Busbar is the execution control plane for AI agents. Unlike LLM gateways that only route model requests, Busbar governs model calls, MCP tool calls, A2A delegation, and downstream actions, adding policy, identity, approvals, and audit. Bring your existing SDK. Six native LLM protocols in and six out, with no rewrites or lowest-common-denominator translation. Self-hosted, Apache-2.0, one static Rust binary.
Busbar is a single binary you run in your own infrastructure, sitting between your applications and every AI provider. One endpoint to route and fail over chat, embeddings, images, and audio across providers, enforce hard budget caps, provision or revoke access, and see every request’s cost, latency, and traffic.
BusbarControl what AI can do before it acts
