Composable agent runtime with enforced isolation boundaries

Multi-language agent runtime and library for execution scope management, lifecycle events, and middleware on tool and LLM calls.

TypeScript multi-agent framework that runs in your own environment: consequential actions wait for approval and every run leaves a verifiable record. Describe the goal, not the graph. 13 built-in providers (Claude, OpenAI, Gemini, DeepSeek and more) plus any OpenAI-compatible endpoint, local models included.