Explore the directory

A coding-agent skill that runs a structured, multi-phase security audit, using isolated agents for reconnaissance, hunting, candidate validation and independent verification, producing machine-readable findings.

• Agent skills
• Security

An LLM inference server for Apple Silicon Macs, managed from the menu bar, with continuous batching and a tiered in-memory and SSD key-value cache.

• Inference
• Desktop utilities

A desktop GUI and toolkit for Claude Code that manages sessions, custom agents, usage analytics and MCP servers, built independently and not affiliated with Anthropic.

• Coding agents

A high-performance observability data pipeline that collects, transforms and routes logs, metrics and traces to any combination of vendors.

• Monitoring

An open-source reference stack for running AI agents such as OpenClaw, Hermes and LangChain Deep Agents more safely inside NVIDIA OpenShell sandboxes, with managed inference and lifecycle operations.

• Agent frameworks
• Containers

A small, native local inference engine for running a curated set of large language models, including DeepSeek V4 and GLM, on consumer hardware such as Macs, NVIDIA GPUs and Strix Halo systems.

• Inference

A curated collection of open Chinese large language models, covering base models, domain-specific fine-tunes and applications, datasets and tutorials, aimed at models that are small enough to run privately at low training cost.

• Curated lists

An open-source platform for building enterprise-grade AI agents, combining a RAG pipeline, an agentic workflow engine and MCP tool use, aimed at uses such as customer service and internal knowledge bases.

• Agent frameworks
• RAG

An agent skill and Python service that strips multi-vendor AI provenance marks, such as invisible watermarking and C2PA or EXIF metadata, from text and files you own.

• Agent skills

An MCP server that gives AI assistants such as Claude structured knowledge of n8n's workflow nodes, properties and operations, so they can build and configure n8n workflows.

• MCP servers
• Workflow automation

An agent harness and service framework for Go that lets a developer describe a capability in conversation, generate a Go service for it, and use that service as a tool from the same agent.

• Agent frameworks
• Backend

A tool that automates browser-based workflows using vision-language models and computer vision instead of hand-written selectors, through a Playwright-compatible SDK or a no-code workflow builder.

• Browser automation

A machine learning compiler and deployment engine that compiles large language models to run across GPUs and platforms including AMD, NVIDIA, Apple and Intel GPUs, web browsers, iOS and Android.

• Inference

A browser-based code explorer, built on VS Code, that lets a developer browse, search and review a GitHub or GitLab repository by adding "1s" to its URL.

• Git

An all-in-one multimodal retrieval-augmented generation framework, built on LightRAG, for querying documents that mix text, images, tables and equations through a single interface.

• RAG

A YAML-based workflow engine for AI coding agents that turns processes such as planning, implementation, validation, review and PR creation into deterministic, repeatable pipelines.

• Coding agents
• Workflow automation

A multilingual large voice generation model with a full pipeline for inference, training and deployment, supporting zero-shot multilingual and cross-lingual voice cloning.

• Speech

A curated, automatically ranked directory of machine learning Python libraries, grouped into more than 30 categories such as frameworks, NLP, computer vision and MLOps, updated weekly.

• Curated lists

A high-performance neural network inference framework optimized for mobile, embedded and desktop deployment, with no third-party runtime dependencies and both CPU and Vulkan GPU backends.

• Inference

A mobile and web client for using Claude Code and Codex remotely, with end-to-end encryption, push notifications and instant switching between phone and desktop.

• Coding agents

An MCP server that reduces how much raw tool output enters an AI coding agent's context window, tracks session state in SQLite for recovery after compaction, and encourages agents to run scripts instead of reading large amounts of data directly.

• MCP servers
• Agent memory

An open-source, local-first 3D architectural editor built with React Three Fiber and WebGPU, usable from the browser or a CLI, with MCP tools for connecting AI agents.

• MCP servers
• Design tools

An open-source AI-plus-no-code platform for building business systems, where AI coding agents and a WYSIWYG interface work on the same production infrastructure.

• Backend
• Workflow automation

The official Python implementation of the Model Context Protocol, for building MCP servers that expose tools, resources and prompts, and MCP clients that connect to them.

• MCP servers