC_API_KEY=

##...

#############
# Main model:

## Specify the model to use for the main chat
#AIDER_MODEL=

########################
# API Keys and settings:

## Specify the OpenAI API key
#AIDER_OPENAI_API_KEY=

## Specify the Anthropic API key
#AIDER_ANTHROPIC_API_KEY=

## Specify the api base url
#AIDER_OPENAI_API_BASE=

## (deprecated, use --set-env OPENAI_API_TYPE=<value>)
#AIDER_OPENAI_API_TYPE=

## (deprecated, use --set-env OPENAI_API_VERSION=<value>)
#AIDER_OPENAI_API_VERSION=

## (deprecated, use --set-env OPENAI_API_DEPLOYMENT_ID=<value>)
#AIDER_OPENAI_API_DEPLOYMENT_ID=

## (deprecated, use --set-env OPENAI_ORGANIZATION=<value>)
#AIDER_OPENAI_ORGANIZATION_ID=

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

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

#################
# Model settings:

## List known models which match the (partial) MODEL name
#AIDER_LIST_MODELS=

## Specify a file with aider model settings for unknown models
#AIDER_MODEL_SETTINGS_FILE=.aider.model.settings.yml

## Specify a file with context window and costs for unknown models
#AIDER_MODEL_METADATA_FILE=.aider.model.metadata.json

## Add a model alias (can be used multiple times)
#AIDER_ALIAS=

## Set the reasoning_effort API parameter (default: not set)
#AIDER_REASONING_EFFORT=

## Set the thinking token budget for models that support it. Use 0 to disable. (default: not set)
#AIDER_THINKING_TOKENS=

## Verify the SSL cert when connecting to models (default: True)
#AIDER_VERIFY_SSL=true

## Timeout in seconds for API calls (default: None)
#AIDER_TIMEOUT=

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

## Use architect edit format for the main chat
#AIDER_ARCHITECT=

## Enable/disable automatic acceptance of architect changes (default: True)
#AIDER_AUTO_ACCEPT_ARCHITECT=true

## Specify the model to use for commit messages and chat history summarization (default depends on --model)
#AIDER_WEAK_MODEL=

## Specify the model to use for editor tasks (default depends on --model)
#AIDER_EDITOR_MODEL=

## Specify the edit format for the editor model (default: depends on editor model)
#AIDER_EDITOR_EDIT_FORMAT=

## Only work with models that have meta-data available (default: True)
#AIDER_SHOW_MODEL_WARNINGS=true

## Check if model accepts settings like reasoning_effort/thinking_tokens (default: True)
#AIDER_CHECK_MODEL_ACCEPTS_SETTINGS=true

## Soft limit on tokens for chat history, after which summarization begins. If unspecified, defaults to the model's max_chat_history_tokens.
#AIDER_MAX_CHAT_HISTORY_TOKENS=

#################
# Cache settings:

## Enable caching of prompts (default: False)
#AIDER_CACHE_PROMPTS=false

## Number of times to ping at 5min intervals to keep prompt cache warm (default: 0)
#AIDER_CACHE_KEEPALIVE_PINGS=false

###################
# Repomap settings:

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

## Control how often the repo map is refreshed. Options: auto, always, files, manual (default: auto)
#AIDER_MAP_REFRESH=auto

## Multiplier for map tokens when no files are specified (default: 2)
#AIDER_MAP_MULTIPLIER_NO_FILES=true

################
# History Files:

## Specify the chat input history file (default: .aider.input.history)
#AIDER_INPUT_HISTORY_FILE=.aider.input.history

## Specify the chat history file (default: .aider.chat.history.md)
#AIDER_CHAT_HISTORY_FILE=.aider.chat.history.md

## Restore the previous chat history messages (default: False)
#AIDER_RESTORE_CHAT_HISTORY=false

## Log the conversation with the LLM to this file (for example, .aider.llm.history)
#AIDER_LLM_HISTORY_FILE=

##################
# Output settings:

```

--------------------------------

### Run Aider with o3-pro

Source: https://aider.chat/docs/leaderboards

Command to initialize Aider using the o3-pro model.

```bash
aider --model o3-pro
```

--------------------------------

### Install PortAudio on Linux

Source: https://aider.chat/docs/install/optional.html

Install the PortAudio library on Linux systems for Aider's voice coding feature. Some Linux environments may also require the ALSA sound plugins.

```bash
sudo apt-get install libportaudio2
```

```bash
sudo apt install libasound2-plugins
```

--------------------------------

### Initialize Aider with specific models

Source: https://aider.chat/docs/leaderboards/edit.html

Use these commands to launch Aider with a specific model. Some models require provider prefixes or specific API base configurations.

```bash
aider --model gpt-3.5-turbo-0301
```

```bash
aider --model gpt-4-turbo-2024-04-09
```

```bash
aider --model gemini/gemini-1.5-pro-latest
```

```bash
aider --model gpt-3.5-turbo-1106
```

```bash
aider --model gpt-4o-mini
```

```bash
aider --model together_ai/qwen/Qwen2-72B-Instruct
```

```bash
aider --model openrouter/x-ai/grok-2-mini
```

```bash
aider --sonnet
```

```bash
aider --model bedrock/us.amazon.nova-pro-v1:0
```

```bash
aider --model ollama/qwen2.5:32b
```

```bash
aider --model openai/hf:01-ai/Yi-Coder-9B-Chat --openai-api-base https://glhf.chat/api/openai/v1
```

```bash
aider --model gemini/gemini-1.5-flash-exp-0827
```

```bash
aider --model ollama/qwen2.5-coder:7b-instruct-q8_0
```

```bash
aider --model gemini/gemini-1.5-flash-002
```

```bash
aider --model mistral/codestral-2405
```

```bash
aider --model gpt-3.5-turbo-0613
```

```bash
aider -3
```

```bash
aider --model ollama/qwen2:72b-instruct-q8_0
```

```bash
aider --model groq/llama3-70b-8192
```

```bash
aider --model Codestral-22B-v0.1-Q4_K_M
```

```bash
aider --model ollama/codestral:22b-v0.1-q8_0
```

```bash
aider --model claude-3-haiku-20240307
```

```bash
aider --model ollama/codestral
```

```bash
aider --model ollama/yi-coder:9b-chat-q4_0
```

```bash
aider --model gemini/gemini-1.5-flash-latest
```

```bash
aider --model openrouter/microsoft/wizardlm-2-8x22b
```

```bash
aider --model ollama/yi-coder:9b-chat-fp16
```

```bash
aider --model openai/Qwen2.5-Coder-3B-Instruct
```

```bash
aider --model ollama/mistral-small
```

```bash
aider --model gemini/gemini-1.5-flash-8b-exp-0924
```

```bash
aider --model command-r-08-2024
```

```bash
aider --model command-r-plus-08-2024
```

```bash
aider --model gemini/gemini-1.5-flash-8b-exp-0827
```

```bash
aider --model fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct
```

```bash
aider --model together_ai/qwen/qwen1.5-110b-chat
```

```bash
aider --model ollama/gemma2:27b-instruct-q8_0
```

```bash
aider --model ollama/codeqwen:7b-chat-v1.5-q8_0
```

```bash
aider --model ollama/mistral-nemo:12b-instruct-2407-q4_K_M
```

```bash
aider --model ollama/codegeex4
```

```bash
aider --model openai/Qwen2.5-Coder-1.5B-Instruct
```

```bash
aider --model command-r-plus
```

```bash
aider --model ollama/hermes3:8b-llama3.1-fp16
```

```bash
aider --model ollama/wojtek/opencodeinterpreter:6.7b
```

```bash
aider --model o1-mini
```

```bash
aider --model ollama/tulu3
```

```bash
aider --model ollama/llama3.2:3b-instruct-fp16
```

```bash
aider --model ollama/hermes3
```

```bash
aider --model ollama/granite3-dense:8b
```

```bash
aider --model openai/Qwen2.5-Coder-0.5B-Instruct
```

--------------------------------

### Initialize Aider with OpenAI Models

Source: https://aider.chat/docs/llms/openai.html

Commands to launch Aider within a project directory using specific OpenAI models or to list available models.

```bash
# Change directory into your codebase
cd /to/your/project

# o3-mini
aider --model o3-mini

# o1-mini
aider --model o1-mini

# GPT-4o
aider --model gpt-4o

# List models available from OpenAI
aider --list-models openai/
```

--------------------------------

### Run Aider with Qwen-2.5 72B Instruct (Diff)

Source: https://aider.chat/docs/leaderboards/edit.html

Command to run Aider with the 'openrouter/qwen/qwen-2.5-72b-instruct' model, utilizing the 'diff' edit format.

```bash
aider --model openrouter/qwen/qwen-2.5-72b-instruct
```

--------------------------------

### Modify Docker Setup

Source: https://aider.chat/docs/usage/not-code.html

Update Dockerfile and docker-compose.yml for security and service configuration.

```dockerfile
+ USER appuser
+ HEALTHCHECK --interval=30s --timeout=3s \
+   CMD curl -f http://localhost:8000/health || exit 1
```

```yaml
  services:
    postgres:
      image: postgres:15
+     ports:
+       - "5432:5432"
+     volumes:
+       - pgdata:/var/lib/postgresql/data
```

--------------------------------

### List Available xAI Models

Source: https://aider.chat/docs/llms/xai.html

Use the '--list-models' flag with a xAI provider prefix to see all available models from xAI.

```bash
# List models available from xAI
aider --list-models xai/

```

--------------------------------

### In-context Instruction Example

Source: https://aider.chat/docs/usage/watch.html

Adding an AI comment directly within a function to request specific changes.

```javascript
app.get('/sqrt/:n', (req, res) => {
    const n = parseFloat(req.params.n);

    // Add error handling for NaN and less than zero. AI!

    const result = math.sqrt(n);
    res.json({ result: result });
});
```

--------------------------------

### Implement Function via AI Comment

Source: https://aider.chat/docs/usage/watch.html

Example of using an AI comment to trigger the implementation of a function.

```javascript
function factorial(n) // Implement this. AI!
```

```javascript
function factorial(n) {
  if (n === 0 || n === 1) {
    return 1;
  } else {
    return n * factorial(n - 1);
  }
}
```

--------------------------------

### Markdown Code Block Example

Source: https://aider.chat/docs/faq.html

Illustrates the standard markdown format for code blocks using triple backticks.

```markdown
Here's some code:

```
print("hello")
```


```

--------------------------------

### Run Aider with Anthropic

Source: https://aider.chat/docs/llms/anthropic.html

Commands to initialize Aider in a project directory and list available Anthropic models.

```bash
# Change directory into your codebase
cd /to/your/project

# Aider uses Claude 3.7 Sonnet by default
aider

# List models available from Anthropic
aider --list-models anthropic/
```

--------------------------------

### Add Factorial Function

Source: https://aider.chat/docs/usage/modes.html

Adds a recursive Python function to calculate the factorial of a number. Includes example usage.

```python
def factorial(n):
    if n == 0 or n == 1:
        return 1
    else:
        return n * factorial(n - 1)

# Example usage
print(factorial(5))  # Output: 120
```

--------------------------------

### Run Aider with Qwen 2.5 Coder (OpenRouter)

Source: https://aider.chat/docs/leaderboards/edit.html

Command to run Aider with the 'openrouter/qwen/qwen-2.5-coder-32b-instruct' model, utilizing the 'diff' edit format.

```bash
aider --model openrouter/qwen/qwen-2.5-coder-32b-instruct
```

--------------------------------

### Minimal Variable Rename Diff

Source: https://aider.chat/docs/unified-diffs.html

A surgical diff example showing a variable rename across multiple lines.

```text
@@ ... @@
-def factorial(n):
+def factorial(number):
-    if n == 0:
+    if number == 0:
         return 1
     else:
-        return n * factorial(n-1)
+        return number * factorial(number-1)
```

--------------------------------

### Capture script execution output

Source: https://aider.chat/docs/usage/lint-test.html

Example of a Python traceback captured after running a script via the /run command.

```text
Traceback (most recent call last):  
 File "myscript.py", line 22, in <module> 
   raise ValueError("something bad happened")  
ValueError: something bad happened
```

--------------------------------

### Run Aider with Grok 3 Mini Beta

Source: https://aider.chat/docs/leaderboards

Execute this command to utilize the Grok 3 Mini Beta model through OpenRouter. Verify your OpenRouter configuration.

```bash
aider --model openrouter/x-ai/grok-3-mini-beta
```

--------------------------------

### List supported models with Aider

Source: https://aider.chat/docs/llms/other.html

Use the --list-models flag to search for available models matching a partial name.

```bash
$ aider --list-models turbo

Aider v0.29.3-dev
Models which match "turbo":
- gpt-4-turbo-preview (openai/gpt-4-turbo-preview)
- gpt-4-turbo (openai/gpt-4-turbo)
- gpt-4-turbo-2024-04-09 (openai/gpt-4-turbo-2024-04-09)
- gpt-3.5-turbo (openai/gpt-3.5-turbo)
- ...
```

--------------------------------

### Multiple AI Comments Example

Source: https://aider.chat/docs/usage/watch.html

Using multiple AI comments across a file to coordinate complex refactoring tasks.

```python
@app.route('/factorial/<int:n>')
def factorial(n):
    if n < 0:
        return jsonify(error="Factorial is not defined for negative numbers"), 400

    # AI: Refactor this code...

    result = 1
    for i in range(1, n + 1):
        result *= i

    # ... into to a compute_factorial() function. AI!

    return jsonify(result=result)
```

--------------------------------

### Enable Analytics Opt-in

Source: https://aider.chat/docs/more/analytics.html

Use this command to trigger the initial opt-in prompt for analytics collection.

```bash
aider --analytics

Aider respects your privacy and never collects your code, prompts, chats, keys or any personal
info.
For more info: https://aider.chat/docs/more/analytics.html
Allow collection of anonymous analytics to help improve aider? (Y)es/(N)o [Yes]:
```

--------------------------------

### High-Level Variable Rename Diff

Source: https://aider.chat/docs/unified-diffs.html

A high-level diff example that presents the entire function body for better context and accuracy.

```text
@@ ... @@
-def factorial(n):
-    if n == 0:
-        return 1
-    else:
-        return n * factorial(n-1)
+def factorial(number):
+    if number == 0:
+        return 1
+    else:
+        return number * factorial(number-1)
```

--------------------------------

### Sample Aider YAML Configuration

Source: https://aider.chat/docs/config/aider_conf.html

A comprehensive sample of the `.aider.conf.yml` file, illustrating all valid configuration entries. This file can be placed in your home directory or the root of your git repository.

```yaml
##########################################################
# Sample .aider.conf.yml
# This file lists *all* the valid configuration entries.
# Place in your home dir, or at the root of your git repo.
##########################################################

# Note: You can only put OpenAI and Anthropic API keys in the YAML
# config file. Keys for all APIs can be stored in a .env file
# https://aider.chat/docs/config/dotenv.html

##########
# options:

## show this help message and exit
#help: xxx

#############
# Main model:

## Specify the model to use for the main chat
#model: xxx

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

## (deprecated, use --set-env OPENAI_API_TYPE=<value>)
#openai-api-type: xxx

## (deprecated, use --set-env OPENAI_API_VERSION=<value>)
#openai-api-version: xxx

## (deprecated, use --set-env OPENAI_API_DEPLOYMENT_ID=<value>)
#openai-api-deployment-id: xxx

## (deprecated, use --set-env OPENAI_ORGANIZATION=<value>)
#openai-organization-id: xxx

## Set an environment variable (to control API settings, can be used multiple times)
#set-env: xxx
## Specify multiple values like this:
#set-env:
#  - xxx
#  - yyy
#  - zzz

## Set an API key for a provider (eg: --api-key provider=<key> sets PROVIDER_API_KEY=<key>)
#api-key: xxx
## Specify multiple values like this:
#api-key:
#  - xxx
#  - yyy
#  - zzz

#################
# Model settings:

## List known models which match the (partial) MODEL name
#list-models: xxx

## 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: xxx
## Specify multiple values like this:
#alias:
#  - xxx
#  - yyy
#  - zzz

## Set the reasoning_effort API parameter (default: not set)
#reasoning-effort: xxx

## Set the thinking token budget for models that support it. Use 0 to disable. (default: not set)
#thinking-tokens: xxx

## Verify the SSL cert when connecting to models (default: True)
#verify-ssl: true

## Timeout in seconds for API calls (default: None)
#timeout: xxx

## Specify what edit format the LLM should use (default depends on model)
#edit-format: xxx

## Use architect edit format for the main chat
#architect: false

## Enable/disable automatic acceptance of architect changes (default: True)
#auto-accept-architect: true

## Specify the model to use for commit messages and chat history summarization (default depends on --model)
#weak-model: xxx

## Specify the model to use for editor tasks (default depends on --model)
#editor-model: xxx

## Specify the edit format for the editor model (default: depends on editor model)
#editor-edit-format: xxx

## Only work with models that have meta-data available (default: True)
#show-model-warnings: true

## Check if model accepts settings like reasoning_effort/thinking_tokens (default: True)
#check-model-accepts-settings: true

## Soft limit on tokens for chat history, after which summarization begins. If unspecified, defaults to the model's max_chat_history_tokens.
#max-chat-history-tokens: xxx

#################
# Cache settings:

## Enable caching of prompts (default: False)
#cache-prompts: false

## Number of times to ping at 5min intervals to keep prompt cache warm (default: 0)
#cache-keepalive-pings: false

###################
# Repomap settings:

## Suggested number of tokens to use for repo map, use 0 to disable
#map-tokens: xxx

## 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 (default: 2)
#map-multiplier-no-files: true

################
# History Files:

## Specify the chat input history file (default: .aider.input.history)
#input-history-file: .aider.input.history
```

--------------------------------

### Diff edit format example

Source: https://aider.chat/docs/more/edit-formats.html

The diff format uses search/replace blocks with the file path specified before the fenced block.

```text
mathweb/flask/app.py
<<<<<<< SEARCH
from flask import Flask
=======
import math
from flask import Flask
>>>>>>> REPLACE
```

--------------------------------

### Run Aider with Ollama Qwen2.5 Coder 7B (Whole)

Source: https://aider.chat/docs/leaderboards/edit.html

Command to run Aider with the 'ollama/Qwen2.5.1-Coder-7B-Instruct-GGUF:Q8_0-32k' model, utilizing the 'whole' edit format.

```bash
aider --model ollama/Qwen2.5.1-Coder-7B-Instruct-GGUF:Q8_0-32k
```

--------------------------------

### Run Aider with Gemini 2.5 Pro

Source: https://aider.chat/docs/leaderboards

Command to initialize Aider using the Gemini 2.5 Pro model with specific thinking token configuration.

```bash
aider --model gemini/gemini-2.5-pro-preview-06-05 --thinking-tokens 32k
```

--------------------------------

### Unified Diff Hunk Example

Source: https://aider.chat/docs/unified-diffs.html

A representation of a unified diff hunk used for search and replace operations without line numbers.

```text
@@ ... @@
 def main(args):
     # show a greeting
-    print("Hello!")
+    print("Goodbye!")
     return
```