What teams build with openclaw-rs.
openclaw-rs is a Rust runtime for AI agents — event-sourced, sandboxed, single-binary. Here's what people actually ship with it, and which primitives each use case leans on. All facts trace to the project docs; no invented benchmarks.
Migrate off TypeScript OpenClaw
openclaw-rs keeps the same openclaw.json config, Markdown skills, and plugin contract — so migrating from TypeScript OpenClaw is a runtime swap, not a rewrite.
Read the use case →Run AI agents in production on Rust
openclaw-rs is a runtime, not a toolkit: an append-only event store, OS-level sandboxing, and an axum JSON-RPC gateway ship in one binary built for production.
Read the use case →Build a Telegram AI assistant in Rust
The Telegram adapter ships today in openclaw-channels: bridge Claude or GPT to a Telegram bot with allowlist access control and rule-based routing, no Node runtime.
Read the use case →Self-host an AI agent gateway
openclaw-rs is a self-hosted AI gateway: an axum JSON-RPC server with auth, rate limiting, encrypted credentials, and an embedded dashboard — MIT-licensed, on your own box.
Read the use case →Auditable, replayable agent session logs
openclaw-rs stores each session as an append-only SessionEvent log in sled: replayable, auditable, and time-travel-capable across the full run history.
Read the use case →Embed a Rust agent runtime in Node.js
openclaw-node exposes the Rust core to Node.js via napi-rs — providers, credential store, event store, validation, and tool registry — with pre-built binaries.
Read the use case →