Bring your own model
An AI terminal for Ollama and LM Studio
Taviraq is provider-neutral. Point it at a local model running in Ollama or LM Studio and keep assistant traffic on your own machine — while still getting explicit context, command-risk checks, and approval before risky commands run.
Local models, treated as a first-class provider
Connect OpenAI-compatible APIs, Ollama, or LM Studio. Taviraq lets you use separate models for chat and for command-risk classification, so you can run a capable local chat model and a smaller, fast model for risk scoring — or the same one for both.
- Ollama — use models you already pulled locally as the assistant backend.
- LM Studio — connect to its local server endpoint the same way.
- Separate risk model — pick a dedicated model for command-risk classification.
- Stay local — when your provider is local, assistant context does not leave your machine.
Safety still applies with local models
The safety layer is independent of the provider. Agent mode checks built-in protected-command patterns and then asks the command-risk model before auto-execution. If classification fails or cannot be parsed, the command is treated as risky and requires confirmation. Risky or unclear commands pause in an in-app confirmation modal before they touch your shell.
Why a local-model terminal
Running models locally keeps prompts and terminal context on your hardware, avoids per-token API costs, and works offline. Combined with local secret masking and Keychain-stored keys, Taviraq is a practical choice when privacy and control matter.