Vidit-Ostwal/Vidit-Ostwal
Keeps the read me updated
Always Getting Better
Repositories
Vidit-Ostwal/crewAI
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
Vidit-Ostwal/Jev-Playing-Flipping-Birds
TypeSafe Jev plays Flappy Bird via flappy-bird-gymnasium, spectated live over WebSocket/FastAPI
Vidit-Ostwal/vidit-ostwal.github.io
Personal Portfolio Website
Vidit-Ostwal/ApexAgents-DockerImage
Contains code for apex agents docker image
Vidit-Ostwal/sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
Vidit-Ostwal/muesli
Muesli - local meeting transcription + dictation for macOS (Granola + WisprFlow alternative)
Vidit-Ostwal/Maze-Bench-OpenEnv
Ice-sliding maze environment built on OpenEnv
Vidit-Ostwal/text-2-sql-chatbot
This application is a Text-to-SQL Chatbot designed to answer natural language questions about pharmaceutical sales and prescription data.
Vidit-Ostwal/RLM-demo
The RLM Interactive Console is a full-stack application designed to demonstrate and interact with Reinforcement Learning Models (or similar agentic systems).
Vidit-Ostwal/MakeMyDocsBot
MakeMyDocsBot is a smart documentation synchronization bot designed to help maintainers keep multi-language documentation up-to-date across feature branches.
Vidit-Ostwal/Automating-3DSurvival-Playing
An autonomous vision-language agent that plays Survival 3D on YouTube Playables. It watches the game through screenshots, sets goals from the UI, plans movement, and executes keyboard actions in a loop.
Vidit-Ostwal/Automatic-UI-Fixing-Harness
The harness drives a real browser (Playwright), explores the app via BFS, converts discovered paths into plain-English test goals, executes them in parallel, and verifies each step with an LLM-based verifier to produce structured findings and an HTML report.
Vidit-Ostwal/price-negotiation-rl-OpenEnv
An OpenEnv RL environment where an LLM agent plays the buyer and negotiates against an LLM-powered seller over real marketplace listings.
Vidit-Ostwal/OpenEnv
An interface library for RL post training with environments.
Vidit-Ostwal/Understanding-prime-env
A skill that generates a rich, self-contained HTML report explaining any Prime Intellect verifiers environment.
Vidit-Ostwal/verifiers
Environments for LLM Reinforcement Learning
Vidit-Ostwal/hf-sandbox
Modal-style sandbox API on top of Hugging Face Jobs
Vidit-Ostwal/prime-environments
Training-Ready RL Environments + Evals
Vidit-Ostwal/Creating-Better-Visual-Finetuning
Vidit-Ostwal/price-negotiation-rl-env
A verifiers-based multi-turn buyer-seller negotiation environment where a trainable buyer policy learns strategic bargaining against a fixed seller model using utility-, anchoring-, concession-, and formatting-based rewards.
Vidit-Ostwal/VLM-from-scratch
This is majorly for my own learning purpose.
Vidit-Ostwal/trl
Train transformer language models with reinforcement learning.
Vidit-Ostwal/unsloth-zoo
Utils for Unsloth https://github.com/unslothai/unsloth
Vidit-Ostwal/github-mcp-server
GitHub's official MCP Server
Vidit-Ostwal/PersonalBlog
Codebase of all the personal blogs.
Vidit-Ostwal/lighteval
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
Vidit-Ostwal/Learning-GO
This is an attempt to get started with Golang
Vidit-Ostwal/gemini-cli
An open-source AI agent that brings the power of Gemini directly into your terminal.
Vidit-Ostwal/A2A
An open protocol enabling communication and interoperability between opaque agentic applications.