zeroclaw

ZeroClaw is a personal AI assistant infrastructure distributed as a single Rust binary. It functions as an agent runtime configured and run on your own hardware, retaining full ownership of the agent, data, and machine. Core capabilities include: - Multi-channel communication: One agent can answer across 30+ configured channels. Inbound messages from Discord, Telegram, Matrix, email, webhooks, and CLI are delivered to the same agent loop. - Provider-agnostic LLM support: Pluggable model providers include Anthropic, OpenAI, local Ollama, and any OpenAI-compatible endpoint. Fallback chains and routing keep the agent running if a provider fails. - Security-first design: Default autonomy mode is supervised, requiring approval for medium-risk operations and blocking high-risk ones. Features include workspace boundaries, command policy, OS-level sandboxes (Landlock, Bubblewrap, Seatbelt, Docker), and cryptographic tool receipts for every action. - YOLO mode: Exist for trusted development environments. - Hardware capability: Supports Raspberry Pi, STM32, Arduino, and ESP32 via the Peripheral trait via GPIO, I2C, SPI, and USB. - Gateway and dashboard: HTTP/WebSocket gateway for clients with a web dashboard for chat, memory browsing, config editing, cron management, and tool inspection. - SOP engine: Event-triggered Standard Operating Procedures via MQTT, webhook, cron, or peripheral events, with approval gates and resumable runs. - IDE integration: Agent Client Protocol support via JSON-RPC 2.0 over stdio for editor integration. Configuration is managed via a single TOML file. The runtime uses SQLite and embeddings for memory. Installed as a system service via systemd, launchctl, or Windows Service. Dual-licensed under MIT and Apache 2.0.