All Projects

Launched Paxio - “AI that works with you”. Ask Paxio to order on Zepto, Ask it to Doomscroll the entire web, Connects Gmail, Notion, Calendar, Inbuilt memory for context + Autonomous Workflows. 7k+ impressions and 44 users.

Desktop Native Interface containing Personal Agent (integrating gmail, calendar, notion, forms and many more), Financial Agent to manage end to end budget tracking & expense analysis, Legal Agent to interact ith the Law in an interactive way powered by custom RAG piplines and Experiments with Shopping Agent to order autonomously on Quick Commerce. [Check out Technical Blog below]

Includes a Canvas Chat Interface (Interact with your favourite LLMs in Canvas native interface, Multi mode where a single query runs parallely on multiple LLMs, Vote Mode wherein LLM vote upon best response of each other), Workflow Builder (Build simple workflows with many Nodes like Input, Output, Processing, Condition, Notes in a interactive drag and drop interface), Explainer Video Maker (Generate simple explainer videos using AI of any topic with gameplay backgrounds)

Includes: RAG chatbot on Financial & Legal Parsed Data using ChromaDB, Panel of AI Agents simulating Voting Process, Image Memory, Blinky (Desktop Assistant similar to Cluely), Image based Memory System. Also experimenting with SFT, CFT, RLHF, RLVR on Language Models

Openclaw like ReAct (Reasoning + Action) based CLI with Many Inbuilt Tools (Wikipedia, Weather API, etc), Conversational Memory, Stats & Tokens Use Interface, Create Personas to Chat with, Create Agent Profiles, Connect Whatsapp and Telegram, Schedule and Create Cron Jobs to run at specified intervals, Build Agentic Workflows which can be run, Reusable Prompt Templates. Also similar to Langchain like Agentic Framework for building, calling Tools, Memory for plugins

AI for Fashion (Outfit Of The Day - OOTDify). Upload your wardrobe clothes & let the AI Stylist Recommend the Best Fit for you based on your mood. Figure out your Body Type and Chat with the AI Stylist with GenZ Slang. Collaborated with Team of 2 more peers to build this for a hackathon