A human-centric framework for building and manage real-life AI and ML systems, streamlining the transition from prototyping to production deployment.

A browser automation skill for coding agents that enables them to write and execute custom Playwright scripts for testing and complex web flows.

An HTTP/HTTPS proxy that provides security guardrails for AI agents by evaluating outbound API requests against static rules and LLM-based policies.

A serverless Web SSH terminal based on Cloudflare Workers that allows users to manage remote servers directly from a browser with built-in SFTP and AI assistance.

A self-hosted API relay service for Claude that enables multi-account management, cost-sharing, and private access to Anthropic's models.

A unified LLM API gateway that provides bidirectional protocol translation and intelligent failover across multiple providers like OpenAI, Anthropic, and DeepSeek.

A local-first workbench for managing prompts, skills, and AI programming assets, featuring one-click distribution to multiple AI coding tools and built-in version control.

An automated codebase maintenance tool that uses AI to find dead code, doc drift, and security issues overnight and submits fixes as pull requests.

A deep learning package that turns quantum-mechanical reference data into fast, scalable interatomic potentials for molecular and materials science simulations.

A documentation generator that compiles a single Markdown source into a static website, AI context files, and agent protocols for both human and machine consumption.

A visibility layer for AI coding agents on Windows that provides a centralized dashboard to monitor, navigate, and manage multiple parallel agent sessions.

A Java SDK for the Model Context Protocol that enables Java applications to interact with AI models and tools through a standardized, interoperable interface.

A terminal security gate that intercepts and blocks malicious commands, homograph URLs, and data exfiltration before they execute.

An MCP server plugin for x64dbg and x32dbg that enables AI agents to programmatically control the debugger and perform reverse engineering tasks.

A security-conscious control plane that allows AI agents and HTTP tools to manage Proxmox VE VMs, LXCs, and backups via MCP and OpenAPI.

A unified memory stack for LLM agents that provides semantically lossless compression for text and multimodal data, featuring a self-evolving retrieval system to maximize recall while minimizing token usage.

darknet‑mcp‑server is a self‑hosted MCP server that wraps 66 security‑tool APIs (HIBP, ThreatFox, ransomware trackers, Tor onion search, blockchain intel, etc.) into a single endpoint. AI agents can call these tools conversationally to get breach, ransomware, dark‑web, malware and IP reputation data in one unified response, dramatically reducing the manual, multi‑tab workflow of traditional investigations.

A Kotlin Multiplatform SDK for the Model Context Protocol, enabling developers to build standardized clients and servers that provide context, tools, and resources to LLMs.

A tile-based runtime engine for ultra-low-latency LLM inference that minimizes time per output token for massive models on NVIDIA B200 GPUs.

The official C# SDK for the Model Context Protocol, enabling .NET applications to implement MCP clients and servers to provide LLMs with standardized access to data and tools.

A community-powered distributed inference cluster that lets volunteers share their GPU power to provide free AI image and text generation for everyone.

An enhanced launcher and management console for the Codex desktop client that provides unified control over model routing, session management, and request logging.

A file-backed, spec-driven workflow framework that gives AI coding agents a structured process for planning, building, and verifying software features one at a time.

A browser automation tool that allows AI coding agents to maintain persistent browser sessions and use compact accessibility trees for efficient web interaction.

A high-performance real-time inference engine for small-batch AI workloads that uses hand-written kernels and static graphs to minimize latency without requiring model compilation.

An infrastructure layer that provides a single, shared persistent memory database with vector search for all your AI tools, eliminating fragmented data across different AI clients.

A provider-neutral framework of best practices and blueprints for designing production-safe agentic harnesses that separate model proposals from runtime execution and authorization.

A collection of 22 specialized skill modules for Claude Code that provide structured methodologies and automation scripts for professional cybersecurity operations.

A distributed, scalable graph database designed for large-scale graph analytics and millisecond latency in applications like knowledge graphs and recommendation systems.

A privacy-first, open-source web analytics platform that enables self-hosted tracking of visitors and revenue without using cookies or cross-site profiling.

An open-source, deterministic browser automation platform for building visual scraping and automation workflows that can be triggered via API.

A competitive speedrun project focused on finding the fastest algorithm to train a language model to a target validation loss on FineWeb using 8x H100 GPUs.

A command-line tool for LM Studio that allows users to manage local AI models and control the API server via the terminal.

An MCP server that provides AI agents with a comprehensive suite of reverse-engineering tools for JavaScript, WASM, and native processes, featuring an adaptive tool-discovery system to manage token usage.

A vLLM plugin that enables high-performance LLM inference on Apple Silicon Macs by using MLX as the compute backend.

A VS Code extension that integrates DeepSeek models into the Copilot Chat model picker, enabling DeepSeek's reasoning and vision capabilities while keeping Copilot's native agent and tool-calling features.

An open-source framework from UC Berkeley that uses AI to evolve high-performance algorithms and synthesize specialized, end-to-end software systems tailored to specific workloads and hardware.

An AI-native remote desktop tool with a built-in MCP server that enables AI agents to view and control remote computers globally.

A tool for running local code and uncommitted changes on remote machines or local containers, enabling an iterative edit-run loop without pushing commits.

A factory for minting custom, repo-aware AI agent harnesses with their own CLI, skills, and governance, compatible with multiple agent hosts.

A deep learning framework built in Java that supports a wide range of neural network architectures from CNNs to LLMs and Diffusion models with CUDA acceleration.

An agent-ergonomic browser automation CLI that wraps chrome-devtools-mcp to provide token-efficient, high-success web navigation and interaction for AI agents.

A set of Claude Code skills that automates the discovery, filtering, and structured note-taking for academic papers, integrating with arXiv, HuggingFace, and Obsidian.

A meta-aggregation gateway that consolidates multiple AI API providers and aggregation sites into a single API key and entry point with smart routing and cost optimization.

A React component library built on shadcn/ui that provides pre-built, customizable UI elements for building AI-native applications faster.

An open-source AI testing agent that converts plain-English Gherkin steps into automated end-to-end web tests, removing the need for manual coding.

A high-performance AI coding terminal and control plane that unifies multiple AI coding CLIs into one workspace with token tracking, credential isolation, and cross-device session continuity.

A developer-oriented platform for the full lifecycle management of AI agents, providing tools for prompt engineering, automated evaluation, and execution observability.