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

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

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.

A Python framework for building and deploying high-performance model inference APIs and multi-model serving systems for any AI/ML model.

An open-source Robotic Process Automation tool that automates browser and desktop tasks using a macro recorder, JavaScript API, and AI-driven macro generation.

A spec-driven offensive security framework for Claude Code that implements a structured 9-phase Cyber Kill Chain workflow with safety guards and 32 specialized security skills.

An agentic skill that gives LLMs access to Ghidra via a JSON-based CLI and background daemon, allowing AI to autonomously perform reverse engineering tasks.

A developer-centric API and integration testing tool that auto-generates tests and data-mocks from real user traffic using eBPF.

A compiler and runtime system that reduces LLM inference latency by fusing multi-GPU inference into a single, high-performance megakernel.

Agent Beacon is an open‑source telemetry layer that automatically captures, normalises, and stores activity from dozens of AI‑agent runtimes (local CLIs, browser chats, CI jobs, cloud SDKs). It writes a unified JSONL log on the endpoint, offers a local read‑only dashboard, and can forward data to any major SIEM, log‑aggregation service, or object storage. Packages for macOS, Linux, and Windows support MDM‑style fleet deployment, and an offline rule engine (`beacon scan`) enables threat detection without network access.

A high-performance, geo-distributed federated metadata lake that provides unified access and governance for data and AI assets across multiple sources and regions.

A configuration sidecar for Grok Bot that allows users to run any OpenAI-compatible model with verified wire-level mappings to ensure native performance and reasoning behavior.

An open-source evaluation framework for AI applications and agents that provides a library of ready-to-use graders and tools to generate custom evaluation rubrics.

A spec-driven development framework for Claude Code and Codex that turns feature requests into structured research, design, and task lists before executing them.

A collaboration infrastructure that provides the building blocks and SDKs to enable real-time synchronization, comments, and notifications for humans and AI working together in an app.

A Rust and Tauri-based MITM framework that intercepts Codex CLI API requests to bypass safety filters via system prompt injection and response tampering.

An MLIR-based compiler toolchain for homomorphic encryption that allows developers to write encrypted computations and deploy them across multiple HE libraries and schemes.

A desktop runtime middleware that allows users to access and operate Codex AI coding tools remotely via a web browser from any device.

A high-performance Rust-based web crawler and scraper that streams pages and handles JavaScript rendering to feed data into LLM and RAG pipelines.

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 CLI tool that allows users to customize system prompts, UI themes, and functional behavior of Claude Code by patching its installation.

An LLM-first SEO analysis toolkit for AI IDEs that uses 89 scripts and 10 specialist agents to automate technical SEO audits and strategic planning.

A local-first MCP server and agent control plane that allows any LLM to author, edit, and manage ComfyUI workflows and models using natural language.

An open evaluation framework for AI agents that measures their ability to complete long-horizon, professional real-world tasks across 55 subdomains using verifiable outcomes in OS sandboxes.