stream-chain

Stream-Chain orchestrates multi-agent pipelines by passing each agent's output as input to the next, enabling complex sequential workflows. Define custom chains or use predefined pipelines (Analysis, Refactor, Test, Optimize) where context flows continuously between steps, maintaining continuity across transformations like code analysis, refactoring, and test generation.

Yes. Stream-Chain supports streaming data flow across sequential prompts, allowing you to coordinate multi-agent pipelines where streaming context propagates from one step to the next. This enables sophisticated data transformations and complex processing pipelines difficult for single agents to handle.

Use Stream-Chain's predefined pipelines or custom chains to run sequential tasks: analyze codebase structure, identify improvements, generate tests, and optimize performance. Each step builds on the previous output with full context propagation, structured progress tracking, timing data, and a final summary.

Stream-Chain depends on claude-flow as its orchestration foundation, leveraging it to coordinate multi-agent execution, enforce per-step context propagation, and support configurable execution controls like verbose mode, timeouts, and debug settings.

Stream-Chain provides configurable execution controls including verbose output, timeout settings, and debug mode. These settings apply across your custom chains or predefined pipelines, giving you visibility into each step and control over execution flow, timing, and error handling.

Use predefined pipelines (Analysis, Refactor, Test, Optimize) for standard development tasks with proven workflows. Use custom chains for maximum flexibility when your sequential processing needs don't fit standard patterns or require specialized task combinations.