super▌

Orchestrates parallel task execution across up to 12 concurrent Sparky subagents using a rolling pool scheduler. \n \n Parses markdown plan files, extracts task definitions, and launches subagents continuously as slots open without waiting for batch completion \n Maintains canonical file paths and naming constraints across parallel tasks to prevent filename drift and cross-task conflicts \n Validates each subagent result, updates the plan file with completion logs, and immediately schedules the

Save important project knowledge based on what the user wants to preserve.

Search your coding memory for past work, sessions, and implementation details. \n \n Queries personal session memories, project/repo memories, or both in parallel using optional scope flags ( --user , --repo , --both ) \n Returns formatted results with timestamps and relevance scores to help recall previous decisions, implementations, and coding patterns \n Designed for retrieving context about past work when users ask about earlier sessions, how something was implemented, or what they worked on

GPU-optimized OCR using Surya.