Building a Library-First AI Agent SDK in Rust

Description and use

A Rust SDK for AI agents that can be embedded in services, reduces memory usage, and supports extensions via a stable C ABI.

Need an embeddable, performant Rust agent runtime instead of a TypeScript/Node CLI that hits memory limits on low‑spec servers.

The Rust SDK enables embedding an AI agent into services, reduces memory usage, and allows plugin extensions via stable C ABI.

1. Design library‑first architecture with crates: rpi‑ai, rpi‑agent, rpi‑tools, rpi‑harness, rpi‑cli.
2. Implement minimal agent example using FauxProvider (no API key).
3. Define custom tool (AddTool) and integrate via AgentBuilder.
4. Bridge async Provider to sync StreamFn for compatibility.
5. Run example with cargo run and observe streaming output.
6. Replace FauxProvider with real provider (Anthropic/OpenAI) for production use.
7. Extend with native Rust cdylib plugins via rpi‑plugin‑sdk ABI.
8. Install extensions with rpi install <name> and use in CLI or embedded runtime.

I was running an agent on a low-spec server and kept hitting memory limits. So I ported the core runtime to Rust.

rpi is split into independent crates. Each layer can be used on its own: rpi‑ai, rpi‑agent, rpi‑tools, rpi‑harness, rpi‑cli.

Run it with: cargo run