Roo Code

Roo Code. Docs checked 2026-10-12. Local-models page documents Ollama and LM Studio specifically.

VS Code coding agent. Local path is documented for Ollama and LM Studio; OpenAI Compatible is also documented.

What it’s for

In-editor agent with filesystem and terminal tools.

Local endpoint

llama-server base: http://127.0.0.1:8080/v1
Strata base: http://127.0.0.1:8083/v1
Model name: Model ID on the OpenAI Compatible provider
API key: Required field in the OpenAI Compatible UI

Tool calling

Native OpenAI tool calling is required — Roo’s docs say a model without it cannot be used.

Long context

Not documented as a Roo-side control.

ROCm / Radeon gotchas

Same as Cline — you own the server. Official Ollama ROCm is rocky on gfx1201; prefer llama-server Vulkan.

Hybrid local + cloud

Yes — many cloud providers plus local Ollama / LM Studio / OpenAI Compatible.

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.

Roo Code → llama-server :8080

Provider: OpenAI Compatible
Base URL: http://127.0.0.1:8080/v1
API Key: local-not-a-secret
Model ID: qwen
# Roo docs: native OpenAI tool calling is required.
# Official local-models page names Ollama and LM Studio specifically.

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

Roo Code → Strata :8083

Provider: OpenAI Compatible
Base URL: http://127.0.0.1:8083/v1
API Key: local-not-a-secret
Model ID: qwen
# Roo docs: native OpenAI tool calling is required.
# Official local-models page names Ollama and LM Studio specifically.

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