An anti-detection browser server for AI agents that uses C++ engine-level fingerprint spoofing to bypass bot detection via a REST API and CLI.

Caliber automates the creation and synchronization of AI agent context files across multiple coding tools, keeping project instructions accurate as the code evolves.

A Go CLI proxy that allows Claude Code to route requests through multiple LLM providers like OpenCode, AWS Bedrock, and OpenRouter with automatic format transformation.

A high-performance WebGL rendering engine and force graph algorithm that enables real-time simulation of massive network graphs on the GPU.

A community-driven platform for C++ heterogeneous programming that enables a single binary to run across CPUs and GPUs from all major vendors.

An OpenVINO-powered inference engine for Intel devices that serves LLMs, VLMs, and speech models via OpenAI-compatible endpoints.

A standards-style pattern language for turning complex engineering and research work into explicit, reviewable reasoning to maintain coherence across teams and AI agents.

Klavis is a platform for AI agents to access hundreds of prebuilt MCP-based tool integrations, featuring intelligent connectors to optimize context window usage and sandboxes for LLM training.

AiiDA is a workflow manager for computational science that automates data provenance tracking and manages high-throughput simulations across HPC environments.

A persistent engineering context system that helps coding agents understand a repository's architecture and design decisions without rediscovering them every session.

An open-source atomistic simulation engine built in PyTorch that accelerates Machine Learning Interatomic Potentials (MLIPs) through automatic batching and GPU acceleration.

A PyTorch library for neural network quantization that supports both post-training quantization and quantization-aware training to optimize model efficiency.

A Python client library and SDK for the Qdrant vector search engine, enabling efficient storage and retrieval of vector embeddings.

A distributed attention mechanism designed for ultra-long context and heterogeneous mask training, offering linear scalability and high performance on H100 and B200 GPUs.

A web application that provides a state-of-the-art working environment for data scientists by orchestrating Kubernetes-based containers and tools like Jupyter and RStudio.

A CNCF open-source tool for packaging, versioning, and securely sharing AI/ML projects using OCI-compliant artifacts called ModelKits.

A developer UI for the Google Agent Development Kit that simplifies the building, debugging, and orchestration of AI agents.

An MCP server that gives AI agents the tools to interact with dbt projects, allowing them to execute SQL, analyze data lineage, and manage dbt pipelines.

A comprehensive benchmark for evaluating Graph Retrieval-Augmented Generation (GraphRAG) models to determine when they outperform traditional RAG across various reasoning and retrieval tasks.

xLLM is an open‑source C++ inference framework that delivers high‑throughput, low‑latency LLM serving on Chinese AI accelerators (Ascend, Cambricon, Moore Threads, etc.). It separates a brpc‑based service layer from a hardware‑optimized engine, includes hybrid KV‑cache management via Mooncake, and provides ready‑to‑run deployment scripts for models such as GLM‑5.3‑Flash and MiniMax‑M3. The project is Apache‑2.0 licensed and backed by JD.com and several Chinese university labs.

A Kubernetes-native distributed AI platform for scalable LLM fine-tuning and training across multiple frameworks like PyTorch, JAX, and DeepSpeed.

A PostgreSQL extension for high-performance, cost-effective vector search that enables billion-scale vector hosting on modest hardware using RaBitQ compression.

A high-performance, lightweight cross-platform database client that supports a wide range of data sources and integrates AI assistants via MCP for schema-aware querying.

An MCP server and Chrome extension that gives AI agents access to a user's active browser session for real-time debugging, network inspection, and Lighthouse audits.

A composable vector indexing library that enables scalable and cost-effective nearest-neighbor search across various database storage backends.

A tool to mount Hugging Face Hub repositories and Buckets as local filesystems, enabling lazy loading of models and datasets without full downloads.

An inference engine for Hugging Face-compatible language and multimodal models that provides continuous batching, paged KV-cache management, and distributed serving.

An open-source registry for MCP servers, AI agents, skills, and prompts that centralizes discovery, management, and deployment of AI building blocks.

A visual annotation tool for AI agents that captures element selectors, CSS, accessibility data, and DevTools edits to streamline UI bug fixing.

A GitHub Action that scans websites for accessibility barriers and uses GitHub Copilot to propose AI-powered fixes via GitHub issues.

An open-source low-code dashboard and page designer that supports AI-driven conversational generation and connects to over 20 different data sources.

An MCP server that enables AI agents to interact with MongoDB databases and MongoDB Atlas, providing tools for data querying and cluster management.

An ML-powered web application and API security tool that protects against OWASP Top 10 and zero-day attacks by learning normal traffic patterns.

A library for training and analyzing sparse autoencoders to improve the mechanistic interpretability and safety of neural networks.

A framework for generative recommendation systems that reformulates recommendation as a generative modeling problem to overcome compute bottlenecks and scale to trillion-parameter models.

An AI API gateway that provides smart routing, automatic failover, and cost control for Claude Code, Codex, Gemini, and OpenAI upstreams.

A validated cycle-level GPU simulation framework that traces real SASS execution to model performance and power for NVIDIA GPUs, including full support for the Hopper (H100/H200) architecture.

A native macOS notch overlay that tracks real-time usage limits and cost estimates for Claude Code and Codex.

An extension for llama.cpp that introduces AMD-optimized GGUF quantization formats and accelerated kernels to improve LLM inference speed and memory efficiency on Radeon GPUs.

xDiT is an open‑source inference engine for diffusion‑transformer models (e.g., Flux, Stable Diffusion 3, CogVideoX). It provides multiple parallelism methods—Unified Sequence Parallel (USP), PipeFusion, data‑parallel, and CFG‑parallel—that can be combined to scale across many GPUs or machines. Single‑GPU speed‑ups come from kernel optimisations, torch.compile, and cache tricks. The project ships a CLI model runner, example scripts, Docker images, and a ComfyUI plugin (TACO‑DiT) for easy integration. It supports a wide range of DiT models and many attention back‑ends (FlashAttention, cuDNN, NVIDIA TransformerEngine, AMD AITER, etc.).

A tool that simplifies local AI model inference by packaging models and their environments into OCI containers, automating GPU acceleration and host configuration.

A macOS menu bar app that monitors AI coding sessions, allowing users to approve tools and answer agent prompts directly from the notch surface.

A linter for AI agent configurations that validates files like CLAUDE.md and .cursorrules to prevent AI tools from silently ignoring custom instructions.

okf‑skills is a Claude Code plugin/skill set that lets agents create, validate, back‑fill and visualise Open Knowledge Format (OKF) bundles – markdown‑based knowledge packs with provenance, trust and staleness metadata. It ships as a Claude marketplace plugin, as skills.sh‑discoverable agent skills, a GitHub Action for CI validation, and a read‑only MCP server. Install via `/plugin install okf@scaccogatto` or `npx skills add scaccogatto/okf-skills`. Use the `/okf:*` commands to produce bundles, run the deterministic validator, or render an interactive HTML graph. The repo is MIT‑licensed and actively CI‑tested.

A production-ready skill for Claude Code that automates iOS app building and simulator interaction using accessibility-based navigation and token-optimized outputs.

A unified LLM gateway that manages multiple providers and API keys with capacity-aware scheduling to prevent rate limit errors.

An open-source codebase intelligence tool that provides agents and teams with cited context from current code, git history, and technical web research.

An evidence-bound resume toolkit for AI internship seekers that polishes resumes, tailors them to JDs, and generates interview prep based on verifiable technical evidence.