SuperAPI AI Directory

longgraph

Agents & models

View repository

Updated 10-15 23:59

About this skill

longgraph — route to the right durable run

longgraph has one shared compiler, loop-graph, and focused entries that bind only goal-specific rules. All compile the same executor, supervisor, ledger, directives, and ops artifacts. Do not execute the generated runtime nodes from this authoring skill.

Fit and route

  • Use loop-converge for multi-round unused code, duplication, consolidation, reuse, or slimming.
  • Use loop-deliver for a product or engineering requirement that needs incremental implementation and acceptance proof.
  • Use loop-research to compare feasible approaches with open-source implementations, primary research, and controlled experiments before committing to one.
  • Use loop-graph directly only when none of the focused packs fits but the work still needs durable state, gates, owner boundaries, host switching, or independent verification.
  • If the request is one self-contained task that fits a normal host goal/task, explain that longgraph adds no value and recommend sending the task directly. Do not wrap it in another objective or invent a lighter longgraph mode.

Shared reference: lib/methodology.md explains why the graph's discipline exists. The baseline and pack boundary is in skills/loop-graph/docs/preset-contract.md.