“Agent orchestration”

Lists available Cursor agents (planner, architect, tdd-guide, code-reviewer, security-reviewer, build-error-resolver, e2e-runner, refactor-cleaner…

Multi-agent patterns covering task decomposition, agent specialization, result aggregation, error handling, and context sharing

Patterns for chaining agents into structured workflows with handoff documents between stages.

Meta-skill que orquestra todos os agentes do ecossistema.

Open-source desktop workspace that runs, supervises and follows coding agents across git worktrees, from task to merged pull request.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith

Bernstein — Multi-Agent Orchestration

alex-chernysh

Orchestrate parallel AI coding agents from your editor.

MCP-Native LLM Orchestration Agent

Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.

Analyze the user's task and propose the optimal orchestration pattern, then execute it.

Patterns for coordinating multiple LLM agents including sequential, parallel, router, and hierarchical architectures—the AI equivalent of microservicesUse…

Resolve agent ownership and handoff design.

Meta-agent skill for orchestrating complex tasks through autonomous sub-agents.

Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows.

Run a long multi-agent engineering effort as an orchestrator that steers and does not implement.

通过自主子代理编排复杂任务。将宏观任务分解为子任务，生成带有动态 SKILL.md 文件的专用子代理，协调基于文件的通信，整合结果，并在完成后解散代理。强制触发词：orchestrate (编排), multi-agent (多代理), decompose task (分解任务), spawn agents…

Use only when a workflow requires iterative planning, tools, handoffs or state beyond one model call.

Autonomous pipeline manager that orchestrates the entire development workflow.

Use to ship a multi-part change by running several agents IN PARALLEL — fan-out across subagents, each isolated in its own git worktree, then verify-and-merge.

LLM Orchestration Agent

Coordinate multiple OpenClaw agents as one governed system with registry discovery, hierarchy-aware planning, task delegation, and permission boundaries.

Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration.

Use when Codex needs to coordinate multiple agents with roles, task lifecycles, handoff protocols, artifact sharing, or review gates.

Activate for multi-agent swarm coordination recursive agent loops hyperbolic space planning long-horizon task decomposition and parallel Node execution.