open-web-agent-rs/README.md

open-web-agent-rs

A Rust-based web agent with an embedded OpenAI-compatible inference server (supports Gemma models only).

Project Structure

This project is organized as a Cargo workspace with the following crates:

• agent-server: The main web agent server
• local_inference_engine: An embedded OpenAI-compatible inference server for Gemma models

Setup

1. Clone the repository
2. Copy the example environment file:

   cp .env.example .env
   

3. Install JavaScript dependencies:

   bun i
   

4. Start the SearXNG search engine:

   docker compose up -d searxng
   

Running the Project

Local Inference Engine

To run the local inference engine:

cd crates/local_inference_engine
cargo run --release -- --server

Agent Server

To run the agent server:

cargo run -p agent-server

Development Mode

For development with automatic reloading:

bun dev

Building

To build all crates in the workspace:

cargo build

To build a specific crate:

cargo build -p agent-server
# or
cargo build -p local_inference_engine