ORNL/flowcept
Runtime provenance for AI and scientific workflows—capture, enrich, and query workflow data via observability adapters and code annotation across edge, cloud, and HPC.
This tool helps scientists, machine learning engineers, and data analysts track and understand the execution of their complex AI and scientific workflows. It captures detailed records of what data went into each step, what came out, and how long each part took, even across different computing environments like local machines, cloud, or supercomputers. The output is a clear, human-readable report summarizing the workflow's structure and performance, making it easier to debug, reproduce, and audit results.
Use this if you need to automatically monitor and audit the steps and data flow within your scientific simulations, machine learning training, or data processing pipelines, especially across distributed systems.
Not ideal if you are only running simple, one-off scripts where tracking every input and output is unnecessary, or if you primarily need to monitor infrastructure metrics rather than workflow execution details.
Stars
14
Forks
7
Language
Python
License
MIT
Category
Last pushed
Feb 21, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mlops/ORNL/flowcept"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
flyteorg/flyte
Dynamic, resilient AI orchestration. Coordinate data, models, and compute as you build AI...
TianpeiLuke/cursus
Cursus is an intelligent pipeline generation system that automatically creates complete...
FloomAI/Floom
🌊 Floom, "The K8s for AI", orchestrates & executes Generative AI pipelines, Empowering...
Somi-AI/flowiseai-railway
Flowise AI Railway Template that come with pre-configured persisted volume, PostGIS & private networking.
woodyhayday/FlowSpec
FlowSpec: Automation Workflow Schema - A lightweight JSON schema for defining automations and...