- Providence, RI
- https://fpiedrah.com/
Stars
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
Simple & elegant figures for research papers, with examples in Julia and Python
Generative Agents: Interactive Simulacra of Human Behavior
A fast type checker and language server for Python
Elegant, renumbering free ID system using fractional hex midpoints.
🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.
ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.
Reliable, minimal and scalable library for evaluate and conduct world model research
DSPy: The framework for programming—not prompting—language models
Secure and fast microVMs for serverless computing.
Get your documents ready for gen AI
AeroSpace is an i3-like tiling window manager for macOS
GenAI Agent Framework, the Pydantic way
The lean application framework for Python. Build sophisticated user interfaces with a simple Python API. Run your apps in the terminal and a web browser.
FastStream is a powerful and easy-to-use asynchronous Python framework for building asynchronous services interacting with event streams such as Apache Kafka, RabbitMQ, NATS and Redis.
The property-based testing library for Python
A Git-compatible VCS that is both simple and powerful
DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphic…
An Open-source RL System from ByteDance Seed and Tsinghua AIR
Library for LLM-driven action model acquisition via natural language
MLGym A New Framework and Benchmark for Advancing AI Research Agents
Training Large Language Model to Reason in a Continuous Latent Space
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
Ongoing research training transformer models at scale
open-source framework for creating and managing simulations populated with AI-powered agents. It provides an intuitive platform for designing complex, interactive environments where agents can act,…

