open-multi-agent-orchestration — Claude Code skill: AI agent teams

What open-multi-agent-orchestration does

The skill hands your agent working knowledge of open-multi-agent, a TypeScript library for AI agent teams. Agents get separate roles, models and tool sets, while the framework resolves task order through a dependency graph, runs independent steps in parallel and keeps shared memory. Everything stays in one process, so there is no subprocess overhead.

It ships code examples: a single agent via runAgent, a team via createTeam and runTeam, and an explicit task pipeline via runTasks with the dependsOn field. Mixed teams are covered too, with one agent on Anthropic and another on OpenAI, plus custom tools through defineTool() and Zod schemas. Streaming output and progress events are in there as well.

You need a key before the first run: ANTHROPIC_API_KEY is required, OPENAI_API_KEY only if the team includes OpenAI models. The framework itself installs from npm as @jackchen_me/open-multi-agent. When a task fails, everything depending on it is skipped, so put checks on each graph node instead of only at the end.