Connect Aider to OpenLLM Buddy

Use Aider with OpenLLM Buddy. Set the OpenAI-compatible base URL and key with flags, environment variables, or .aider.conf.yml.

Coding · Integration guide

What is Aider?

Aider is a terminal-based AI pair programmer that reads your repository, edits files, and commits each change to git. Visit Aider.

Why connect OpenLLM Buddy?

Aider works with any OpenAI-compatible server. Prefixing the model with openai/ routes it to your OpenLLM Buddy base URL.

Before you start, create an API key in the console and deploy a model. If anything fails, run the curl test in Step 4 first: no tool can fix a broken endpoint.

1

Install Aider

Install with the official installer, which keeps Aider in its own environment.

Terminal
bash
python -m pip install aider-install
aider-install
2

Run with your endpoint

From inside a git repository, pass the base URL, key, and the model with the openai/ prefix.

Terminal
bash
cd your-project
aider \
  --openai-api-base https://openllmbuddy-proxy.botbuddytech.workers.dev/v1 \
  --openai-api-key YOUR_API_KEY \
  --model openai/gemma4:26b
3

Save the settings

Put the same values in .aider.conf.yml in your repo or home folder so you can just type aider.

.aider.conf.yml
yaml
openai-api-base: https://openllmbuddy-proxy.botbuddytech.workers.dev/v1
openai-api-key: YOUR_API_KEY
model: openai/gemma4:26b

Prefer environment variables for the key: OPENAI_API_BASE and OPENAI_API_KEY. Keep a .aider.conf.yml that contains a key out of version control.

4

Test the endpoint with curl

Confirm the key, URL, and model id work before debugging Aider. A short JSON reply means the endpoint is healthy.

Terminal
bash
curl -sS https://openllmbuddy-proxy.botbuddytech.workers.dev/v1/chat/completions   -H "Authorization: Bearer YOUR_API_KEY"   -H "Content-Type: application/json"   -d '{"model": "gemma4:26b", "messages": [{"role": "user", "content": "Reply with OK"}], "max_tokens": 16}'

Troubleshooting

  • Unknown model warning — Aider does not know the context window of custom models. It still works; add a .aider.model.metadata.json entry to silence the warning.
  • Bad edits — smaller models struggle with Aider's diff formats. Try --edit-format whole or a larger model.
  • 401 or 403 — the API key is wrong, revoked, or missing the Bearer prefix. Create a fresh key in the console.
  • 404 on /chat/completions — the base URL must end in /v1, with no trailing /chat/completions and no extra path.
  • Model not found — the model id must match your deployment exactly. Run the curl test and copy the id you used.
  • Timeouts on the first request — a GPU that was idle may still be loading the model. Retry after a minute.
  • Connection refused from Docker or a remote host — use the public HTTPS base URL, never localhost.

Connection details

Use these values wherever Aider asks for an OpenAI-compatible provider.

Reference
text
Base URL:  https://openllmbuddy-proxy.botbuddytech.workers.dev/v1
Chat URL:  https://openllmbuddy-proxy.botbuddytech.workers.dev/v1/chat/completions
API key:   your key from the console
Model id:  gemma4:26b