Quick Start
1. Add your first Provider
@zlogic.run does not provide models — you need to configure a provider. Keys come from environment variables (on by default) or the system keyring; see Key Management.
The quickest start — export a key:
export DEEPSEEK_API_KEY=sk-...
Keys never go into the configuration file: the variable exported above is matched
to the provider automatically. If you need a custom endpoint, add a provider in
~/.config/zlogic/models.yaml (see Providers & Models
for the full shape):
# ~/.config/zlogic/models.yaml
providers:
my-provider:
sdk: openai_chat
base_url: https://api.openai.com/v1
models:
gpt-4o: {}
DeepSeek and OpenAI are fully tested; the other built-in SDKs are in beta. See Providers & Models.
2. Launch the CLI
zlogic
The TUI starts inside your terminal. Type a message and press Enter to start a
conversation.
Common shortcuts:
| Action | Key |
|---|---|
| Send message | Enter |
| New line | Shift+Enter |
| Cancel / open history | Esc |
| File reference | @ |
| Slash command | / |
| Switch model | /model |
The CLI keeps the real terminal experience: long replies stream into the terminal you are already using, and sensitive actions (writing files, running commands, accessing resources) request your approval right there. See CLI Reference.
3. Try the desktop app
Open the desktop app, create or open a Workspace (any folder), then start a conversation in the Chat view. The desktop adds file browsing, usage stats, visual configuration, the plugin/skill marketplace, local history (checkpoints), managed connections and more. See Choosing CLI vs Desktop.
Next steps
- Point the desktop at a remote engine: Remote daemon
- Extend the agent with Plugins & Skills
- Let the agent answer from your data: Connections
- Review Security & Approvals