The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
Python ai-gatewayanthropicazure-openaibedrockgatewaylangchainlitellmllmllm-gatewayllmopsmcp-gatewayopenaiopenai-proxyrustrust-aivertex-ai
#![allow(
clippy::disallowed_types,
clippy::disallowed_methods,
reason = "a dev-only installer tool that never talks to providers"
)]
mod agent;
mod error;
mod install;
mod session;
mod target;
pub use agent::{
Agent, ClaudeCode, Codex, Configure, Drive, Install, LaunchSpec, Opencode, Outcome, Prompt,
Settings, Usage, Wire,
};
pub use error::Error;
pub use install::{Fetch, HttpFetch, Installed, Installer, Packaging, Release};
pub use semver::Version;
pub use session::Session;
pub use target::{Arch, Os, Target};