NoCode Workflow
Architected a graph-based multi-agent orchestration framework, replaced 4 weeks of training with minutes of drag-and-drop on a canvas to build customized LLM workflows with traceability, and benefited 1200+ users monthly; listed as a trending space on Hugging Face.
- Reduced processing time by 86% through model routing and by dispatching concurrent LLM batches through Redis-backed Celery workers.
- Solved bugs reported by users and balanced requests against available resources to keep the product meeting real community needs.
- FastAPI + Celery + Redis backend; React/TypeScript (Vite) frontend, deployed to Render.com and HuggingFace Spaces.
- Built-in cost estimator resolves output-token pricing from a Redis cache of the OpenRouter catalogue.
- 500+ stars on GitHub.
- 70+ stars on Hugging Face.