Opensource IDE For Exploring and Testing API's (lightweight alternative to Postman/Insomnia)

SoTA Approach for ARC-AGI 2

A high-throughput and memory-efficient inference and serving engine for LLMs

Real Work is a framework for RL environments that simulate real work.

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

A live stream development of RL tunning for LLM agents

GenAI Agent Framework, the Pydantic way

DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.

II-Researcher: a new open-source framework designed to aid building search / research agents

Model Context Protocol Servers

A benchmark to evaluate language models on questions I've previously asked them to solve.

Convert your idea to a plan

Latest Advances on System-2 Reasoning

From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓

[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards

Cost-efficient and pluggable Infrastructure components for GenAI inference

Adaptive LLM Inference

Experimentation framework for Popper

Environments for LLM Reinforcement Learning

Rush Hour puzzle goodies!

Aana SDK is a powerful framework for building AI enabled multimodal applications.

Code and dataset of CodeSteer

A Python script to solve Futoshiki puzzles

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.