Composable agent runtime with enforced isolation boundaries

Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support

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.