domsteil
Follow
Stars
An MCP Server that's also an MCP Client. Useful for letting Claude develop and test MCPs without needing to reset the application.
Two conversational AI agents switching from English to sound-level protocol after confirming they are both AI agents
Exploring Applications of GRPO
A toolkit for developing and comparing reinforcement learning algorithms.
Official implementation of paper: SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna
Reinforcement Learning Agents in Javascript (Dynamic Programming, Temporal Difference, Deep Q-Learning, Stochastic/Deterministic Policy Gradients)
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Make websites accessible for AI agents
Clean, minimal, accessible reproduction of DeepSeek R1-Zero
An open infrastructure to democratize and decentralize the development of superintelligence for humanity.
A comprehensive repository of reasoning tasks for LLMs (and beyond)
npm for design engineers: largest marketplace of shadcn/ui-based React Tailwind components, blocks and hooks
A react-based starter app for using the Live API over websockets with Gemini
AG2 (formerly AutoGen): The Open-Source AgentOS. Join us at: https://discord.gg/pAbnFJrkgZ
A full-featured, hackable Next.js AI chatbot built by Vercel
Business Data Benchmark (BDB) is a set of real-world questions to evaluate AI systems connected to business data.
A collection of projects designed to help developers quickly get started with building deployable applications using the Anthropic API
A testnet open-source Layer 2 from the future, co-designed with the developer tools stack.
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.