Ronin is a Claude-Code-style terminal agent: it reads, edits, and runs your code, and every write sits behind a diff you approve. The stack is provider-agnostic, so the same agent runs on Claude when you want quality, or free on Gemini / Cerebras / Groq / Ollama. --offline strips every network tool for air-gapped work.
Multi-provider is the point, not a toggle:
- Consensus — several models run the same task; a judge returns one cross-checked answer
- Dojo — rival models each attempt the change in isolated git worktrees; a judge keeps the best diff
- Kaizen — the agent finds a weakness in its own source, patches it in a worktree, and keeps the diff only if tests pass
Python → 7-package monorepo → 1,376 offline tests → MCP + 200 plugins
If you only click one link on this profile: star / clone Ronin.
AI/ML engineer in Charlotte. I ship agents and production ML — APIs, cloud, real users — not notebook demos.
Most of that energy now goes into Ronin. The other systems below are how I learned to put LLM and ML systems on the internet and keep them there.
rohith = {
"location" : "Charlotte, NC",
"education" : "MS Information Technology, University of Cincinnati (GPA: 3.89)",
"cert" : "AWS Solutions Architect Associate",
"currently" : "Building Ronin. Shipping the rest.",
"status" : "Open to AI Engineer | GenAI | LLM roles (US)",
}|
Agentic RAG over PubMed. Searches, pulls papers, synthesizes clinical answers with Claude Sonnet, streamed live. |
Two-tower PyTorch + BPR, candidate generation, LightGBM rerank, Kafka on Kubernetes. |
|
Scores LinkedIn posts for corporate cringe, roasts them, rewrites them like a human. |
PyTorch NN + LSTM ensemble, SHAP, drift detection that retrains when the distribution moves. |
|
LangGraph agents for real-time risk scoring and an audit trail on every decision. |
🚌 MR BusesInterstate booking plus an AI chatbot that knows routes and can help you book. |
| System | Status | Response |
|---|---|---|
| RO MedRAG | 🔴 DOWN | n/a |
| BullshiftDetector | 🟢 LIVE | 126 ms |
| MR Buses | 🟢 LIVE | 115 ms |
| RO Fraud Detection | 🔴 DOWN | n/a |
🤖 Checked automatically every 6 hours by GitHub Actions · last run 2026-09-22 21:14 UTC
- Ronin · pushed 2026-09-21 · Masterless, terminal-native coding agent (Claude Code-style: reads, edits, runs code) f…
- RohiRo · pushed 2026-08-18 · ro · a personal agent operating system.
- Ro-Resume-Agent · pushed 2026-07-05 · AI resume builder + ATS scorer.
- .github · pushed 2026-06-11 · Community health defaults
- agentfaceoff · pushed 2026-06-11 · Live LLM battle arena · same prompt to two models, token-by-token split-screen streamin…
flowchart LR
subgraph Data["📥 Data & Retrieval"]
Docs[Docs & APIs] --> VS[(FAISS · pgvector · hybrid search)]
Events[Events] --> Kafka[Kafka] --> CH[(ClickHouse / BigQuery)]
end
subgraph Brain["🧠 Agents & Models"]
VS --> LG[LangGraph / Ronin planner]
LG <--> Claude[Claude · Gemini · Groq · Ollama]
PT[PyTorch Two-Tower / LSTM] --> LGB[LightGBM Rerank]
end
subgraph Evals["🧪 Evals & Observability"]
LG --> EV[golden sets · LLM-as-judge]
EV --> LF[Langfuse: traces · cost · drift]
end
subgraph Serve["🚀 Serving & Infra"]
LG --> API[FastAPI + SSE]
LGB --> API
API --> UI[Next.js / React]
API --> Cloud[GCP · AWS] --> K8s[Kubernetes + Terraform]
end
Core
| Credential | Details |
|---|---|
| Claude with Google Cloud's Vertex AI | Anthropic Education · May 2026 |
| Claude 101 | Anthropic · Apr 2026 |
| AI Fluency: Framework & Foundations | Anthropic · Apr 2026 |
| AWS Certified Solutions Architect – Associate | Amazon Web Services · May 2025 (exp. May 2028) |
| MS, Information Technology | University of Cincinnati · GPA 3.89 · Dec 2024 |
| Deep Learning Specialization | Andrew Ng / DeepLearning.AI · 2024 |
| LangChain & LLM Agents for Production | DeepLearning.AI · 2024 |
Ronin is the open-source line. The portfolio talks back if you want the rest of the story.