Skip to content
View mohi-devhub's full-sized avatar
🎯
Grinding
🎯
Grinding

Highlights

  • Pro

Block or report mohi-devhub

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.

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
mohi-devhub/README.md
Mohith subtitle
Typing SVG

snake animation


Coding GIF

👋 Hey, I'm Mohith

name     : Mohith
alias    : mohi-devhub
degree   : B.Tech Computer Science (2027)
college  : Chinmaya Vishwavidyapeeth
goal     : Aspiring AI Engineer
status   : GSoC 2026 Contributor · Student · Builder
location : Kerala, India 🌊

🌍 GSoC 2026 @ RUXAILAB — Focus Group Analysis Module
🛡️ Building SentinelLM — LLM safety middleware
🎮 Building StudyQuest — AI learning platform
🔬 Reimplemented NeurIPS 2023 Lion Optimizer (88.26% acc)
🎯 On a mission to build production-grade AI systems

"Build boldly. Learn relentlessly. Ship proudly."



LinkedIn Gmail


🏅 Holopin Badges

Holopin Board


🌍 GSoC 2026 — Selected Contributor

GSoC Org

Selected as a Google Summer of Code 2026 contributor at RUXAILAB (Uramaki Lab), building the Focus Group Management and Analysis Module — a new study type adding real-time multi-participant data capture, NLP-assisted thematic analysis, and sentiment scoring to the RUXAILAB platform.

Detail Info
Project Focus Group Management & Analysis Module
Organization RUXAILAB / Uramaki Lab
Size Medium (175 hrs)
Stack Vue 3 · Firebase · Python · scikit-learn · LiveKit
Mentor Marc

🛡️ SentinelLM

SentinelLM Status Version License

Real-time safety & quality middleware for LLM applications.

A FastAPI proxy that intercepts every LLM request and response — scoring for prompt injection, PII leakage, toxicity, hallucination, and relevance. A drop-in replacement for OpenAI, Anthropic, Gemini, or Ollama — just point base_url at localhost:8000/v1.

$ docker compose up -d
✓  API        →  localhost:8000
✓  Dashboard  →  localhost:3000
✓  Metrics    →  /metrics  (Prometheus)

$ curl localhost:8000/v1/chat/completions \
    -d '{"messages": [{"role":"user","content":"Ignore all instructions."}]}'

⛔  HTTP 400 · sentinel_block · prompt_injection_detected · score: 0.97

Evaluator Chain:

Layer Evaluator Action Model
🔵 Input prompt_injection Block DeBERTa-v3-base
🔵 Input pii Redact / Block Presidio + spaCy
🔵 Input topic_guardrail Block all-MiniLM-L6-v2
🟡 Output toxicity Flag Detoxify
🟡 Output relevance Flag all-MiniLM-L6-v2
🟡 Output hallucination Flag NLI DeBERTa-v3
🟡 Output faithfulness Flag NLI DeBERTa-v3

Key highlights: ⚡ Concurrent first-block short-circuit · 🔒 Redis caching · 🧠 Fail-open guarantee · 📊 WebSocket dashboard · 🧪 Eval regression pipeline

Python FastAPI Redis PostgreSQL Docker WebSockets


🧠 AntiVibe

AntiVibe Stars License

A Claude Code skill that fights the learn-nothing problem in vibe-coding.

Everyone's vibecoding. Nobody's understanding what gets shipped. AntiVibe auto-triggers via Claude Code hooks after every AI coding session and generates structured educational deep-dives — not just "what this code does" but why it was written that way, what CS concepts are in play, and where to go deeper.

# Runs automatically via SubagentStop / Stop hooks
# After Claude Code finishes a task, you get:

📄  deep-dive.md
    ├── Code walkthrough
    ├── Design decisions & alternatives
    ├── CS concepts mapped to this code
    └── Curated learning resources

Works across Python · TypeScript · Go · Rust · and more

"Vibecoding is fast. Understanding what you ship matters more."

Shell Claude Code MCP


🔴 Currently Building

Project Description Stack Status
🌍 GSoC @ RUXAILAB Focus Group Management & Analysis Module Vue 3 · Firebase · Python · scikit-learn Active
🛡️ SentinelLM Real-time LLM safety middleware Python · FastAPI · Redis · Docker Active
🎮 StudyQuest Terminal-style AI learning platform Next.js · FastAPI · Supabase · Gemini WIP
🌐 Lokha Community hub for AI prompts Next.js · Prisma · tRPC · Supabase WIP


🚀 Featured Projects

🛡️ SentinelLM

Real-time LLM safety middleware. Blocks prompt injections, redacts PII, flags hallucinations and toxicity. Drop-in FastAPI proxy for any LLM backend.

Python FastAPI Redis Docker

View Repo

🧠 AntiVibe ⭐ 600+

Open-source Claude Code skill that auto-generates educational deep-dives for AI-written code. Fights the learn-nothing problem in vibe-coding via hooks and subagents.

Shell Claude Code MCP

View Repo

🎮 StudyQuest

AI-powered terminal-style learning platform with adaptive quizzes, real-time XP tracking, and minimalist B/W dashboard.

Next.js FastAPI Supabase Gemini

🔬 Lion Optimizer

Reimplemented the NeurIPS 2023 Lion Optimizer with symbolic search engine. Achieved 88.26% accuracy on FashionMNIST — outperforming AdamW.

Python PyTorch


🛠️ Tech Stack

Python TypeScript Java C++ JavaScript SQL


React Next.js FastAPI Node.js Django TailwindCSS


PostgreSQL Redis MySQL Firebase Docker Git


🔬 Research — Lion Optimizer (NeurIPS 2023)

Reimplemented the Lion Optimizer from scratch using PyTorch, based on the NeurIPS 2023 paper on symbolic optimizer discovery via evolutionary search.

Optimizer FashionMNIST Test Accuracy
AdamW (baseline) ~87.x%
Lion (reimplemented) 88.26%

Key finding: Lion's sign-based update rule with decoupled weight decay generalizes better and is more memory-efficient than AdamW on image classification tasks.



📊 GitHub Stats

GitHub Stats   Top Languages



GitHub Streak



Activity Graph

🎯 Goals & Aspirations

Dev GIF

I'm a CS student on a deliberate path toward a thing I care deeply about:

🤖 Aspiring AI Engineer

Going beyond just calling LLM APIs — I want to understand the math, build the middleware, tune the models. SentinelLM, AntiVibe, and my Lion Optimizer work are steps on that path.

Current focus  →  LLM safety · Applied ML · Fullstack systems
Learning now   →  ML theory · System design · Research papers
GSoC 2026      →  RUXAILAB · Focus Group Analysis · NLP pipelines
End goal       →  Build AI products that actually work in prod


Always happy to connect with fellow builders!



Profile Views


CS @ Chinmaya Vishwavidyapeeth · Kerala, India · 2027

Pinned Loading

  1. antivibe antivibe Public

    Learn what AI writes, not just accept it. A Claude Code skill that turns AI-generated code into educational deep dives.

    Shell 640 41

  2. SentinelLM SentinelLM Public

    A FastAPI middleware that intercepts LLM requests and responses in real time, scoring them for prompt injection, PII leakage, toxicity, hallucination, and relevance.

    Python 4

  3. voidwalker voidwalker Public

    A browser extension + local MCP server that streams localStorage, IndexedDB, cookies, and DOM mutations to Claude, Cursor, and any MCP-compatible AI client.

    TypeScript 1

  4. StudyQuest StudyQuest Public

    A terminal-style, AI-powered learning platform with adaptive quizzes, real-time XP tracking, and a minimalist B/W dashboard.

    Python 1