tmf set — Direct Configuration
Syntax
bash
tmf set <app> --baseUrl <url> --key <api-key> [options]Description
tmf set directly configures an AI application without relying on the Provider API. Unlike tmf use, which routes through the cloud provider registry, set allows you to point any supported app at an arbitrary API endpoint — ideal for self-hosted models, custom proxies, or providers not yet in the registry.
Before writing, the current config is automatically backed up (.bak), and you can restore it with tmf rollback.
Options
| Option | Description |
|---|---|
--baseUrl <url> | Required. Base URL for the API endpoint |
-k, --key <api-key> | Required. API key |
-m, --model <model> | Single model name |
--models <models...> | Multiple models: opus=X,sonnet=Y,haiku=Z or positional |
--env <env...> | Custom env vars to set (KEY=VALUE format) |
--effort <level> | Effort level: low, medium, high, xhigh |
--save-as <name> | Save parameters as a reusable template |
Supported Apps
The <app> argument accepts any supported application name: codex, claude-code (aliases: claude, cc), openclaw, opencode, hermes, pi.
Examples
bash
# Point Claude Code at a self-hosted Ollama instance
tmf set claude-code --baseUrl https://ollama.local/v1 --key ollama
# Configure OpenCode CLI with a custom proxy
tmf set opencode --baseUrl https://proxy.example.com/v1 --key sk-xxx --model gpt-4o
# Set up Hermes with role-based models and save as template
tmf set hermes --baseUrl https://api.deepseek.com/v1 --key sk-xxx \
--models opus=deepseek-v4-pro,sonnet=deepseek-v4-pro,haiku=deepseek-v4-flash \
--save-as deepseek