Open source

Twelve Python libraries I published — retrieval, agents, scraping, and fallbacks when a model fails.

AgentEnsemble

Multi-agent orchestration. ReAct, Swarm, Pipeline, Debate, WorkflowGraph. Routing, planning, cost tracking.

ragfallback

Stop RAG pipelines from failing silently. Query rewriting, retrieval confidence scoring, fallbacks, retries.

AgentCare

Voice AI for healthcare. Call intake, structured extraction, missing-data recovery, appointment orchestration, post-call analytics.

RAGNav

Hybrid BM25 + dense retrieval with RRF fusion. Navigation-first RAG for long documents.

nepal-gov-agent

Agentic RAG on Nepal government policy and legal documents. Citations, offline-capable, Nepali + English.

scrapeflow-py

Playwright-based web scraping. LLM extraction, hybrid selectors, session persistence, rate limiting, anti-detection.

AskPandas

Natural-language queries on CSV data using local LLMs. No API keys, no cloud.

lingo-nlp-toolkit

Lightweight NLP utilities bridging traditional pipelines and transformer-ready workflows.

PyroChain

Agentic feature engineering. PyTorch + LangChain agents for multimodal feature extraction.

toxic-comment-classifier

Deep learning toxicity detection. Per-category scores for obscene language, threats, insults, identity hate.

socialmediaextractor

Extract social media profile links from websites. Useful for lead enrichment and web intelligence pipelines.

trustpilot-scraper

Scrape Trustpilot reviews programmatically. Structured output for sentiment analysis and competitive research.