Repository Showcase
Live demos, project pages, and build notes.
A focused engineering gallery for frontend platform work, AI tooling, LLM cost optimization, and developer productivity experiments. The polished resume and contact profile lives at faraazuddin-mohammed.com.
Featured
tokenometer
Estimate prompt spend before execution and price actual provider usage after each LLM step.
Project Gallery
Click any project for repository context, links, and detail pages.
tokenometer
Estimate prompt spend before execution and price actual provider usage after each LLM step.
routerlab
Route LLM steps by cost and quality, then keep multi-step agent chains inside a running task budget.
promptc
Prompt workflow tooling with an emphasis on repeatability, structure, and regression feedback.
llm-tokens-atlas
Dataset and analysis project for understanding LLM token behavior, context use, and cost implications.
ast-ai-model-router
Model routing experiments for choosing AI providers based on workload, capability, and tradeoffs.
suture
Drop a zero-dependency `.ai/` control plane into a repo to route local coding-agent work by cost, context, and model role.