The official CLI for the Claude Platform that enables sending messages, managing API resources, and treating AI agents as version-controlled code.

An MCP server that enables AI agents to programmatically create and edit Draw.io diagrams, automating the creation of architectural diagrams and flowcharts.

Neo.mjs is a self-evolving software organism consisting of a multi-threaded application engine and an AI Agent OS that enables a swarm of cross-model AI agents to inhabit and maintain live software.

Deep Lake is a serverless database for AI that stores and streams large-scale unstructured data and vectors, optimizing the workflow for deep learning training and LLM applications.

A CLI tool for managing Model Context Protocol (MCP) servers, providing global configuration, server discovery, and easy integration across multiple AI clients.

A gradient processing and optimization library for JAX that provides composable building blocks for creating custom optimizers and loss functions.

A local server that exposes ChatGPT account models via OpenAI and Ollama compatible APIs, allowing them to be used in third-party chat and coding tools.

An MCP proxy server that aggregates multiple Model Context Protocol servers into a single HTTP entry point, simplifying tool and resource management.

A browser-hosted mobile simulation platform for GUI agent research that provides programmable state and deterministic judges for scalable RL training and verifiable evaluation.

An AI-native management tool for Milvus vector databases that provides a visual interface for data exploration, cluster monitoring, and AI-driven administration.

A command-line tool designed for AI agents to fetch, discover, and extract structured data from the web, replacing the need for fragile parsing scripts and raw HTML dumps.

A browser-based tool to export ChatGPT and Google Gemini conversations as Markdown, HTML, or PDF files while preserving formatting and metadata.

A collection of libraries for building real-time, collaborative applications on Cloudflare Workers using Durable Objects, featuring WebSocket management and CRDT support.

A collection of pre-built, customizable Vue and Nuxt components for AI applications, providing UI elements for chat, reasoning, and AI workflows.

An SDK that connects AI agents to Slack, Microsoft Teams, and Discord, enabling native interactive UI and human-in-the-loop approvals.

An open-source AI agent for Unity that automates C# coding, asset modification, and editor UI creation with built-in hot reload and semantic analysis.

An automated vulnerability research pipeline engine that uses YAML-defined workflows to orchestrate data ingestion, filtering, and LLM-based security assessments.

An open-source Playwright library for AI-powered browser regression testing that uses natural language steps and multi-model consensus assertions to prevent test fragility.

An open-source control plane that turns AI agent logic into production-ready REST APIs with built-in scaling, observability, and cryptographic identity.

An Apache 2.0 React SDK for embedding visual drag-and-drop workflow editors into applications, featuring a plugin-first architecture and a reference execution stack for AI workflows.

A collaboration tool for AI engineers and domain experts to build and curate high-quality datasets for NLP, LLMs, and multimodal models.

A high-performance inference toolkit for deploying and serving open-source text embeddings and sequence classification models with low latency.

A Python-embedded DSL for authoring machine learning kernels that compiles to Triton, offering higher abstractions and automated performance tuning to simplify GPU programming.

An MCP server that provides AI agents with instant, local, and up-to-date documentation for 100+ popular libraries to prevent hallucinations caused by outdated training data.

ONNX Simplifier (onnxsim) is a tool that automatically reduces ONNX model size and complexity by constant‑folding, shape inference, and graph optimizations, with optional correctness checks and export to MLIR, Core ML, TFLite, and more.

A large-scale benchmark dataset and framework simulating internal company documents and questions to help teams evaluate and fine-tune RAG systems for enterprise environments.

A collection of efficient Triton kernels for LLM training that increases throughput by 20% and reduces memory usage by 60% through kernel fusion and chunking.

A transport proxy for the Model Context Protocol (MCP) that enables communication between stdio-based and SSE/StreamableHTTP-based servers and clients.

A fast Rust-based terminal diff viewer and code review TUI that supports side-by-side diffs, GitHub PR reviews, and AI-powered commit and change explanations.

A cross-platform terminal workspace written in Zig that integrates high-performance terminal emulation with AI agent workflows, SSH management, and an embedded browser.

Tura is an open-source agent runtime harness that reduces token usage and improves performance by replacing repetitive tool-calling loops with macro commands and backward reasoning.

A pure-Python reference implementation of the CuTe layout-and-tensor algebra used in CUTLASS 3.x, enabling layout prototyping and testing without a GPU.

A metasearch library that aggregates results from multiple web search services and provides content extraction tools for text, images, videos, and news.

A benchmark and sandboxed environment for evaluating multimodal AI agents on their ability to complete open-ended tasks in real computer operating systems.

A high-performance, multi-language PDF toolkit for text and image extraction and markdown conversion, optimized for RAG pipelines and AI assistants.

An autonomous research agent that uses a hypothesis-tree framework to optimize software and ML tasks through disciplined, automated experimentation and validation.

PowerInfer is a CPU/GPU hybrid LLM inference engine that uses activation locality to run large models quickly on consumer-grade GPUs by offloading 'cold' neurons to the CPU.

A high-performance C++ library for writing task-parallel programs with a flexible task graph system and GPU acceleration support.

The official command-line interface for Kaggle, allowing users to manage datasets, competitions, models, and notebooks directly from their terminal.

A Neovim plugin that integrates Copilot's Next Edit Suggestions and provides a built-in terminal for interacting with AI CLI tools with context-aware prompts.

A multi-agent system that converts PyTorch programs into verified Triton kernels and iteratively optimizes their performance using hardware profiling and LLM-guided bottleneck diagnosis.

A Blockbench plugin that implements the Model Context Protocol (MCP), allowing AI agents to control and interact with 3D modeling tools.

An AI-powered penetration testing tool that uses a multi-agent architecture to simulate human security experts in discovering vulnerabilities across Web apps and APIs.

A Nix flake-based reverse engineering environment that integrates with Claude Code to provide automated, context-aware toolchains for analyzing binaries and network captures.

An MCP server providing AI agents with real-time global intelligence across 30+ domains, featuring 132 tools and a Qdrant vector store for semantic search.

Perplexity‑AI is an unofficial Python wrapper that scrapes the public Perplexity.ai web UI to run search, reasoning, and research queries without an API key. It offers synchronous and asynchronous clients, streaming answers, file uploads, and a small MCP server for integration with Claude Code. An optional driver can automate Chrome to create temporary Gmail accounts via Emailnator, letting users refresh the free‑tier “5 pro queries” limit. The library includes typed interfaces, retry/back‑off, rate‑limit handling, and custom exceptions.

An MCP server that bridges AI models with WinDbg (CDB and KD) to enable natural language crash dump analysis and kernel debugging on Windows.

A PyTorch wrapper that abstracts the boilerplate code for distributed training, allowing users to run the same script on any device configuration including multi-GPU and TPU.