A cross-device companion app and client for AI coding agents that lets you run sessions locally and control them remotely via mobile, web, or desktop.

vllm.cpp is a pure‑C++ inference engine that mirrors the vLLM Python server’s performance and features while being only ~66 MiB in size. It runs GGUF‑quantized LLMs (and multimodal models) on CPU, CUDA, Metal, Vulkan, etc., offering token‑for‑token identical output, continuous batching, speculative decoding, and an OpenAI‑compatible HTTP API—all without any Python runtime.

A Go server that reverse‑proxies Google Gemini’s web UI protocol and exposes it as an OpenAI‑compatible API (chat, models, streaming, video, image, music, web‑search). Works anonymously or with Google cookies, includes rate‑limiting, proxy & cookie pools, SQLite/MySQL persistence, and a lightweight admin UI.

slotstream is a Swift‑based inference engine that runs the 125‑billion‑parameter Qwen‑3.8‑Flash‑Next model on Apple‑silicon Macs. It streams 4‑bit‑quantised weights from SSD into a RAM cache, enabling ~12 tokens / s on a 48 GB Mac. The tool offers a CLI, Ollama‑compatible and OpenAI‑compatible HTTP APIs, optional vision support, speculative decoding, and a Swift package for embedding in apps.

A collection of modular extensions and libraries for the Pi Coding Agent that add capabilities for coding, browser automation, and workflow observability.

An open-source platform for securely running and managing Model Context Protocol (MCP) servers using container isolation and centralized governance.

An AI-powered CLI tool that analyzes hardware and recommends optimal local LLM models from a multi-source registry, featuring integrated safety verification and MCP support.

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

A collection of standardized task definitions and instructions that enable AI coding agents to perform complex AI/ML workflows on the Hugging Face Hub.

A Go library that integrates llama.cpp for local LLM and VLM inference with hardware acceleration, requiring no CGo or external servers.

A high-performance fork of llama.cpp that provides better CPU inference speed and support for additional state-of-the-art quantization types.

A high-performance, open-source search database that provides full-text, vector, and hybrid search capabilities as a fast alternative to Elasticsearch.

A benchmark for evaluating AI agents on expert-curated research workflows across various scientific domains, verified in a terminal environment.

A native macOS sticky note app with a fanning deck UI that lives at the screen edge for quick, unobtrusive note-taking.

An automatic hyperparameter optimization framework for machine learning that uses a define-by-run API to efficiently find optimal model parameters.

An MCP server that connects AI assistants to the Unity Editor and Unity Hub, providing over 330 tools for AI-powered game development and automation.

An open-source SQL interface for deploying, managing, and querying cloud resources and SaaS APIs across multiple providers.

A lightweight library for easy one-line loading and efficient pre-processing of massive multi-modal datasets for machine learning training and evaluation.

A collection of agent plugins for Claude Code and GitHub Copilot CLI that automate the development of Power Platform applications, sites, and flows.

A local proxy and trace viewer for AI coding agents that allows users to inspect API traffic, system prompts, and tool calls to debug agent behavior.

CodeBoarding creates visual architecture maps and documentation for codebases by combining static analysis and LLM reasoning, helping developers and AI agents understand system structure.

A Deep Reinforcement Learning library providing single-file, transparent implementations of popular algorithms to simplify research, debugging, and prototyping.

A simulated bash environment with a virtual filesystem that allows for safe execution of bash-like commands in a sandbox.

A high-performance CUDA kernel library for LLMs that provides optimized GEMM and fused MoE primitives for NVIDIA SM90 and SM100 GPUs.

A terminal application that manages multiple AI coding agents in isolated git workspaces, allowing developers to run several tasks simultaneously without conflicts.

A self-hosted MCP gateway and management platform that provides a unified way to connect, manage, and operate multiple Model Context Protocol servers.

A marketplace of production-ready plugins for Claude Code that extends its capabilities with specialized workflows for development, finance, and documentation.

A high-efficiency communication protocol that unifies publish/subscribe, geo-distributed storage, and computation for distributed systems.

Caura is an open-source governed memory layer for AI agent fleets that enables shared, self-improving knowledge storage and retrieval across multiple agents.

A library of 30 skills and 5 specialized agents for AI coding assistants to ensure .NET development follows production-tested patterns and best practices.

An MCP plugin that adds semantic code search to AI coding agents, allowing them to efficiently retrieve relevant snippets from large codebases using a vector database.

An open-source, self-hosted ERP for construction project management that provides tools for BOQ, BIM/CAD takeoff, 4D scheduling, and 5D cost modeling.

A secure sandbox for AI coding agents that uses Incus system containers to provide isolated environments with real-time threat detection and credential protection.

A local, reversible PII anonymization tool for Italian legal text that allows users to use cloud LLMs without sending sensitive personal data.

A hardware detection and recommendation tool that tells users which open-weight AI models will run best on their specific machine based on their CPU, RAM, and GPU.

An open-source PyTorch framework for physics and scientific machine learning that provides reusable components and training recipes for AI in science and engineering.

A tool to verify if third-party AI API providers are using genuine models by comparing their statistical output fingerprints against official API baselines.

A tool for automatically generating themed image cards from Markdown and publishing them as notes to Xiaohongshu.

A cloud-native web honeypot server that uses deceptive pages, spider traps, and AI-generated content to detect and analyze malicious web crawlers and attackers.

A web-based workstation surface that serves your local computer's files, terminal, and git state to any browser, featuring integrated AI agents for machine automation.

An API proxy that converts client-only AI model interfaces into standard OpenAI-compatible APIs, enabling the use of restricted models in any application.

A GitHub Actions-based framework that wraps AI coding agents to automate PR reviews, CI fixes, and issue triage using your own LLM keys or subscriptions.

A comprehensive collection of examples and tutorials for deploying and fine-tuning Liquid AI's open-weight Liquid Foundation Models (LFMs) on mobile, desktop, and browser environments.

An MCP server that connects AI assistants to Figma, enabling design system extraction, bidirectional token synchronization, and programmatic design creation.

A cloud-native data pipeline orchestrator for managing the development and maintenance of data assets like machine learning models and tables with integrated lineage and observability.

An agentic AI security tool that identifies exploitable vulnerabilities in source code by simulating attacker paths and using a falsification engine to minimize false positives.

Apache TVM is an open machine learning compilation framework that optimizes and deploys models into minimum deployable modules using a Python-first approach.

A decision engine and orchestration framework for spec-driven AI development that ensures software stability by requiring human-led decisions before AI agents execute tasks.