Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/dallay/corvus/llms.txt

Use this file to discover all available pages before exploring further.

The Fastest AI Agent Framework

Ultra-lightweight Rust runtime. Trait-based architecture. Deploy anywhere.

Why Corvus?

Ultra-Lightweight

<5MB binary with <10ms startup time. 99% smaller than OpenClaw, runs on $10 hardware.

Trait-Based Architecture

Every subsystem is a trait — swap providers, channels, tools, memory, and runtimes with zero code changes.

22+ AI Providers

First-class support for OpenAI, Anthropic, OpenRouter, Ollama, and more. Add any OpenAI-compatible endpoint.

Secure by Design

Gateway pairing, strict sandboxing, allowlists, and workspace scoping. Security-first at every layer.

Get Started

1

Install Corvus

Install via npm, cargo, or download the binary directly.
npx @dallay/corvus --help
2

Run Setup Wizard

Configure your API key and preferences with the interactive onboarding.
corvus onboard --interactive
3

Start Your Agent

Launch the agent and start building autonomous workflows.
corvus agent -m "Hello, Corvus!"

Core Features

AI Providers

Connect to 22+ AI providers with unified trait interface

Messaging Channels

Telegram, Discord, WhatsApp, Slack, and more

Tools & Capabilities

Shell, file operations, memory, browser automation

Hybrid Memory

Vector + keyword search with SQLite or SurrealDB

Secure Sandbox

Docker and native runtimes with strict policies

AIEOS Identity

Portable AI personas with AIEOS v1.1 standard

Explore Documentation

Architecture Overview

Learn about Corvus’s trait-based plugin system and runtime model

Configuration Guide

Configure providers, channels, memory, and security settings

API Reference

Explore the core traits and CLI command reference

Extend Corvus

Build custom providers, channels, tools, and memory backends

Build docs developers (and LLMs) love