Google's Engineering Practices documentation

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with C…

Prompt Optimization Paper List

DSPy: The framework for programming—not prompting—language models

Point Cloud Library (PCL)

This is a package for LiDARTag, described in paper: LiDARTag: A Real-Time Fiducial Tag System for Point Clouds

Find dead Python code

Efficient Universal Perception Encoder: a single on-device vision encoder with versatile representations that match or exceed specialized experts across multiple task domains.

Memory Sparse Attention - A scalable, end-to-end trainable latent-memory framework for 100M-token contexts.

The official Python SDK for Model Context Protocol servers and clients

Correlation Alignment for Domain Adaptation

The Lensfun project Git repository

🐍 Geometric Computer Vision Library for Spatial AI

DexiNed: Dense EXtreme Inception Network for Edge Detection

[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥

BoxMOT: Pluggable python and c++ SOTA multi-object tracking modules with support for axis-aligned and oriented bounding boxes

Python sandboxes for llms

Exactly what it sounds like

Connect ClickHouse to your AI assistants.

Reference PyTorch implementation and models for DINOv3

🙃 A delightful community-driven (with 2,500+ contributors) framework for managing your zsh configuration. Includes 300+ optional plugins (rails, git, macOS, hub, docker, homebrew, node, php, python…

Model Context Protocol Servers

TensorDict is a pytorch dedicated tensor container.

Dataset of diseased plant leaf images and corresponding labels

BayesOpt: A toolbox for bayesian optimization, experimental design and stochastic bandits.

Immutable and statically-typeable DataFrames with runtime type and data validation

Claude Conductor - a simple Claude Code framework

A customized PyTorch layer and a customized PyTorch activation function using B-spline transformation

Interpolating natural cubic splines. Includes batching, GPU support, support for missing values, evaluating derivatives of the spline, and backpropagation.