Skip to content
View AnvitDevadiga's full-sized avatar

Achievements

Achievement: QuickdrawAchievement: YOLO

Achievements

Achievement: QuickdrawAchievement: YOLO

Block or report AnvitDevadiga

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
AnvitDevadiga/README.md

Hi, I'm Anvit Devadiga

I'm an AI Engineer building production-ready generative AI and agentic systems.

I focus on building AI that does actual work: retrieving context, using tools, coordinating workflows, and executing code safely. I care just as much about the engineering around the model—clear APIs, resilient integrations, and system reliability—as I do about the models themselves.

What I work with

  • AI & Agents: LangGraph, Model Context Protocol (MCP), tool calling, human-in-the-loop workflows
  • Retrieval & Search: RAG, Chroma, FAISS, Oracle AI Vector Search
  • Backend & Data: Python, TypeScript, FastAPI, PostgreSQL, SQLite, WebSockets
  • Models & Voice: LLM APIs, Ollama, Hugging Face, Whisper, Edge-TTS, scikit-learn
  • Infra: Docker, Git, REST APIs, webhooks

How I build

I design workflows with reliability in mind. That means isolated execution environments, explicit approval gates for external actions, deterministic calculations where accuracy matters, and proper error and rate-limit handling for production APIs.

Pinned Loading

  1. LegalEagle LegalEagle Public

    Offline RAG legal assistant for Indian law — Constitution, IPC & BNS. Powered by Llama 3 + ChromaDB. Zero API cost, zero telemetry.

    Python

  2. spider-sense spider-sense Public

    🕷️ Spider-Sense: An autonomous predictive price intelligence platform. Powered by Bright Data Scraper Studio, it extracts real-time product data across Amazon, Walmart, and Best Buy. It uses scikit…

    Python

  3. msdesk msdesk Public

    Autonomous operational reporting agent built on TrueForge with custom Slack MCP (SSE), sandboxed Python analytics, and human-in-the-loop safety gates.

    JavaScript

  4. Multi-AgentResearchAssistant Multi-AgentResearchAssistant Public

    LangGraph multi-agent pipeline with Search, Summarizer, Critic and Report agents — deployed via FastAPI on Render.com

    Python