An evaluation framework that measures how coding agents evolve executable policies through iterative experimentation and feedback in interactive environments.

A deep learning library for in-the-wild 3D face reconstruction and animation, featuring tools for speech-driven avatars and emotion recognition.

A query language that extends SQL with free-text primitives to enable conversational search over databases containing both structured and unstructured data.

A ComfyUI custom node for precise resolution and aspect ratio control, featuring a visual 2D canvas and model-specific optimizations for AI image generation.

A library for preparing machine translation data, providing tools for cleaning monolingual data, mining bitext, and running knowledge distillation pipelines.

A PyTorch toolkit for accelerated MRI reconstruction that provides an end-to-end pipeline for sampling, reconstruction, and validation using deep learning.

SwinFusion is a Swin Transformer-based framework for general image fusion that combines information from multiple source images across various domains, such as infrared, visible, and medical imaging.

A declarative YAML-based language for creating reliable, composable LLM prompts and integrating them into software systems with support for control flow and code execution.

A Python package for ontology engineering that integrates deep learning models with formal knowledge representation to support tasks like ontology matching and subsumption prediction.

A curated collection of production-grade skills, agents, and workflows for AI coding agents like Claude Code, providing standardized automation for the full software development lifecycle.

A Chinese meme generator and translator that uses DeepSeek to convert modern text into a formal, pseudo-ancient "Zhouli" style and decode it back into plain language.

A set of Python tools for experimenting with and studying recommender systems, providing support for training, running, and evaluating recommendation algorithms.

A multi-agent security console for macOS that runs isolated AI agent instances in separate macOS user accounts to ensure data privacy and system security.

A unified interface for various automatic differentiation backends in Julia, providing a consistent syntax for computing gradients, Jacobians, and Hessians.

An MCP server and Firefox extension that lets AI assistants securely manage tabs, search history, and read webpage content with explicit user consent.

Mundi is an open source web GIS that uses LLMs to automate geoprocessing algorithms and symbology editing for vector, raster, and point cloud data.

ASASR is a faithful image super-resolution framework based on FLUX.1-dev that uses Adversarial Sobolev Alignment to reduce artifacts and improve structural fidelity in upscaled images.

An autonomous browsing agent that uses LLMs and the Chrome DevTools Protocol to navigate websites, interact with dynamic content, and automate complex web workflows.

A high-performance Rust rewrite of the DSPy framework that enables programmatic, automated optimization of LM-powered application pipelines.

A toolkit for evaluating PII detection models and generating synthetic PII datasets using templates to improve Named Entity Recognition (NER) accuracy.

An open-source Spark library that integrates Amazon SageMaker into Spark ML pipelines for scalable model training and inference on DataFrames.

A CNN-based architecture for panoptic segmentation that predicts class- and instance-specific labels for every pixel in an image.

MeanVC is a lightweight, zero-shot voice conversion system that uses mean flows and a diffusion transformer to enable real-time, single-step timbre transfer.

An enterprise AI landing zone that provides a centralized, governed gateway for AI consumption with unified security, compliance, and observability.

Claude Code Multi‑Agent is an open‑source framework that gives Anthropic’s Claude Code project awareness and expert‑agent capabilities. It uses a Python Hook system and a locally‑run Ollama model to automatically detect the codebase type, analyse user intent, load 300+ domain‑specific “Skills” (backend, frontend, testing, security, etc.), and enforce automatic documentation (DEVELOPMENT.md, KNOWLEDGE.md, CHANGELOG.md). After cloning, installing Ollama, a model, and uv, you drop your project into the repo and Claude Code instantly knows its context, suggests appropriate tools, and can be driven with slash commands like `/backend‑specialist` or workflow commands such as `/kiro/spec`. Key points: - Zero‑config start; all configuration lives in `.claude/settings.json` and `prompts.json`. - Hooks run on session start, user prompt, tool use, etc., handling project detection, intent analysis, and doc updates. - Skills are defined by `SKILL.md` files and are auto‑discovered. - Works entirely locally (no external API), integrates with Git, and is MIT‑licensed. Ideal for developers or small teams who want a reproducible, on‑premise AI coding assistant.

An MCP server that enables AI models to interact with Elasticsearch and OpenSearch, providing tools for searching documents, managing indices, and monitoring cluster health.

A collection of ML software builds and tools optimized for the deprecated AMD GFX906 architecture to enable modern AI workloads on legacy hardware.

A text-based interactive debugging framework for Python programs that allows LLM agents to use tools like pdb and bash to investigate and fix bugs in code repositories.

A high-frequency trading framework in Java and Python that enables L2 tick-data backtesting and live market execution using a unified codebase.

A code-first educational collection of handwritten Python implementations for various tabular anomaly detection methods, including PCA reconstruction, RobustPCC, and PU learning.

An AI-powered PRD generator that transforms natural language descriptions into structured technical documentation and SOPs to optimize the performance of AI coding agents.

An open-source, low-code platform providing seamless access to pre-trained AI/ML models for infectious and neglected disease research and drug discovery.

A context curation tool that enables AI coding agents to automatically identify, pack, and manage the specific files and code excerpts needed for a task to avoid token limits and missing information.

A comprehensive suite of APIs and tools to integrate safety, privacy, explainability, and fairness into Generative AI and traditional ML models to ensure trustworthiness.

Next.js Evals is a Vercel‑maintained framework for automatically testing AI coding agents on real‑world Next.js tasks. It syncs eval fixtures from the `vercel/next.js` repo, runs agents in a Vercel sandbox, checks hidden assertions, records pass/fail, token usage, and cost, and exports a JSON leaderboard that powers the public Next.js evaluation site.

A real-time radiance field rendering project that replaces Gaussian kernels with deformable Beta Kernels to improve geometric detail, color representation, and memory efficiency.

A large-scale synchronized dataset of video, audio, and tactile force data from robotic sliding contact used for material recognition and cross-modal learning.

A machine learning runtime written in Rust that enables running ONNX models trained in PyTorch and other Python frameworks in Rust and WebAssembly environments.

A collection of example projects and templates demonstrating how to implement AI features like LLMs, computer vision, and simulation in Unity using the Sentis package.

A high-performance inference engine for GPUs and AI accelerators that enables efficient model deployment and academic validation.

A computer vision project that integrates YOLOv7 and YOLOv8 for real-time object detection and tracking across video streams from various sources.

A collection of example projects for self-hosting and deploying various Stable Diffusion family models using the BentoML framework.

A ROS-based development and simulation framework for the xArm series of robotic arms, providing hardware interfaces, MoveIt motion planning, and Gazebo simulation.

Q‑Transformer is a PyTorch library that implements the autoregressive Q‑function approach for scalable offline reinforcement learning, targeting robotic tasks that combine video observations and language instructions. It provides a vision‑transformer model, data‑collection agent, replay‑memory dataset, and Q‑learning trainer, all installable via `pip install q-transformer`.

TFTS is a TensorFlow-based library that provides a unified interface for implementing state-of-the-art deep learning models for time series prediction, classification, and anomaly detection.

A Triton-based subset of PyTorch's nn module that provides a readable and hackable collection of neural network layers for developing custom deep learning operations.

continuous-eval is a Python library for modular, data‑driven evaluation of LLM‑powered pipelines. It provides a catalog of retrieval, generation, code, and agent metrics, lets you attach those metrics to individual pipeline modules, runs them on a dataset, and can enforce regression tests. Custom LLM‑as‑a‑judge metrics are also supported.

Ekho is a Chinese text-to-speech engine that converts written text into spoken audio, supporting custom voice data integration.