A CLI proxy that filters and condenses verbose shell output to reduce LLM token usage by 60-90% for AI coding assistants.

A unified Elixir interface that standardizes requests and responses across 20+ LLM providers, simplifying the integration of text, image, and audio AI models.

Token Optimizer MCP is an MIT‑licensed Node.js library and local server that intercepts LLM‑agent tool calls, replaces redundant reads with diffs, builds a per‑project knowledge graph, and measures the real monetary impact of each token. Benchmarks show up to 98 % reduction on several workloads and a 0.915× cost for 20‑turn sessions. It ships a zero‑telemetry dashboard, supports 16 clients (Claude Code, Gemini, Codex, …), and requires only a local install.

An LLM inference framework for CPU servers that optimizes memory usage to outperform GPUs in long-horizon, multi-turn inference and ultra-long context tasks.

Judge0 is a robust, sandboxed online code execution system that allows developers to integrate secure code compilation and execution for over 90 languages into their applications.

An AI-powered penetration testing workbench that integrates security tools, AI assistance, and isolated execution environments into a single auditable workspace.

An in-memory platform for distributed, scalable machine learning that provides a wide range of algorithms and an AutoML feature for automated model building.

A reliability layer for self-hosted LLM tool-calling that uses guardrails, rescue parsing, and retries to make local models significantly more dependable at using tools.

A knowledge base of skills, rules, and validation hooks that teach AI coding agents to generate correct, compile-ready UdonSharp code for VRChat world development.

An MCP server that connects AI assistants to the Brazilian fiscal ecosystem, providing tools for CNPJ/CPF validation, NF-e parsing, and tax compliance analysis.

A library for flexible and powerful tensor operations using Einstein-inspired notation to make deep learning code more readable and framework-independent.

A GPU-native SQL engine that accelerates databases like DuckDB by offloading query execution to NVIDIA GPUs without requiring query rewrites.

A tool that proxies your Mac or Linux terminal into a web browser, enabling remote access to command-line tools and AI agents without complex SSH setups.

An API-based scraper that automates the collection of structured responses and metadata from ChatGPT for SEO monitoring, AI training, and brand analysis.

A local graphical user interface for the bd CLI that enables developers to visually manage issues and epics when collaborating with coding agents.

A Claude Code skill that helps developers upgrade Ruby on Rails applications from version 2.3 to 8.1 using a sequential, dual-boot migration strategy.

A unified configuration manager for AI coding assistants that allows users to manage profiles and install skills or MCPs across multiple tools from a single interface.

An open-source identity and access layer for AI agents that provides standardized authentication, permissions, and observability across thousands of external system integrations.

nnsight is a Python library that lets you trace, read, and modify any intermediate tensor of a PyTorch model (including Hugging Face, Diffusers, and vLLM models) without writing hooks. You write normal Python inside a `with model.trace(...):` block; the library injects your code during the forward pass, lets you save values, compute gradients, generate text step‑by‑step, batch prompts, or run the same trace remotely on NDIF‑hosted large models. Install with `pip install nnsight` and use wrappers like `TransformersModel` to start probing or editing model internals.

A plugin for AI coding agents that enforces a Spec-Driven Development workflow, requiring agents to define project context, specifications, and plans before implementing code.

A GUI for dispatching multiple AI coding agents in parallel, using git worktrees to isolate each task into its own branch and directory for concurrent development.

A lightweight CLI tool to manage and activate modular skills, expert agent roles, and slash commands for AI coding assistants like Claude Code and Cursor.

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

A low-code AI development tool based on PaddlePaddle that provides pre-trained model pipelines for rapid training, inference, and deployment across diverse hardware.

A Prometheus exporter that collects NVIDIA GPU metrics using nvidia-smi or NVML, supporting Linux, Windows, and macOS.

A PyTorch library for the pre-training, fine-tuning, and evaluation of Universal Time Series Transformers, enabling zero-shot forecasting across diverse datasets.

A Kubernetes operator that automates the lifecycle of Flux CD, providing self-service ephemeral environments and AI-assisted GitOps management.

A command-line interface for Power BI that enables automation of semantic models and reports, specifically designed to integrate with AI agents like Claude Code.

A cross-platform configuration manager for AI CLI tools like Claude Code and Gemini CLI, enabling one-click provider switching and unified MCP server management.

A fully-differentiable CFD solver for 3D compressible flows, enabling the integration of machine learning and numerical fluid dynamics through automatic differentiation.

An HTTP(S) mock server and proxy for testing that simulates API dependencies, records traffic, and provides specialized mocking for AI/LLM chat-completion APIs.

An offline-first synchronization extension for SQLite powered by CRDTs, enabling conflict-free data replication across devices and AI agents.

A local-first Kanban board that integrates AI agent orchestration and governance, allowing users to spawn and manage autonomous coding agents within a Git-native workflow.

A library and CLI utility that automatically configures GNU/Linux containers to leverage NVIDIA GPU hardware, regardless of the container runtime.

A cross-platform C# library based on llama.cpp that allows developers to run LLaMA and other LLMs locally on CPU and GPU with high-level APIs.

An open-source project that provides a full-lifecycle training pipeline for building a lightweight 0.1B MoE large language model from scratch, including pretraining, SFT, and RLHF.

A high-performance CUDA implementation of causal depthwise 1D convolutions for PyTorch, supporting multiple precisions and kernel sizes.

A high-performance TypeScript Byte Pair Encoder/Decoder for OpenAI models that allows developers to accurately count tokens and estimate API costs in JavaScript environments.

A graph deep learning library for materials science that provides various GNN architectures to predict material properties and simulate potential energy surfaces.

The official Python SDK for xAI's APIs, enabling developers to integrate text, image, and video generation and understanding into their applications.

A multi-backend deep learning framework that allows users to build and train models across JAX, TensorFlow, and PyTorch to avoid framework lock-in and optimize performance.

Vald is a cloud-native, distributed fast approximate nearest neighbor (ANN) search engine designed for searching through billions of dense feature vectors.

An SDK to wrap machine learning models as web servers that connect to Label Studio to automate labeling through pre-annotations and interactive predictions.

A high-performance infrastructure for multi-dimensional sparse attention, implementing Neighborhood Attention to reduce the computational cost of self-attention for 2D and 3D data.

A collection of official extensions for the Eino framework, providing pre-built integrations for LLM providers, vector databases, and DevOps tools.

A low-level Gaussian process framework built in JAX that provides researchers with the flexibility to implement and extend GP models closely following mathematical notation.

A Python SDK for the Agent Client Protocol (ACP) that provides typed schema models and asyncio transports for building standardized AI agents and clients.

A plugin for Unreal Engine that simplifies the integration of LLMs and Generative AI, featuring support for multiple AI APIs and the Model Control Protocol for AI-driven editor control.