Python tool for converting files and office documents to Markdown.

Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.

A minimal, terminal-native pomodoro timer built for SSH sessions. No curses, no TUI dependencies — just carriage-return countdowns that work over any connection.

AI coding agent optimized for small LLMs. 87% benchmark with 4B-active model.

A set of delightful extensions for Pi

Multi-agent AI coding orchestration system designed to drive successful coding outcomes with a high level of transparency (think more light-factory than dark-factory).

🇰🇷 Korean LLM Datasets | Pre-training, SFT, DPO, RLHF, CoT | 한국어 LLM 데이터셋 큐레이션

A solution to visualize and explore 3D models in your browser.

An introduction to DSPy

TradingAgents: Multi-Agents LLM Financial Trading Framework

AI Engineer Workshop - DSPy is All You Need

Collection of Claude Skills for DSPy framework - program language models, optimize prompts, and build RAG pipelines systematically

A classic guessing game powered by LLM

Code and dataset for TurtleBench: A Visual Programming Benchmark in Turtle Geometry

Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.

Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems.

A multi-agent system built with DSPy that coordinates research and writing agents to produce comprehensive articles on any topic.

Official implementation for BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation

Now you can move a digital robot and an actual machine in real time! With 6 axes, you can use Rhino+Grasshopper to link any object with urdf and an actual machine.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

A collection of AI-generated malware algorithms for red teaming and blue teaming

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.

Code for subgoal synthesis via image editing

JORA: JAX Tensor-Parallel LoRA Library (ACL 2024)

Accelerate, Optimize performance with streamlined training and serving options with JAX.