Goose · amdai

Goose

Block. Docs checked 2026-10-12.

Local-first agent that can use the OpenAI provider against a custom host, or a declarative JSON provider.

What it’s for

Desktop/CLI agent with recipes. Local path is OpenAI-compatible or Ollama.

Local endpoint

llama-server base: http://127.0.0.1:8080
Strata base: http://127.0.0.1:8083
Model name: GOOSE_MODEL
API key: OPENAI_API_KEY=not-needed

Tool calling

Tool calling depends on the model. Ollama path documents a toolshim; OpenAI-compatible is native function-calling if the server implements it.

Long context

context_limit on a declarative provider. Not documented as auto-detected from llama-server.

ROCm / Radeon gotchas

Goose does not install ROCm. OPENAI_HOST is the host root; OPENAI_BASE_PATH defaults to v1/chat/completions.

Hybrid local + cloud

Yes — 25+ cloud providers plus custom OpenAI host.

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.

Goose → llama-server :8080

# OPENAI_HOST is the host root, not a BASE_URL. Default path is v1/chat/completions.
export OPENAI_HOST=http://127.0.0.1:8080
export OPENAI_BASE_PATH=v1/chat/completions
export OPENAI_API_KEY=not-needed
export GOOSE_MODEL=qwen

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

Goose → Strata :8083

# OPENAI_HOST is the host root, not a BASE_URL. Default path is v1/chat/completions.
export OPENAI_HOST=http://127.0.0.1:8083
export OPENAI_BASE_PATH=v1/chat/completions
export OPENAI_API_KEY=not-needed
export GOOSE_MODEL=qwen

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