Console

Home / Agents / Aider

Aider

AI pair programming in your terminal

Aider-AI OpenAI-compatible macOSLinuxWindows
Official install page All tools

Aider is an AI pair-programming tool for the terminal; it edits your codebase with repo context and makes git commits for each change. It connects to any OpenAI-compatible endpoint and suits engineers who work from the command line and value git history and repo maps.

Base URL (root)https://quantoport.comPut this in each tool's base_url or *_BASE_URL setting.
OpenAI-compatible pathhttps://quantoport.com/v1Append /v1 for anything speaking the OpenAI wire (/v1/chat/completions).
Recommended modelsdeepseek-v4.1-flashdeepseek-v4-proclaude-sonnet-5Names published in our own catalogue — confirm the live list for your key with GET /v1/models.

Skip it — one-line setup

The script installs Aider from its official source, writes the gateway settings into the tool's own config file (backing up any existing one) and runs a live check. It asks for your gateway key, or take it from --key / --key-file. --uninstall restores exactly what it wrote.

shell
curl -fsSL https://quantoport.com/agents/aider/setup | bash

1 · Install

Install Aider from its own official source.

install
curl -LsSf https://aider.chat/install.sh | sh   # macOS/Linux; Windows: powershell -ExecutionPolicy ByPass -c "irm https://aider.chat/install.ps1 | iex"; or python -m pip install aider-chat

2 · Configure — point it at QuantoPort

Gateway base URL https://quantoport.com; get your key from the console.

config
export OPENAI_API_BASE=https://quantoport.com/v1
export OPENAI_API_KEY=YOUR_API_KEY
aider --model openai/<model-id>

On the China endpoint set OPENAI_API_BASE=https://api.shinlinkai.com/v1 (OpenAI wire only). The openai/ model prefix is required. Equivalent forms: the --openai-api-base / --openai-api-key flags, or openai-api-base / openai-api-key / model keys in ~/.aider.conf.yml.

3 · Verify

One request proves you are on our channel.

verify
aider --model openai/<model-id> --message "reply with OK"

4 · Common pitfalls

  • The model name must carry the openai/ prefix, or requests will not use the OpenAI-compatible route.
  • Aider warns about models it does not recognize; this is expected and does not affect functionality.
  • The China endpoint is OpenAI wire only — do not use aider's Anthropic/Gemini-specific settings there.
  • Override the env vars per run with --openai-api-base / --openai-api-key, or persist them in ~/.aider.conf.yml.

Sources for the tool-side steps: aider.chat/docs/llms/openai-compat.html aider.chat/docs/install.html aider.chat/docs/config/options.html aider.chat/docs/config/aider_conf.html