Skip to content
View Vidit-Ostwal's full-sized avatar
🎯
Focusing | Breaking Stuff
🎯
Focusing | Breaking Stuff

Block or report Vidit-Ostwal

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
Vidit-Ostwal/README.md

Hi, I'm Vidit Ostwal 👋

GenAI Engineer passionate about agents, RL environments, and open-source AI tooling.


🚀 My Story

I graduated from BITS Pilani in 2023 and have been working as a GenAI Engineer since then — building and iterating on agents, RAG pipelines, and fine-tuning workflows. Outside of work, I actively contribute to open-source projects.

Around January 2025, I started exploring CrewAI because I wanted to deeply understand how agent orchestration frameworks are built.

That curiosity turned into:

  • 60+ pull requests merged
  • Becoming a Top 10 contributor
  • Winning 2nd Runner-Up at the CrewAI Fall Hackathon
  • Joining the review team for an upcoming book on the framework

After that, my curiosity shifted toward RL environments.

I started exploring projects like Prime Intellect and OpenEnv, built a few playful environments, and became increasingly interested in building environments genuinely useful for training frontier models.

Building, experimenting, and learning in public.

Know more about my work here: https://vidit-ostwal.github.io/


🚢 Recent Ships

  • Jun 2026 · Automating 3D Survival Playing — Autonomous vision-language agent that plays Survival 3D on YouTube Playables with screenshots, planning, and keyboard actions.
  • Jun 2026 · Automatic UI Fixing Harness — Black-box UI defect discovery harness for locally hosted web apps using Playwright exploration and LLM verification.
  • May 2026 · Understanding Prime Env Skill — Skill and installer that generates a rich HTML report explaining any Prime Intellect verifiers environment.
  • Apr 2026 · Maze Bench — Ice-sliding multi-player maze environment for benchmarking planning and coordination in RL agents.
  • Mar 2026 · Price Negotiation RL — RL environment where an LLM agent negotiates prices against an LLM-powered seller using real marketplace listings.
  • Jan 2026 · RLM Demo — Full-stack interactive console for demonstrating and chatting with reinforcement learning models and agentic systems.
  • Oct 2025 · MakeMyDocsBot — CrewAI-powered bot that auto-syncs multilingual documentation across feature branches with a Git pre-push hook.

Pinned Loading

  1. MakeMyDocsBot MakeMyDocsBot Public

    MakeMyDocsBot is a smart documentation synchronization bot designed to help maintainers keep multi-language documentation up-to-date across feature branches.

    Python

  2. crewAI crewAI Public

    Forked from crewAIInc/crewAI

    Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

    Python

  3. price-negotiation-rl-OpenEnv price-negotiation-rl-OpenEnv Public

    An OpenEnv RL environment where an LLM agent plays the buyer and negotiates against an LLM-powered seller over real marketplace listings.

    Python 3

  4. Maze-Bench-OpenEnv Maze-Bench-OpenEnv Public

    Ice-sliding maze environment built on OpenEnv

    Python

  5. RLM-demo RLM-demo Public

    The RLM Interactive Console is a full-stack application designed to demonstrate and interact with Reinforcement Learning Models (or similar agentic systems).

    TypeScript

  6. text-2-sql-chatbot text-2-sql-chatbot Public

    This application is a Text-to-SQL Chatbot designed to answer natural language questions about pharmaceutical sales and prescription data.

    Python