Work Archive
Repository-backed systems and applied ML work.
The archive now focuses on real project repos instead of placeholder demos, with work spanning chat infrastructure and causal inference pipelines.
AI Infrastructure
Meridian
2026
An intelligent AI chat router that auto-selects the best free model for each prompt, streams responses over SSE, and supports user-configured providers with Supabase-backed sessions and history.
Providers
10+
Guest Limit
20 reqs
Streaming
SSE
Project highlights
- Automatic prompt difficulty routing across free OpenRouter models
- Real-time streaming chat responses via Server-Sent Events
- Multi-provider support with custom keys and compatible API endpoints
Next.js 16React 19FastAPIOpenRouterSupabaseTypeScript
Machine Learning
Treatment Effect Estimation
2026
A causal inference pipeline for IHDP treatment-effect estimation, covering naive baselines, S/T/X-learners, manual DML, EconML estimators, policy analysis, and reproducible evaluation artifacts for ATE and CATE.
Methods
6+
Dataset
IHDP
Outputs
ATE/CATE
Project highlights
- Reusable preprocessing pipeline for IHDP with aligned scaling and train/test splits
- ATE and CATE estimation with S-Learner, T-Learner, X-Learner, and propensity baselines
- Manual DML plus EconML LinearDML and CausalForestDML implementations
PythonEconMLDoWhyscikit-learnSHAPPandas