Triple-C is a cross-platform desktop application that sandboxes Claude Code inside Docker containers. Each project can optionally enable full permissions mode (`--dangerously-skip-permissions`), giving Claude unrestricted access within the sandbox.
- **AWS Bedrock**: Per-project AWS credentials (static keys, profile, or bearer token). SSO sessions are validated before launching Claude for Profile auth.
- **Ollama**: Connect to a local or remote Ollama server via `ANTHROPIC_BASE_URL` (e.g., `http://host.docker.internal:11434`). Requires a model ID, and the model must be pulled (or used via Ollama cloud) before starting the container.
- **OpenAI Compatible**: Connect through any OpenAI API-compatible endpoint (LiteLLM, OpenRouter, vLLM, text-generation-inference, LocalAI, etc.) via `ANTHROPIC_BASE_URL` + `ANTHROPIC_AUTH_TOKEN`. API key stored securely in OS keychain.
> **Note:** Ollama and OpenAI Compatible support is best-effort. Claude Code is designed for Anthropic models, so some features (tool use, extended thinking, prompt caching, etc.) may not work as expected with non-Anthropic models behind these backends.
When "Allow container spawning" is enabled per-project, the host Docker socket is bind-mounted into the container. This allows Claude Code to create **sibling containers** (not nested Docker-in-Docker) that are visible to the host. The entrypoint detects the socket's GID and adds the `claude` user to the matching group.
If the Docker access setting is toggled after a container already exists, the container is automatically recreated on next start to apply the mount change. The named config volume (keyed by project ID) is preserved across recreation.
Triple-C supports [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) servers as a Beta feature. MCP servers extend Claude Code with external tools and data sources.
- **Auto-pull**: Docker images for MCP servers are pulled automatically if not present when the project starts
- **Docker networking**: Docker-based MCP containers run on a per-project bridge network (`triple-c-net-{projectId}`), reachable by container name — not localhost
- **Config injection**: MCP server configuration is written to `~/.claude.json` inside the container via the `MCP_SERVERS_JSON` environment variable, merged by the entrypoint using `jq`
Optional per-project integration with Flight Control — an AI-first development methodology bundled with Triple-C. When enabled, the bundled files are installed into the container, skills are installed, and workflow instructions are injected into CLAUDE.md.
Triple-C includes an optional web terminal server for accessing project terminals from tablets, phones, or other devices on the local network. When enabled in Settings, an axum HTTP+WebSocket server starts inside the Tauri process, serving a standalone xterm.js-based terminal UI.
- **Session cleanup**: All terminal sessions are closed when the browser disconnects
The web terminal shares the existing `ExecSessionManager` via `Arc`-wrapped stores — same Docker exec sessions, different transport (WebSocket instead of Tauri IPC events).
Triple-C includes optional speech-to-text powered by [Faster Whisper](https://github.com/SYSTRAN/faster-whisper) running in a separate Docker container. When enabled, a microphone button appears in the bottom-left corner of each terminal view.
- **Hotkey**: `Ctrl+Shift+M` to toggle recording
- **Models**: `tiny`, `small`, or `medium` (configurable in Settings)
- **Port**: Default `9876` (configurable)
- **Language**: Optional language hint for transcription
- **Auto-start**: When STT is enabled in Settings, the container starts automatically with the app — no need to manually start it after each restart
- **On-demand fallback**: If not auto-started, the container starts automatically when you first click the mic button
**How it works**: Audio is captured in the browser via the Web Audio API, encoded as WAV, and sent to the Faster Whisper container's `/transcribe` endpoint. The transcribed text is inserted directly into the active terminal. The STT container uses a named Docker volume (`triple-c-stt-model-cache`) to cache Whisper models across restarts.
