Rust agent runtimes, in depth.
Long-form articles on the primitives behind openclaw-rs, how the runtime is built, and how it compares to TypeScript OpenClaw, LangChain, Mastra, and Rig. Subscribe via RSS.
Event sourcing for AI agents
openclaw-rs stores every session as an append-only log of SessionEvent values in sled. Here's why event sourcing fits agent workloads and what the projection model looks like in Rust.
Why we rewrote OpenClaw in Rust
OpenClaw is a great TypeScript framework. Rewriting it in Rust gave us memory safety, sub-millisecond message routing, and a single-binary deploy story — without breaking the existing plugin contract.
An embedded Vue 3 dashboard inside a Rust gateway
openclaw-ui is a Vue 3 + Vite dashboard that's compiled into the openclaw-gateway binary via rust-embed. Here's why we ship UI inside the runtime and how the embed pipeline works.
Telegram-as-channel — building an allowlisted Rust bot
openclaw-channels ships a complete Telegram Bot API adapter — attachments, allowlisting, rule-based routing. Here's how the channel-adapter shape works in Rust.
AES-256-GCM + Argon2id — how openclaw-rs stores API keys at rest
Encrypted credential storage in Rust: AEAD with AES-256-GCM, Argon2id for key derivation, per-record nonces, 0600 file permissions, and ApiKey wrappers that redact themselves.
Single-binary deployment for AI agents
Why openclaw-rs ships as one statically-linked Rust binary — and what that buys you in container images, cold starts, and ops simplicity compared to a Node.js deployment.
A JSON-RPC 2.0 agent gateway on axum
How openclaw-gateway exposes the same JSON-RPC surface over HTTP and WebSocket using axum, tower middleware, and the embedded Vue 3 dashboard — all in one binary.
Calling Rust from Node — what napi-rs gives you for free
openclaw-node exposes the Rust core to JavaScript via napi-rs. Pre-built binaries, TypeScript definitions, real async, no FFI boilerplate. Here's how it actually works.
Migrating from TypeScript OpenClaw to Rust
How to move a production TypeScript OpenClaw deployment to openclaw-rs without rewriting plugins or changing your config. The compatibility surface is the migration path.
A zero-trust runtime for AI agents
Input validation, secret redaction, fail-secure errors, capability-based tool registration. The defence-in-depth model openclaw-rs uses to make untrusted prompts safe by construction.
Sandboxing Rust agents on Linux, macOS, and Windows
Three platform-specific sandbox backends behind one Rust API — bubblewrap, sandbox-exec, and Job Objects. Here's how openclaw-rs isolates tool execution without locking you to one OS.