Rust bindings for the PyTorch C++ API (libtorch), enabling the use of PyTorch's tensor operations and deep learning tools in Rust.

A fast, header-only C++ machine learning library that provides a wide array of ML methods and functions with bindings for Python, Julia, Go, and R.

A deep probabilistic programming library built on PyTorch that allows users to create and scale universal probabilistic models for large datasets.

A platform for building AI agents featuring a no-code visual builder and a TypeScript SDK with full two-way synchronization for collaborative agent management.

Vearch is a cloud-native distributed vector database that enables efficient similarity search of embedding vectors for AI applications.

AnyGPT is an open‑source multimodal LLM (text, speech, images, music) that uses discrete tokenisation to unify all modalities. It provides base and chat checkpoints, inference scripts, and the AnyInstruct dataset for training and zero‑shot multimodal tasks.

An interactive terminal tool for querying JSON using jq syntax, featuring real-time output, AI-assisted query generation, and schema-aware autocompletion.

An AI-integrated productivity tool that auto-schedules your day, breaks down large tasks, and provides burnout prediction based on work patterns.

A browser extension that uses LLMs to detect and skip sponsored segments in Bilibili videos by analyzing subtitles and audio.

A Go-based vulnerability scanner and exploitation tool for the Spring framework that integrates with AI agents via MCP to automate penetration testing.

A cross-platform Python-based AI assistant that integrates multiple LLM providers, voice interaction via Whisper and Kokoro, and web scraping for a unified desktop AI experience.

A Python library for developing and comparing multi-objective multi-agent reinforcement learning algorithms through a standardized API and a set of benchmark environments.

An open-source platform for causal learning that recovers causal structures from observational data using a variety of discovery algorithms.

A framework and dataset for disentangling task transfer learning in computer vision, providing a pretrained task bank and tools to analyze task affinities.

Reverb is a Linux‑only, Python‑friendly library (with a C++ backend) that provides a gRPC‑based, distributed experience‑replay service for reinforcement‑learning research. It lets you define tables with configurable sampling/removal strategies (uniform, prioritized, FIFO, etc.), rate limiters, and capacity limits, and supports checkpointing and sharding across multiple servers. Install via `pip install dm-reverb[tensorflow]` and use the `reverb.Server`/`reverb.Client` API to insert and sample data. Designed for research, not production, and tightly coupled to specific TensorFlow versions.

An optimization toolkit for Continual AI that provides specialized algorithms and visualization tools to prevent catastrophic forgetting and improve model stability.

Marsha is an LLM‑powered, markdown‑style language that lets you describe a data‑processing function with types, a natural‑language spec, and input‑output examples. The Marsha compiler sends this spec to an LLM, generates Python code, validates it against the examples, and produces a ready‑to‑run CLI or REST service.

An engineering toolkit for high-stakes decision frameworks integrating AI and mathematical optimization, featuring tools for LLM evaluation in finance and data provenance.

An AI-oriented code-processing framework that uses a Universal Abstract-Syntax-Tree (UniAST) to provide LLMs with precise, structured coding context for better AI-assisted programming.

A framework for training and deploying low-bit quantized neural networks on low-end microcontrollers, enabling high-accuracy inference on devices with as little as 2KB RAM.

A ROS meta-package for autonomous vehicle navigation providing 2-D/3-DOF path planning, costmap handling, and collision prevention control.

An interactive chat tool that uses LLMs and vector embeddings to help developers understand and navigate GitHub code repositories.

A hosted MCP server that integrates job searching, resume tailoring, and application tracking into AI assistants like Claude and Cursor.

A computer vision project that enhances shuttlecock tracking in badminton videos using trajectory prediction with background estimation and an inpainting-based rectification module to handle occlusions.

A multimodal data extraction package that scrapes clean markdown and structured data from complex documents using vision-language models for RAG and LLM applications.

A Java-based intelligent medical diagnosis system that uses a knowledge graph to link symptoms and diseases for patient self-evaluation and physician assistance.

tts‑now is a cross‑platform Electron desktop app that calls Alibaba Cloud and iFlytek TTS APIs to synthesize speech from text, supporting single and batch jobs, with pre‑built binaries for Windows, macOS and Linux.

An enhancement suite and sidecar for grok2api that monitors proxy node quality and intercepts low-quality responses to prevent AI intelligence degradation.

An AI-driven automation solution that converts natural language requirements into functional software by integrating LLMs with DevOps tools for the entire development lifecycle.

A backend for ONNX that converts ONNX models into TensorFlow models, enabling them to be run using the TensorFlow execution engine.

AMD's library for high-performance machine learning primitives, providing optimized kernels for deep learning on ROCm-enabled platforms.

A cost-efficient routing system that replaces expensive LLM classification calls with lightweight traditional ML surrogates for easy inputs, maintaining teacher-level parity.

An open-source search agent system that provides fully open-sourced training data and models to democratize access to frontier search capabilities for complex information-seeking tasks.

A Julia interface for XGBoost, providing a scalable and efficient distributed gradient boosting framework for regression, classification, and ranking.

A C++ library for communicating with Invensense MPU-6500 and MPU-9250/9255 IMUs, providing easy access to motion and magnetic data via I2C or SPI.

An unofficial Dart/Flutter SDK providing typed clients for the OpenAI API and compatible providers, supporting all major platforms including web.

A set of scripts to automate ChatGPT account registration using DuckMail API and generate Codex OAuth tokens for CLIProxyAPI v6.

An open-source lightweight library for managing hardware products as a collection of independent software features, enabling faster development and reuse across microcontrollers.

A Python package that converts Scikit-Learn pipelines to PMML format to improve model portability and deployment across different environments.

A flexible Bayesian dynamic linear model library for Python that enables time series decomposition and forecasting through additive components.

Cell Ranger is a set of analysis pipelines for processing 10x Genomics Chromium Single Cell data, performing tasks like gene counting and transcript sequence assembly.

A Python library for exploring and querying multilingual wordnets, providing tools for semantic similarity, taxonomic exploration, and lemmatization.

An open-source deployment toolkit that uses Ansible to automate the OS provisioning, driver installation, and deployment of Slurm, Kubernetes, and AI frameworks on Linux servers.

A cross-platform desktop manager for CLIProxyAPI that centralizes AI account management, quota tracking, and configuration for AI coding agents.

Ovo is a Rust library that provides an embeddable multi‑agent runtime kernel. It lets a host application spawn lightweight agents (turns) that run Rhai scripts, with optional OS‑level sandboxing (macOS Seatbelt or Linux Landlock). The crate offers configurable approval policies, a sandbox‑backend trait, and optional toolkit features for jailed filesystem access. It is pre‑stability (0.9.x) and dual‑licensed MIT/Apache‑2.0.

An open-source AI-driven low-code and no-code platform for rapidly building and deploying enterprise-grade cross-platform mobile and web applications.

A warehouse-native event collection layer that unifies tracking across multiple destinations like GA4 and BigQuery using a config-as-code approach.

An MCP server that integrates DeepSeek's V4.1 Flash API into MCP-compatible clients, enabling text and visual chat and file management.