A self-hosted MCP gateway that consolidates multiple MCP servers into a single endpoint for AI clients like Claude and Cursor.

A Go library for building AI agents using a single, unified API that supports multiple AI providers and models.

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 toolkit for creating MCP servers on the 1C:Enterprise platform, allowing AI assistants to automatically access and interact with 1C database data and functionality.

K8E is an open‑source, single‑binary sandbox platform that lets AI agents run untrusted code securely on any Linux host. It supports gVisor, Kata, or Firecracker isolation, provides per‑session eBPF network policies, warm‑pool pods for sub‑500 ms start‑up, and an E2B‑compatible API accessed via the `k8e-sandbox-cli` tool.

A security auditing tool for AI agent skills that analyzes markdown-based skills to identify potential security risks and provide evidence-backed reports before execution.

A set of AI-enabled effects and generators for Audacity that run 100% locally using OpenVINO to provide music separation, noise suppression, and transcription.

A lightweight LLM scheduling framework that reduces prefill overhead by reusing KV caches for frequently accessed external knowledge across LLM systems.

A fork‑ready framework that uses Anthropic Claude Code to automate academic tasks (slides, papers, data analysis, etc.) via specialised agents, a ten‑gate quality suite, and extensible skills; includes setup scripts, pre‑commit hooks, and detailed documentation.

An automated video generation tool that creates scripts, synthesizes voiceovers with local voice cloning, and matches relevant video clips with synchronized word-level subtitles.

A tool for generating professional e-commerce product images using GPT-Image-2 and Codex CLI, featuring 25 specialized scene templates and reference image support.

A series of open generative 3D world models from NVIDIA that create 3D and 4D scenes from a single image or video.

A multi-platform IM agent that routes messages from WeChat, Lark, Telegram, and WhatsApp to various LLMs for automated replies and chat history analysis.

A comprehensive library of recommendation system algorithms and best practices, providing tools for data preparation, model training, evaluation, and production deployment.

A persistent, LLM-supervised memory layer for AI agents that enables cross-session knowledge retention across multiple AI frameworks using a four-graph knowledge store.

PowerInfer is a CPU/GPU hybrid LLM inference engine that uses activation locality to run large models quickly on consumer-grade GPUs by offloading 'cold' neurons to the CPU.

A browser automation tool that allows AI coding agents to maintain persistent browser sessions and use compact accessibility trees for efficient web interaction.

A native desktop workspace for DeepSeek Harness that integrates agentic browsing, local tools, and remote access into a single, local-first environment.

An open-source implementation of OpenAI's CLIP that provides tools and pretrained models for contrastive language-image and audio-text pre-training.

A terminal-based history browser for Claude Code, Pi, and Oh My Pi that provides searchable, viewable, and manageable local conversation transcripts.

A toolkit that provides specialized life science skills to AI agents, enabling them to perform tasks like protein folding, molecular docking, and genomics analysis using NVIDIA's models and libraries.

A Claude Code plugin that implements an architect pattern, orchestrating tasks between Fable 5.1 and GPT-5.6 models to optimize cost and quality through cross-vendor review.

A Rust-based terminal SSH manager that syncs ~/.ssh/config with 18 cloud providers and manages remote Docker/Podman containers fleet-wide.

The official CLI for the MiniMax AI Platform, enabling text, image, video, speech, and vision generation from the terminal or within AI agents.

A Codex skill that transforms photographs into vertical editorial artworks by pairing a real photo with a restrained, paper-textured printmaking version of the same image.

An agent communication SDK that provides a unified interface for AI agents to interact with humans across multiple channels like Slack, Discord, and Telegram using a single handler.

Rome is an open‑source “agentic OS” that lets humans and AI agents collaborate in a persistent, self‑hosted environment. It introduces **Rome Apps**—git‑tracked packages containing actions, agents, skills, UI, and data—so capabilities survive beyond a single chat. You can run it locally via Docker/Electron or use the preview Rome Cloud, build apps with the provided SDKs, and share them through an app store. The platform focuses on composable, reusable software rather than just model prompts, positioning itself between persistent‑agent services and personal‑software platforms.

UModel (Unified Model) is an open‑source, vendor‑neutral semantic runtime that unifies enterprise schemas, entities, and topology into a single graph. It offers a local service with a web UI, CLI, REST/OpenAPI, and generated Go/Python/Java SDKs. Agents can discover services, traverse relationships, and perform model‑guided root‑cause analysis via built‑in AgentGateway/MCP skills. Quick‑start uses `make quickstart` to launch a demo workspace; the system supports multiple GraphStore back‑ends and is licensed under Apache‑2.0.

A lightweight memory management framework for LLMs and AI agents that provides efficient storage, retrieval, and update mechanisms for long-term memory.

An MCP server that enables AI agents to read, search, and edit Notion workspaces using token-efficient Markdown tools.

A PyTorch library providing popular datasets, model architectures, and image transformations for computer vision.

A Model-as-a-Service (MaaS) platform and library that provides a unified interface for discovering, inferring, and fine-tuning hundreds of state-of-the-art AI models across multiple domains.

An open-source driver assistance system based on a fork of openpilot that provides modified driving assist behaviors for over 300 car models.

An observability-driven framework that automatically evolves the harness—including prompts, tools, and middleware—around a coding agent to improve performance without changing the base model.

A browser‑only, non‑linear video editor whose timeline is a JSON file that can be edited live by humans or AI agents via MCP, REST or direct file writes. Zero npm dependencies, optional ffmpeg for fast export, and built‑in AI background removal.

A full-system DNN hardware exploration platform that allows architects to design and evaluate the performance of AI accelerators using a configurable systolic array architecture.

An MCP server that gives AI assistants full access to Mozilla Thunderbird, enabling them to search mail, compose messages, and manage calendars and contacts.

A prompt engineering skill for AI portrait photography that enables consistent style and character recreation across multiple shots by reconstructing professional photographic plans.

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 MCP server that gives AI assistants direct access to shadcn/ui v4 components, blocks, and metadata across React, Svelte, Vue, and React Native.

A CLI tool that orchestrates AI coding agents into repeatable, YAML-defined development workflows with isolated worktrees and explicit review loops.

A demo system for MiniCPM-o 4.5 that enables real-time, full-duplex omnimodal interaction, allowing the AI to see, listen, and speak simultaneously.

A local observability dashboard that tracks token usage, LLM costs, and session traces for AI coding and autonomous agents by reading their local log files.

An open-source observability platform for the Vercel AI SDK that tracks costs, latency, and distributed traces for AI agents.

Python bindings for llama.cpp that enable local LLM inference with an OpenAI-compatible API and support for multiple hardware acceleration backends.

A library of building blocks and training infrastructure for the OLMo family of large language models, providing official training scripts and optimized hardware kernels.

An open-source AI research engine that generates long-form, source-grounded academic drafts with citations verified against CrossRef, OpenAlex, and Semantic Scholar.

A collection of specialized skills for Claude Code and Codex to polish, audit, and validate academic papers in LaTeX and Typst.