Documentation
AI providers
12+ providers, cloud or fully local. Keys in Keychain, streaming responses.
AI in Gisti is optional and pluggable. Summarization (⌘ Y), Chat, and title generation all go through the provider you pick in Settings → AI.
Providers
Cloud (bring an API key):
| Provider | Notes |
|---|---|
| OpenAI | GPT models |
| Anthropic | Claude models |
| Gemini models | |
| Groq | fast open-weights inference |
| DeepSeek | |
| xAI | Grok models |
| Cerebras | |
| Mistral | |
| OpenRouter | one key, many models |
Local (nothing leaves your Mac):
| Provider | Notes |
|---|---|
| Ollama | default http://localhost:11434 |
| LM Studio | OpenAI-compatible local server |
| MLX | any MLX-serve endpoint |
Custom (any OpenAI-compatible endpoint): a home-lab server, a corporate gateway, a tunnel. URL + optional key + model name.
Keys and privacy
- API keys are stored in the macOS Keychain, not in config files.
- Requests go directly from your Mac to the provider: no middleman, no proxy, no telemetry.
- With a local provider, content never leaves the machine. See Privacy.
Behavior
- Responses stream in as they generate.
- Summarization answers in the language of the source text.
- Each request type has its own timeout (summarize 60s, chat 120s by default), tunable in advanced.yaml, along with the prompt templates themselves.