A developer-centric API and integration testing tool that auto-generates tests and data-mocks from real user traffic using eBPF.

Argus is a persistent autonomy framework for research and engineering that uses a multi-role architecture to enable long-running AI agent work with minimal human intervention.

TestHub is an open‑source, AI‑enhanced test‑management system built with Django (backend) and Vue 3 (frontend). It covers requirement analysis, test‑case authoring, API/Web/Android automation, performance testing, and reporting, while offering LLM‑driven test generation and a chatbot assistant.

A multi-agent framework for writing novels and short stories that maintains authorial voice and narrative continuity through specialized agents and a durable knowledge base.

A standardized packaging format and toolchain for local MCP servers, enabling single-click installation of AI tools into desktop applications.

Everywhere is a cross‑platform desktop AI assistant (Windows/macOS) built with .NET 10 and Avalonia. It captures on‑screen context via accessibility APIs and lets you query LLMs (OpenAI, Anthropic, Gemini, etc.) through a global hot‑key, returning markdown‑rich answers. Features include browser/file/terminal agents, rich UI, multi‑language UI, and support for local Ollama models. The project is open source under its LICENSE and provides installers, a portable zip, and full build instructions.

A high-performance Rust-based decoding tool that automatically identifies and decrypts encoded text using A* search and optional BERT-powered plaintext detection.

A self-modifying terminal agent built in Common Lisp that can introspect and modify its own code and state to adapt to tasks.

Olares is an open-source personal cloud operating system that enables users to run AI agents and LLMs locally on their own hardware using Kubernetes.

A multi-account OAuth manager for the official Codex CLI that enables account switching, health-aware rotation, and project-scoped storage to bypass rate limits.

A local MCP server that enables AI assistants to read, search, and edit notes within an Obsidian vault directly via the file system.

A Claude Code plugin marketplace that enables the creation of "loop engineers"—autonomous agents that use a shared file-based memory and a codebase harness to perform and verify work independently.

A modified YouTube client that uses JavaScript injection and Google Gemini to provide AI video summarization, ad-blocking, and advanced download tools.

A video cut detection and analysis tool that automatically identifies scene changes to split videos into individual shots or extract frames.

A learning system plugin for AI agents that turns your assistant into a tutor and examiner to ensure you actually retain the information it explains.

NeMo RL is NVIDIA’s open‑source library for scalable reinforcement‑learning fine‑tuning of large language and vision‑language models. It supports a range of RL algorithms (GRPO, DAPO, GDPO, etc.), works with both PyTorch DTensor and Megatron Core backends, and offers high‑performance generation via vLLM or Megatron inference. Ready‑to‑run Docker containers, Ray‑based distributed training, and extensive YAML recipes make it suitable for quick prototyping up to multi‑node, multi‑GPU production runs.

A content capture and knowledge management system that converts social media feeds from 10+ platforms into a local Markdown knowledge base accessible to AI Agents via MCP.

ParadeDB is a Postgres extension that integrates full-text and vector search directly into the database, eliminating the need for a separate search engine.

TabbyAPI is an open‑source FastAPI server that wraps the ExllamaV3 inference engine, exposing a fast, OpenAI‑compatible HTTP API for locally hosted LLMs (Exl3, FP16/BF16). It supports model loading/unloading, HuggingFace downloads, embeddings, speculative decoding, function calling, and async batching. Distributed as Docker images (CUDA 12.8/13) and licensed under AGPL‑v3, it targets hobbyist/self‑hosted use rather than production workloads.

An open-source AI assistant with persistent memory and interactive UI capabilities that runs across all major platforms and supports on-device inference.

A server-side operating layer for AI Agent workloads that provides an AI-native terminal, token-saving compression for tool outputs, and secure execution runtimes.

A memory enhancement plugin for SillyTavern that uses structured tables to provide AI characters with long-term memory of events, settings, and items.

A comprehensive suite of AI skills for Codex and Claude Code that guides users through the entire mathematical modeling competition process, from problem translation to final paper review.

An open-source team chat system deployed on Cloudflare Workers that allows users to create independent chat spaces without maintaining a server.

An open-source system companion for macOS and Windows that provides system monitoring, disk cleanup, and an MCP server for AI agents to manage the machine.

A video direction skill for Dreamina/Jimeng Seedance 2.5 that transforms creative ideas and reference images into structured video scripts and optimized prompts.

A native workspace for coding agents that allows developers to run multiple terminal-based AI agents side-by-side with isolated Git worktrees and integrated code review.

A multi-account proxy for Claude Code and Codex that pools multiple accounts and automatically rotates them to bypass API quota limits.

An open-source Python library for researching communication systems, featuring tools for radio propagation ray tracing and wireless/optical link-level and system-level simulation.

A modeling framework for high-performance symbolic-numeric computation used in scientific computing and scientific machine learning to optimize and solve complex equation-based models.

A native DeepSeek Harness memory plugin that bounds the context window by archiving older conversation turns into a graph-based navigation layer for exact source-backed recall.

An MCP server that allows AI agents to automate Firefox using WebDriver BiDi, enabling them to navigate the web, interact with elements, and access developer tools.

A framework for self-referential, self-improving agents that can autonomously optimize their own code to solve any computable task.

A container-native workflow engine for Kubernetes that orchestrates parallel jobs, specifically optimized for machine learning pipelines and data processing.

AgentHound is an open‑source offensive security framework that scans AI‑agent infrastructure from a foothold, harvests credentials, validates real access, and builds a graph‑based attack surface. It works via a static collector binary (active or stealth mode) and an optional Neo4j‑backed server for visual analysis.

A set of Claude Code skills that automates the discovery, filtering, and structured note-taking for academic papers, integrating with arXiv, HuggingFace, and Obsidian.

An agent-driven memory system that creates a shared LLM wiki across sessions, agents, and devices by automatically distilling reusable skills from agent history.

Cherry Studio App is a mobile application for iOS and Android that enables interaction with multiple LLM providers like OpenAI, Gemini, and Anthropic.

An agent-native operating system and SDK for generalist robotics that allows developers to build physical AI applications in Python without requiring ROS.

ArtCraft is a desktop IDE that lets artists build 2‑D or 3‑D scenes and then fill them with AI‑generated images, video, audio, meshes and worlds. It offers visual tools for compositing, pose transfer, background removal, and prompt‑driven generation, supporting a catalog of 62 built‑in models plus external providers like Midjourney and Sora. Available for Windows/macOS (Linux from source), it targets creators who want repeatable, controllable AI art workflows.

A native Windows and macOS desktop client for Hermes Agent, providing a streamlined interface and bundled runtime for managing AI agents.

SCAIL-2 is an open-source model for end-to-end character animation and replacement, removing the need for intermediate pose representations to support complex motions and diverse identities.

A PyQt6-based AI customer service desktop application that automates e-commerce responses using a custom agent framework and dual knowledge bases.

An open-source operations platform for building AI agents, apps, and automations to streamline business processes and internal operations.

LightX2V is an open‑source inference framework for fast image and video generation (T2V, I2V, T2I, I2I, T2AV, etc.). It supports many state‑of‑the‑art models (MiniMax‑H3, Wan, HunyuanVideo, Qwen‑Image, etc.) and provides speed‑up techniques such as 4‑step distilled LoRAs, FP8/NVFP4 quantization, tensor/sequence parallelism, and disaggregated deployment on a wide range of hardware. Benchmarks show up to 3.9× faster inference than competing frameworks on H100 GPUs. The project offers Docker images, pip install, Gradio/ComfyUI front‑ends, extensive docs, and an online demo.

A high-performance LLM inference engine optimized for agentic workloads, featuring a split C++ control plane and Python execution plane for maximum speed and usability.

A library for creating environments to train and evaluate LLMs, specifically designed for reinforcement learning workflows.

A dependency-free C++ port of Depth Anything 3 and V2 for fast, monocular metric depth and camera pose inference on CPU and GPU.