A cloud-native, Kubernetes-native control plane for deploying and managing scalable and cost-effective LLM inference infrastructure.

An MLX-native server for Apple Silicon that lets you run Claude Code 100% locally, eliminating API limits and proxies for faster, private on-device AI coding.

A self-hosted, open-source alternative to LangSmith Deployments that allows you to run LangGraph agents on your own infrastructure using the same SDK and APIs.

NVIDIA TensorRT is a high-performance deep learning inference library and SDK that accelerates AI model deployment on NVIDIA GPUs.

A game theoretic approach to explain the outputs of any machine learning model by attributing credit to input features using Shapley values.

An open-source smart LLM router that enables autonomous agents to pay for AI models using USDC micropayments and wallet signatures, while reducing costs through local smart routing.

An MCP integration that allows AI agents like Cursor to read and programmatically modify Figma designs via a WebSocket server and plugin.

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 deliberately vulnerable CTF-style training platform for learning the OWASP Top 10 for LLM Applications through scripted labs and real local model exploitation.

An open-source ETL platform that compiles visual pipelines to SQL and runs them on DuckDB, allowing teams to deploy and own their data infrastructure without per-row billing.

An MCP expansion and AI editor toolset for Unreal Engine 5.8+ that enables AI agents to perform deep world-building, animation, and performance profiling within the editor.

A token-efficient MCP server that uses tree-sitter AST parsing to allow AI agents to retrieve precise source code symbols rather than reading entire files.

DocsGPT is an open‑source, privacy‑focused platform that lets you ingest many document types (PDF, Word, spreadsheets, web pages, audio, etc.) and query them with any LLM. It provides a Flask backend, a React UI, speech‑to‑text, citation‑backed answers, pre‑built chat widgets, and enterprise‑grade deployment options (Docker, Kubernetes, RBAC, OIDC).

An open-source observability framework built on OpenTelemetry that provides complete tracing and monitoring for LLM applications, providers, and vector databases.

A lightweight TypeScript library that provides durable workflows and queues backed by Postgres, ensuring applications can automatically recover from failures without external orchestrators.

A KV cache compression library for LLM inference that uses orthogonal rotation and optimal quantization to reduce VRAM usage and extend context windows.

A platform-agnostic website specification that consolidates fragmented web standards into a single reference, including tools to make sites legible to AI agents.

codex‑web is a thin Node.js wrapper that serves a browser UI for the Codex Desktop AI‑agent platform, letting you control agents from any device while the backend runs on a trusted machine.

ASTRA-sim is a distributed AI system simulator that models the end-to-end software and hardware stack to aid in the design and deployment of next-generation AI infrastructure.

An MCP server that connects AI agents to 70+ Brazilian public data sources, providing 533 tools for querying government data across economy, legislation, and health.

A governance and engineering system that transforms rough workflows and prompts into reusable, cross-platform AI agent skill packages with built-in evaluation and release gates.

A high-performance C++ inference runtime for deploying text, vision, audio, and speech models on NVIDIA Jetson, DRIVE, and DGX Spark edge platforms.

An agent-driven reverse engineering framework that allows AI agents to investigate app behavior and native binaries using tools like Hopper and Ghidra to explain and recreate software features.

A decentralized AI infrastructure that optimizes computational power for model training and inference using a novel Proof of Work 2.0 consensus mechanism.

A bioinformatics-native AI agent skill library that replaces stochastic LLM code generation with versioned, reproducible, and specification-constrained genomic workflows.

A zero-dependency JavaScript/TypeScript SDK for accessing real-time and historical stock market data across multiple global markets, featuring built-in technical indicators and an MCP server for AI integration.

A machine learning experiment tracking and visualization platform that helps developers monitor hyperparameters and metrics across the entire ML pipeline.

A self-improving context layer that teaches AI agents how to query SQL warehouses accurately using approved metric definitions and business knowledge.

A macOS dashboard and proxy gateway that centralizes the management of AI subscriptions, API providers, and usage tracking for tools like Claude Code, Codex, and OpenCode.

A macOS menu bar utility that consolidates system toggles and routine tasks into a single switch hub, featuring AI-powered natural language control and custom scripting.

A context engineering tool that automatically generates and maintains repository-specific instructions and configurations to improve the performance of AI coding agents.

A multi-device, persistent terminal built for coding agents that allows users to run AI coding sessions across desktop and mobile with server-side session recovery.

A native macOS and iOS GUI for the Hermes AI agent, providing visibility and control over sessions, projects, and configurations via a rich interface.

A Python package for statistical computation that provides tools for estimation and inference for a wide range of statistical models.

A knowledge and action layer for Claude Code that enables it to write senior-level .NET 10/C# 14 code using Roslyn-powered analysis and architectural enforcement.

PyMC is a Python package for Bayesian statistical modeling that uses MCMC and variational inference algorithms to estimate parameters in complex probabilistic models.

A security-focused orchestration engine that automates complex security workflows and reconnaissance using declarative YAML definitions and distributed execution.

An MCP server that gives AI assistants deep read/write access to the Unreal Engine Editor, enabling natural language control over assets, blueprints, and world-building.

An AI-native data integration platform that uses LLMs and GraphRAG to enable natural language creation of data pipelines and SQL-free data analysis.

A local-first AI development workbench that integrates prompt optimization, evaluations, RAG, and fine-tuning into a single workflow for teams.

An AI Gateway and LLM observability platform that provides unified API access to 100+ models, request tracing, and prompt management for AI engineers.

NeMo AutoModel is a Python library from NVIDIA that provides ready‑to‑use, highly‑optimized training recipes for a huge range of LLMs, VLMs, and diffusion models. It supports full‑parameter and LoRA fine‑tuning, multi‑node tensor‑ and pipeline‑parallelism, and even speculative‑decoding drafters, all driven by simple YAML configs.

A Python-based UI framework that allows developers to create web-based interfaces for robotics, ML, and dashboards without writing HTML or JavaScript.

A PowerPoint plugin for researchers that automates scientific slide creation through AI assistance, LaTeX/Markdown insertion, and advanced layout tools.

An open-source LLM gateway that unifies multiple AI providers, subscriptions, and local models into a single OpenAI-compatible endpoint with automated fallbacks.

A toolkit for merging pre-trained language models in the weight space, allowing users to combine model strengths without additional training or high inference costs.

A collection of developer utilities and demos for the WebMCP API, enabling web pages to expose structured tools for AI agents to interact with programmatically.

A native macOS app that provides a graphical interface for managing, creating, and booting virtual iPhones for iOS research using vphone-cli.