A Python toolbox for performing gradient-free optimization

Deepchecks: Tests for Continuous Validation of ML Models & Data. Deepchecks is a holistic open-source solution for all of your AI & ML validation needs, enabling to thoroughly test your data and mo…

📑 PageIndex: Document Index for Reasoning-based RAG

A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.)

The cryptography-based networking stack for building unstoppable networks with LoRa, Packet Radio, WiFi and everything in between.

Curated list of awesome Cursor Rules .mdc files

Implement a reasoning LLM in PyTorch from scratch, step by step

A curated list of awesome ASGI servers, frameworks, apps, libraries, and other resources

Zipline, a Pythonic Algorithmic Trading Library

Coding assistant MCP for Claude Desktop

Bringing BERT into modernity via both architecture changes and scaling

Automated Time Series Forecasting

Expert Parallelism Load Balancer

SkyRL: A Modular Full-stack RL Library for LLMs

OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data

FAIR Sequence Modeling Toolkit 2

SONAR, a new multilingual and multimodal fixed-size sentence embedding space, with a full suite of speech and text encoders and decoders.

Checkpoint-engine is a simple middleware to update model weights in LLM inference engines

FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design

Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)

Semi-Structured Agentic Framework. Workflows build themselves as agents discover what needs to be done, not what you predicted upfront.

MLGym A New Framework and Benchmark for Advancing AI Research Agents

Open Vision Agents by Stream. Build Vision Agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

Vanilla DQN, Double DQN, and Dueling DQN implemented in PyTorch

BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically ground…

Optimized Whisper models for streaming and on-device use

🐉 Loong: Synthesize Long CoTs at Scale through Verifiers.

A universal, distributed and secure messaging protocol for Reticulum