A no-code, spreadsheet-like tool for building and enriching datasets using open-source AI models from the Hugging Face Hub or local LLMs.

An autonomous AI auditor that uses adaptive knowledge graphs and a senior/junior agent pattern to iteratively discover and confirm security vulnerabilities in codebases.

A Model Context Protocol (MCP) server that enables AI models to safely perform read-only diagnostics and troubleshooting on RHEL-based Linux systems.

An MCP server that provides a shared, persistent knowledge base for AI agents using atomic memories and an automatically generated knowledge graph.

A framework-agnostic HTTP adapter for hosting Model Context Protocol (MCP) servers in JavaScript and TypeScript applications across various web frameworks.

A modern web interface for managing and interacting with vLLM servers, supporting multi-instance backends, multimodal generation, and agentic tool integration.

A Git-native context hosting platform that provides AI agents with secure, scoped access to version-controlled data from various SaaS tools and web sources.

Dify-Sandbox is a secure execution environment for running untrusted code in multi-tenant systems, restricting resource and system call access to protect the host.

A browser control plugin for AI agents that enables direct Chrome navigation and interaction via the Chrome DevTools Protocol, available as a CLI tool or an MCP server.

An open-source, AI-native alternative to Render that allows developers and coding agents to deploy applications from Git to HTTPS on self-owned infrastructure.

An inference optimization suite for ComfyUI that uses dynamic caching and enhanced torch.compile to speed up image and video generation.

A deterministic output compactor for terminal-heavy AI agent workflows that reduces noisy command output to save tokens and improve context efficiency.

An MCP server that provides AI models with a structured, persistent thinking journal to record, revise, and branch their reasoning process across defined cognitive stages.

A collection of example codes and benchmarks for deploying common open-source deep learning algorithms on Axera AI SoC hardware.

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 CLI-first toolkit for downloading TradingView market data and backtesting Python strategies with execution behavior that mirrors TradingView's Pine Script.

A cross-platform manager that allows users to one-click install and sync MCP servers across multiple AI clients from a built-in marketplace.

A collection of Python-based pipelines and filters that extend Open WebUI with integrations for Azure AI, Google Gemini, N8N automation, and performance monitoring tools.

An agentic, cross-platform SQL database GUI client that supports 70+ databases and uses AI to generate, optimize, and fix SQL queries from natural language.

A library that enables zero-copy, multi-host communication of JAX arrays, allowing JAX simulations to scale across entire CPU and GPU clusters.

A memory adaptor for AI coding agents that provides a unified, cross-agent memory layer to store and recall project context and decisions.

A semantic DataFrame engine that integrates LLM operators into a typed query model to turn unstructured data into reusable, inspectable pipelines.

A foundational PyTorch library that serves as a training engine for deep learning models, providing standardized components for training loops, configuration, and monitoring.

A deep learning framework for JuliaLang that uses explicit parameterization to combine Julia's elegance with XLA performance.

A free, self-hosted annotation platform for NLP, AI agents, and qualitative research that uses YAML configuration for multimodal data labeling and agent evaluation.

A public leaderboard that uses Vectara's Hallucination Evaluation Model (HHEM) to measure and compare how often different LLMs hallucinate when summarizing documents.

A specialized framework for generating high-quality, privacy-preserving synthetic tabular data using statistical models, GANs, and LLMs.

A command-line tool for creating container-based AI/ML development environments using a simple Python declaration instead of complex Dockerfiles.

A lightweight knowledge graph construction and visualization tool based on Neo4j and Spring Boot, featuring visual editing, ER modeling, and external data source integration.

A C++ library for numerical analysis providing multi-dimensional arrays with NumPy-like broadcasting and lazy computing.

OpenTURNS is a scientific C++ and Python library designed to help engineers treat uncertainties, risks, and statistics in industrial applications.

A ComfyUI extension that replaces standard node connections with organized, circuit-board-style orthogonal lines to reduce visual clutter in complex workflows.

A local chat data reader and automation tool for WeChat 4.x that decrypts local databases and media to provide structured access via API and TUI.

A modular machine learning framework designed for fast learning and inference on problems with extremely large output spaces, such as extreme multi-label ranking and large-scale retrieval.

A concise and feature-rich Transformer library that implements a variety of experimental architectural optimizations and research-backed features for text and vision models.

A Python-based UI framework for rapidly building web apps, demos, and internal tools without needing to write JavaScript, CSS, or HTML.

A library for fast, large-scale approximate nearest neighbor search using space partition trees and relative neighborhood graphs.

LakeSoul is a production-ready lakehouse platform with a Rust-native core that provides ACID transactions, automated compaction, and native support for multimodal data and vector retrieval.

A visual management panel for AI agent frameworks like OpenClaw, Hermes Agent, and DeepSeek Harness, featuring a built-in AI assistant for automated system diagnosis and configuration.

An open-source AI orchestration platform that automates the delivery of ML and generative AI pipelines, from data management and training to serverless deployment and monitoring.

A Python package providing a collection of surrogate modeling methods and sampling techniques, with a specific focus on derivatives and gradient-enhanced modeling.

A local CLI tool that prevents AI agents from breaking repository architectural conventions, specifically focusing on API route layering in Next.js projects.

A NestJS module that enables developers to easily expose tools, resources, and prompts to AI agents using the Model Context Protocol (MCP).

A cloud-agnostic ML infrastructure platform for real-time feature serving, model inference, and embedding search at massive scale.

A PyTorch library for training neural networks with multiple losses, providing tools for scalarization and Jacobian descent to resolve optimization conflicts in multi-task learning.

Knowhere is a high-performance C++ core library that serves as the internal engine for the Milvus vector database, enabling efficient vector search and indexing.

A collection of deep learning models and examples implemented using the Burn framework, covering text, image, and audio modalities.

A native macOS tool that uses AI agents to simulate real users navigating iOS, macOS, and web apps to identify UX friction and test user goals.