Teach AI how your work actually gets done. Capture real computer work, extract the workflow graph and judgment, then run it with Codex or your own agent.
-
Updated
Jul 31, 2026 - TypeScript
Teach AI how your work actually gets done. Capture real computer work, extract the workflow graph and judgment, then run it with Codex or your own agent.
Dynamic predicate evaluator over agent state dictionaries for dynamic workflow branch routing
Wavefront level scheduler grouping independent DAG tasks into parallel execution stages
Dynamic predicate evaluator over agent state dictionaries for dynamic workflow branch routing
Wavefront level scheduler grouping independent DAG tasks into parallel execution stages
C++20 framework for LLM application and AI agent orchestration: typed components, Chain/Graph workflows, streaming, callbacks, and unified execution.
**comfy_graph_bind** is a visual input mapper for ComfyUI API-format workflows. It provides a Qt-based editor UI that lets you wire a configurable **Start** node to workflow inputs, defining how your application communicates with ComfyUI workflows.
Software engineering agent workflow as an executable graph: 22 skill nodes, 33 edges, a CI-runnable validator, a resume-capable runner protocol, and 30 drop-in skills
Service request graph showing various stages of bidirectional progress.
To associate your repository with the workflow-graph topic, visit your repo's landing page and select "manage topics."