A native macOS application that manages a local proxy server to centralize AI coding assistant accounts, track quotas, and automate agent configuration.

A collection of official Google Model Context Protocol (MCP) servers and deployment guides that allow AI agents to interact with Google Cloud, Workspace, and other developer tools.

A command-line tool that lets AI agents securely request and use one-time payment credentials from a Link wallet to complete purchases without storing real card details.

An open-source platform for building stable, versioned agent skills that transforms business logic into deterministic, executable capabilities for AI agents.

The official TypeScript and JavaScript library for the OpenAI REST API, providing typed access to text, vision, and real-time multimodal models.

An AI-native terminal and infrastructure agent that allows engineers to manage cloud resources and servers using natural language instead of complex commands.

An MCP server that connects AI assistants to Supabase projects, allowing LLMs to manage tables, query data, and fetch configurations.

NVIDIA Inference Xfer Library (NIXL) is a high-performance communication library that accelerates point-to-point data transfers across CPU, GPU, and various storage backends for AI inference frameworks.

An agentic Linux kernel code review system that uses a multi-stage AI protocol to automatically detect bugs and security vulnerabilities in proposed patches.

A Go SDK and model server for hardware-accelerated local inference of text, vision, audio, and image models without requiring Python.

Nightly builds of llama.cpp with built-in AMD ROCm™ 7 acceleration for high-performance GPU inference on Windows and Ubuntu.

iOS MCP is a jailbreak‑only server that implements the Model Context Protocol, letting LLM agents (Claude, Codex, etc.) control an iPhone via HTTP. It offers 46 tools for touch gestures, hardware keys, UI inspection, app management, file I/O, logs, screenshots, shell commands and more. Install the appropriate .deb (or via Cydia/Sileo), start the service in Settings, and paste the provided MCP prompt into your AI. No built‑in auth – use only on trusted LANs. MIT‑licensed (author code).

Uni‑Agent is an open‑source framework that unifies agent harnesses, sandbox execution, and RL training, enabling thousands of concurrent long‑horizon LLM agents with reproducible recipes and benchmarked results.

A tool that tracks and archives system prompts from popular coding-agent CLIs to allow version-by-version comparison of agent design changes.

A graphical web interface and management hub for llama.cpp that simplifies model loading, parameter configuration, and multi-server aggregation.

Open‑WebSearch is a Node‑JS service that lets AI agents perform live web searches and fetch article content without any API keys. It offers an MCP‑compatible server, a CLI, and a long‑running HTTP daemon, aggregates results from many public search engines, supports proxy use, and can optionally use Playwright‑driven headless browsers for sites that need JavaScript rendering.

An MCP server that gives AI assistants direct access to shadcn/ui v4 components, blocks, and metadata across React, Svelte, Vue, and React Native.

A privacy-first browser tool that exports Claude.ai conversations to high-fidelity Markdown, optimized for Obsidian and RAG pipelines.

A managed agent memory platform and ecosystem of integrations that provides AI agents with long-term memory and data ingestion pipelines.

A workspace multiplexer for AI agents that allows running multiple agents in parallel across isolated git worktrees with persistent sessions and remote approvals.

A semantic version control tool built on Git that tracks changes at the entity level (functions, classes, methods) rather than lines, providing deeper insights for humans and AI agents.

A comprehensive collection of 328 custom ComfyUI nodes providing all-in-one tools for image, video, and audio generation with a focus on zero external dependencies.

Crane is a Rust‑based inference framework (built on candle) that runs LLMs, vision‑language models, OCR, ASR, TTS and music transcription fast on CPU, CUDA, Metal and experimental ROCm. It loads GGUF checkpoints directly, provides a clean Rust API and an OpenAI‑compatible HTTP server, and ships ready‑to‑use demo binaries for chat, image chat, OCR, speech, etc.

A model optimization framework that uses compression algorithms like quantization and pruning to make AI models faster, smaller, and cheaper to run.

A portable set of rules, roles, and tools for AI agents to develop for 1C:Enterprise 8, ensuring adherence to BSL coding standards and platform-specific patterns.

A self-hosted project management and issue-tracking tool with realtime collaboration, MCP-compatible API for AI agents, and zero SaaS lock-in.

A collection of Model Context Protocol (MCP) servers that enable AI assistants to interact with Google Cloud via the gcloud CLI and various cloud APIs using natural language.

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 comprehensive suite of Claude Code skills and agents for AI-powered penetration testing, bug bounty hunting, and AI threat testing.

A high-performance gradient boosting library for decision trees that provides native support for categorical features and fast prediction speeds.

A scientific machine learning library for solving differential equations and learning operators using physics-informed neural networks and other advanced AI architectures.

An AI API proxy and management platform that provides unified access, load balancing, and cost tracking for multiple AI providers like Claude and OpenAI.

A security firewall for AI agents that intercepts network traffic and gates actions against HCL-defined rules to prevent unauthorized production changes.

A local personal memory engine for AI coding agents that records conversations verbatim and provides persistent, context-aware recall without relying on cloud APIs.

An open tabular foundation model that uses in-context learning to provide high-performance classification and regression without requiring hyperparameter tuning.

A framework for building federated AI systems that enables decentralized model training across various ML frameworks and devices.

An open-source agentic API server that acts as a model-agnostic, OpenAI-compatible replacement for building AI applications across any infrastructure.

A Codex desktop‑app plugin that automates registering DeepSeek’s LLM as a native sub‑Agent, handling model choice, API‑key storage, verification, and repair via simple CLI commands.

A Node.js library that provides pre-built bindings for llama.cpp, enabling developers to run LLMs locally with automatic hardware acceleration and TypeScript support.

An open-source SQL Server monitoring tool that provides real-time alerts, performance analysis, and AI-powered diagnostics via a built-in MCP server.

A comprehensive toolkit from Hugging Face for evaluating LLMs across multiple backends with support for over 1,000 benchmarks and custom metrics.

A framework for automating the self-improvement of AI agents by using a coding agent to iteratively optimize prompts and tools based on benchmark failures.

A tmux plugin that manages Claude Code agent sessions in popups, featuring a central picker for live status tracking and bell notifications to alert users when agents need attention.

An autonomous GPU-kernel discovery and optimizer that uses a robust benchmarking pipeline to automatically find and implement high-performance GPU kernels.

A community‑driven guide that shows how to enable llama.cpp’s draft‑MTP speculative decoding for the Qwen‑3.8‑27B GGUF model, delivering 33‑145 % faster token generation on consumer GPUs. It provides the exact launch flags, seven tuning rules, and a large table of measured speed‑ups across many GPU/CPU configurations, plus a `probe.py` script for users to verify the boost on their own hardware.

A Windows-based toolkit that reconstructs static flowcharts and academic diagrams into editable Microsoft Visio (.vsdx) files using an intermediate scene description and an iterative AI-assisted review loop.

A weather-intelligence stack for temperature settlement markets that uses Dynamic Error Balancing (DEB) to provide calibrated temperature probabilities and real-time observations.

Reverse API Engineer is a Python CLI that lets you browse a website (manually or via an AI agent), captures its network traffic, and uses a large language model (Claude, OpenCode, Ollama, etc.) to generate a typed API client in languages like Python, JavaScript, Go, Java, C#, PHP, Ruby, or C. It automates the tedious process of turning undocumented web endpoints into reusable code, offering both interactive and fully automated modes, configurable LLM back‑ends, and scriptable JSON output.