# Engineering projects

Every project catalogued on https://ravicha2.github.io, grouped by how strongly its headline figure is settled. A project measured to an artifact quotes that artifact and pins it to a commit; one in progress says so rather than being quietly graded down.

Categories: Graph & Knowledge, Distributed Systems, Agentic AI & MCP, Robotics, Full-Stack.

## Measured to an artifact

- [NL2REGEX: Distributed Regex Engine](https://ravicha2.github.io/projects/nl2regex/): Distributed natural language to regex engine that transforms complex tabular dataset patterns using plain English, backed by PySpark and Celery with schema-validated triage. **172 cases** — backend tests over the API, Spark projection, Parquet normalization, and ReDoS safety. [github](https://github.com/Ravicha2/NL2REGEX)
- [Fault-Tolerant Document Ingestion Agent](https://ravicha2.github.io/projects/document-ingestion-agent/): Production-grade event-driven AI ingestion engine using Inngest durable steps, NestJS, and dual pgvector/Neo4j storage to eliminate orphaned state during multi-stage document processing. **8** — durable Inngest steps across 4 worker functions, each retryable on its own. [github](https://github.com/Ravicha2/document-ingestion-agent)
- [Lit-Review-Council MCP Server](https://ravicha2.github.io/projects/lit-review-council/): Multi-agent research synthesis engine and Model Context Protocol (MCP) server that orchestrates parallel academic and practitioner research with Borda-count consensus. **PyPI** — published, install via uvx lit-review-council; listed on the MCP Registry. [github](https://github.com/Ravicha2/lit-review-council) · [pypi](https://pypi.org/project/lit-review-council/)

## In progress and not yet settled

- [Shepherd: GraphRAG Compliance Engine](https://ravicha2.github.io/projects/shepherd/): End-to-end ADR violation detector for AI-generated code, ingesting source ASTs and architectural markdown documents into a Neo4j property graph to catch multi-file constraint conflicts. **23.3% → 43.8%** — pooled precision across the five-repo two-arm benchmark (baseline reviewer vs the CPT engine). [github](https://github.com/Ravicha2/Shepherd)

## Supporting work

- [Chatbot Agent with Dynamic DB Tools](https://ravicha2.github.io/projects/node-api/): Conversational AI agent capable of dynamic database schema inspection and tool calling to safely query and mutate structured data. **3 tables / 5 operations** — SQL surface exposed to the agent as typed tools. [github](https://github.com/Ravicha2/node-api)
- [6-DOF Robotic Arm for Ultrasonography Training](https://ravicha2.github.io/projects/robotic-arm-ultrasound/): Developed and tested a 6-degree-of-freedom passive robotic arm probe tracking system to measure position and orientation accuracy during ultrasound medical training. **2023** — IEEE TENCON publication and conference presentation. [paper](https://ieeexplore.ieee.org/document/10349000)
- [Heal: Community Mental Health Support](https://ravicha2.github.io/projects/heal-a2a/): Community mental health peer support platform recognized with the Founder's Choice Award at the Hack2Heal Hackathon. **Live** — deployed at heal.a2a.ing. [demo](https://heal.a2a.ing)

---

## Fetching the rest of this site

- This page as HTML: <https://ravicha2.github.io/projects/>
- Concise index: <https://ravicha2.github.io/llms.txt>
- Full dossier: <https://ravicha2.github.io/llms-full.txt>
- When to use this material: <https://ravicha2.github.io/agents.md>
- API description (OpenAPI 3.1): <https://ravicha2.github.io/openapi.json>
- API reference: <https://ravicha2.github.io/docs/>
- Sitemap: <https://ravicha2.github.io/sitemap.xml>
