An interpretable AI framework for prioritizing the review of IRS Form 990 filings by combining financial anomalies, narrative text, and relationship graphs.

A desktop AI companion with voice interaction, system-level tool access, and long-term memory that can be run locally or via cloud APIs.

An AI pipeline SDK for orchestrating generative video, audio, and image workflows with built-in, hash-verified provenance manifests.

A computer vision-based automation tool that identifies and interacts with screen elements using image recognition to simulate mouse and keyboard input.

An MCP server that enables AI agents to order private phone numbers and receive SMS verification codes from over 200 countries.

A framework for building durable, composable AI agents as dataflows that can crash and resume, retry safely, and provide full execution traces.

A concise command-line tool and Python library for monitoring NVIDIA GPU utilization, temperature, and memory usage.

A tool that checks a website's SEO foundation to ensure it is optimized for search engines and AI retrieval, provided as an agent skill for automated auditing.

A fast, modern text indexing and search engine written in Go that provides full-text search and vector search capabilities for applications.

Ref MCP is a Node‑JS MCP server that lets LLM coding agents search documentation and fetch only the relevant excerpts, dramatically cutting token usage and cost.

CCPlugins provides 24 ready‑made Claude Code CLI commands (e.g., /cleanproject, /commit, /security-scan, /scaffold) that automate repetitive dev tasks, add git safety checkpoints, and deliver fast, deterministic results. Install with a one‑liner script; commands work on any language or OS and can be chained in CI/CD pipelines. The project is actively maintained and MIT‑licensed.

LocalGPT is a Rust‑based, locally‑run tool that turns natural‑language prompts into 3‑D Bevy worlds (`localgpt‑gen`) and provides a privacy‑first AI assistant (`localgpt`) with persistent, searchable memory, autonomous background tasks, and a tiny HTTP API. It works with any LLM (local or cloud), runs as a single binary, and includes sandboxed security features.

ANEMLL is an open‑source toolkit for converting Hugging Face LLMs (LLaMA, Qwen, Gemma 3, etc.) into Core ML models that run entirely on Apple’s Neural Engine. It includes conversion scripts, an ANE profiler, Swift and Python reference implementations, a full‑screen iOS/macOS chat app (TestFlight), and benchmarking tools. The 0.3.5 beta adds monolithic model support, in‑model argmax, and a redesigned chat UI, targeting on‑device, low‑power inference with privacy guarantees.

A VS Code extension that provides a beautiful graphical chat interface for the Claude Code CLI, removing the need for terminal commands.

A local-first gateway for AI agents that organizes MCP tools and prompts into portable 'playbooks' for easy deployment and switching.

An automated reconnaissance workflow tool that orchestrates security scanners and generates structured JSON reports optimized for AI-driven vulnerability analysis.

A vendor-neutral voice input and memory agent for macOS and iOS that builds a local context trail to provide AI with personal long-term memory.

Submagic Core is a lightweight AI environment for Windows that enables model chaining, workflow automation, and side-by-side model comparison.

A unified AI model gateway and governance infrastructure that centralizes model access, cost management, and operational monitoring for AI applications and agents.

A macOS voice input tool that combines real-time speech recognition, local Whisper fallback, and AI-driven text cleanup for seamless bilingual input across applications.

An Android video player based on libmpv that uses the Anime4K algorithm to provide real-time super-resolution upscaling for anime and animation videos.

A trust-first AI agent marketplace and workspace where users can discover, rent, and run task-specific agents within a governed runtime.

A management platform for Hermes Agent that provides a Kanban board and supervision tools to track, review, and schedule autonomous AI tasks.

A self-hosted, long-running AI agent featuring a four-layer cognitive memory system and a self-evolution engine to improve skills over time.

An AI-native desktop platform that generates native Word, PowerPoint, and Excel documents directly from natural language prompts.

A set of TypeScript packages for integrating with the Keslr network to ensure applications are accessed only by verified humans via trust-graph authentication and private network addressing.

Compartment is an encrypted, offline vault that lets AI agents store, retrieve, and manage session memories locally, providing fast hybrid search and privacy‑preserving persistence without any network or API dependencies.

A library that wraps scikit-learn and XGBoost models as LLM-callable tools with auto-generated JSON schemas and Pydantic validation.

A distributed deep learning framework that makes training and inference for large AI models faster and cheaper through advanced parallelism and memory management.

An intelligence runtime and infrastructure layer for AI agents that provides collective error recovery, persistent memory, and self-sovereign cryptographic identities.

A native desktop workspace for coding agents that integrates an editor, terminal, Git, and browser into a single environment with a secure agent kernel.

An agent preset for DeepSeek V4 Flash via opencode-go that uses optimized guidance anchors to prevent shallow reasoning and improve output quality for complex tasks.

An open-source framework for building event-driven multi-agent AI systems using the Solace Platform for scalable and reliable agent communication.

A proxy subscription manager for Cloudflare Workers and Pages that provides a graphical panel to manage VLESS, Trojan, and xhttp nodes with optimized IP selection.

Hailuo AI Pulse is a streamlined AI workspace for Windows that provides content generation, analysis, and creative automation capabilities.

A stateless, multi-protocol gateway that provides a unified endpoint for AI agents and applications to access event streams (Kafka/MQTT) and federated MCP toolsets.

An open-source framework that uses AI runtimes to automate the end-to-end product growth loop, from market research and content creation to result analysis and iteration.

An enterprise-grade TypeScript framework for building production-ready MCP servers with built-in authentication, dependency injection, and visual debugging tools.

A deep learning framework built in Java that supports a wide range of neural network architectures from CNNs to LLMs and Diffusion models with CUDA acceleration.

A collection of state-of-the-art model implementations and best practices for TensorFlow users to accelerate research and product development.

A JavaScript SDK for the Oxylabs AI Studio API, providing AI-powered tools for web scraping, crawling, autonomous browser navigation, and site mapping.

A unified framework for building private, local, and secure knowledge-based LLM applications, featuring a model catalog of 300+ models and an integrated RAG pipeline.

An in-process intelligence layer for AI agents that reduces costs and latency by speculatively executing queries with small models and escalating to flagship models only when needed.

A GUI application and toolkit for Claude Code that provides visual session management, custom agent creation, and usage analytics.

An automated structural MRI morphometry system that integrates CAT12 processing to measure brain tissue volumes and generate quantitative reports.

A structured meta-research skill for Claude Code that transforms research queries into a 13-phase pipeline with hypothesis testing, source triangulation, and automated verification.

A programmatic marketplace that applies ad-tech economics to match consumer AI agents with provider agents through standardized bidding, discovery, and automated settlement.

A package manager and MCP gateway for AI coding agents that centralizes tool and rule configurations into a single version-controlled file for 35+ providers.