Implementation of π₀, the robotic foundation model architecture proposed by Physical Intelligence

A monitor of resources

pyright fork with various type checking improvements, improved vscode support and pylance features built into the language server

Rectified Flow Inversion (RF-Inversion)

Verifiable and Token-Efficient Text Extraction Using LLMs and Vim.

Pure Python Vim clone.

Python client and plugin host for Nvim

LangSmith Client SDK Implementations

🔬 A fast, interactive web-based viewer for performance profiles.

Sampling profiler for Python programs

Library for fast text representation and classification.

A fast, clean, responsive Hugo theme.

Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.

AI Observability & Evaluation

Explorations into some recent techniques surrounding speculative decoding

A lightweight library for converting complex objects to and from simple Python datatypes.

Rapid fuzzy string matching in Python using various string metrics

An open-source 3D-printed direct-drive bionic hand.

A library for efficient similarity search and clustering of dense vectors.

A playbook for systematically maximizing the performance of deep learning models.

Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!

Code for the paper "What's the Magic Word? A Control Theory of LLM Prompting"

Seamless operability between C++11 and Python

Improved file parsing for LLM’s

A toolkit for reproducible reinforcement learning research.

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

An educational resource to help anyone learn deep reinforcement learning.

MLX: An array framework for Apple silicon