Explore the directory

The former standalone Model Context Protocol server for the Weaviate vector database, now deprecated in favor of an MCP server built directly into Weaviate itself.

• MCP servers
• Databases

A self-hosted mobile terminal that mirrors a computer's live tmux sessions onto a phone or desktop browser, so a coding agent such as Claude Code or Codex can be steered and reviewed remotely.

• Coding agents
• Terminals

A folder of Markdown, YAML and bash you drop into a git project to add cross-session memory and delivery governance to AI coding tools, splitting a discovery step that plans from a delivery step that executes in isolation.

• Agent skills
• Agent memory

A self-hosted, model-agnostic framework for orchestrating fleets of specialist AI agents, offering six ensemble-reasoning modes and a separate plan-build-review pipeline for shipping code.

• Coding agents
• Agent frameworks

A Kotlin code generator, built on Kotlin Symbol Processing, that produces clean, null-safe mapping code between classes at compile time with no reflection and full Java interoperability.

• Libraries

A Node.js and TypeScript REST API boilerplate built around vertical-slice clean architecture, paired with an LLM-driven code generator that scaffolds a full CRUD module from a text description.

• APIs
• Backend

A drag-and-drop visual workflow builder for AI agents backed by local Ollama models, connecting data sources, AI processing steps and external tools such as email, search and Slack without cloud dependencies.

• Agent frameworks
• Workflow automation

An OpenCode plugin that discovers available models from any OpenAI-compatible provider automatically and injects them into OpenCode's provider configuration.

• Agent skills

A Model Context Protocol server that exposes Docker Hub's API to LLMs, so AI tools can recommend container images and manage Docker Hub repositories through natural language.

• MCP servers
• Containers

An open-source, self-hosted visual builder for AI agents and workflows, wiring tools, knowledge and logic on a canvas and deploying to email, an API, an MCP server, or an embeddable web widget.

• Agent frameworks
• Workflow automation

A lightweight, multi-platform chat interface for local and cloud LLMs that can run fully offline and optionally encrypts stored chat history and files.

• Inference

A family of methods that compress or actively manage a language model's long reasoning traces into compact representations, cutting the cost of retaining and attending to them during inference.

• Models

An official Model Context Protocol server that connects a Taskade workspace to Claude, Cursor and other AI clients, plus a code generator that turns any OpenAPI specification into MCP tools.

• MCP servers

A Go-based Model Context Protocol server that lets MCP clients such as Claude Desktop query Grafana Loki log data using the LogQL query language.

• MCP servers
• Monitoring

An AI agent add-on that inspects a project in any programming language to understand what it does, then walks the developer through the security work relevant to that specific system.

• Security

A curated collection of Google dorks, Shodan and Censys queries, GitHub dorks and Sigma rules for finding exposed AI infrastructure on the internet, aimed at red-team operators, penetration testers and OSINT researchers.

• Security
• Curated lists

A collection of 370 Chinese-language lecture notes covering AI and LLM courses from Stanford, Berkeley, MIT and KAIST, compiled from public course videos, slides and articles and published as a searchable site plus LaTeX source.

• Tutorials

A set of pre-configured skills and a pre-computed dependency graph that give AI coding agents structural knowledge of a specific codebase, plus git hooks that enforce complexity limits and design-system rules.

• Agent skills
• Code quality

A low-footprint CBOR library for microcontrollers, paired with a Python schema tool that validates YAML, JSON, or CBOR data and can generate C code for encoding and decoding it.

• Libraries

A domain-specific language that lets you write mathematical notation as literate, executable source code, compiling it to C++ or WebAssembly while auto-generating LaTeX-style documentation.

• Languages

An NVIDIA AI Workbench example that adds an agentic layer to a RAG pipeline, routing to live web search when retrieved context is thin and evaluating each response for relevance and hallucination.

• RAG
• AI evals

A local, self-hosted security operations center that ingests Wazuh-format events, triages them with a local LLM, retrieves security knowledge for context, correlates incidents, and exports Sigma detection rules.

• Security

A Rust SDK for the Agent2Agent (A2A) protocol, letting Rust programs implement A2A agents or clients.

• Agent frameworks
• Libraries

A GitHub Action that turns natural-language test steps written in a pull request description into generated, executed, and committed Playwright test code, using multi-agent orchestration.

• Testing
• CI/CD