ZeroClaw

ZeroClaw is a dual-licensed MIT OR Apache-2.0 AI assistant framework written in Rust for self-hosted, edge, and infrastructure use. Its architecture defines swappable provider, channel, tool, memory, runtime, and security-policy components through Rust traits. The project connects model providers to command-line and messaging interfaces, while adding memory backends, scheduled work, tools, and controls such as sender pairing, allowlists, encrypted secrets, filesystem scoping, and tunnel-oriented remote exposure.

Current releases provide builds for macOS, Linux on several architectures, Android ARM64, Windows x64 in at least recent release lines, and Linux package formats. The framework is free and open source; users still pay any model, hosting, messaging, tunnel, or external integration charges that apply.

Top features

• Trait-based components: providers, channels, tools, memory, runtimes, and security policies can be replaced behind defined interfaces.
• Provider routing: built-in and OpenAI-compatible adapters support hosted or local model endpoints without fixing the framework to one vendor.
• Messaging and API channels: documented options include CLI, Telegram, Discord, Slack, Matrix, Signal, WhatsApp, email, and webhooks.
• Memory backends: the architecture lists SQLite, PostgreSQL, Markdown, optional external systems, and a no-memory mode.
• Security controls: pairing, channel allowlists, encrypted secrets, scoped filesystem access, sandbox options, and restrictions on public binds are documented.
• Native or Docker runtime: operators can run directly or use a sandboxed container-oriented adapter.
• Cross-platform releases: archives and packages target desktop, server, mobile, and small-board architectures.

Use cases

• Run an assistant gateway on a small server, edge computer, robot controller, or field device.
• Build a messaging bot that can switch model providers and retain local memory.
• Add a custom provider, channel, tool, or policy implementation in Rust behind an existing trait.
• Deploy a self-hosted assistant with explicit sender pairing and egress or filesystem restrictions.
• Validate resource use and platform behavior on the intended target hardware before adoption.