Aider · amdai

Aider

Aider-AI. Docs checked 2026-10-12.

Terminal pair-programmer that edits a git repo via any OpenAI-compatible endpoint.

What it’s for

CLI coding in the repo you already have. Prefix the model with openai/.

Local endpoint

llama-server base: http://127.0.0.1:8080/v1
Strata base: http://127.0.0.1:8083/v1
Model name: openai/<model-id>
API key: Required and must be non-empty even locally (OPENAI_API_KEY / --openai-api-key).

Tool calling

Repo edits and git. Unknown models warn until you add .aider.model.settings.yml metadata.

Long context

Set max_input_tokens in model settings if aider does not know the model. Server -c still wins.

ROCm / Radeon gotchas

Aider never talks to the GPU. If it downloads nothing and still fails, curl /v1 first.

Hybrid local + cloud

Yes — cloud OpenAI-shaped providers or local base URL.

This is the same question as the calculator’sfully localversushybridtoggle. This page does not quote cloud prices.

Official links

Sources

Copy-paste

More on the connect page. Prove http://127.0.0.1:8080/v1/models first.

Aider → llama-server :8080

# --openai-api-key must be non-empty even locally.
aider --openai-api-base http://127.0.0.1:8080/v1 \
  --openai-api-key local-not-a-secret \
  --model openai/qwen

Exact llama-server flags for our daily driver stay TODO in stacks.yaml. This is the port only.

Aider → Strata :8083

# --openai-api-key must be non-empty even locally.
aider --openai-api-base http://127.0.0.1:8083/v1 \
  --openai-api-key local-not-a-secret \
  --model openai/qwen

Exact Strata flags for our rig stay TODO in stacks.yaml. This is the port only.