Explore the directory

The official MCP server for Magic UI, letting an AI editor such as Cursor, Windsurf or Claude search, browse and install Magic UI components from natural-language requests.

• MCP servers
• UI kits

A Model Context Protocol server for MariaDB that lets AI assistants list databases and tables, read schemas, run read-only SQL queries, and create and query vector embedding stores.

• MCP servers
• Databases

An open-source, wire-first SDK that standardizes LLM, embedding, vector and graph infrastructure behind one protocol, so an application can swap providers without rewriting integration code across LangChain, LlamaIndex, AutoGen, CrewAI or MCP.

• LLM gateways

An offline cybersecurity knowledge base of cheatsheets covering secure development, secure administration, pentesting, forensics, and radio frequencies, paired with a deliberately vulnerable practice app.

• Security

An MCP server that exposes the full Zabbix monitoring API as 237 tools, so AI assistants such as Claude, Codex or JetBrains AI can query hosts, check problems and manage templates.

• MCP servers
• Monitoring

An MCP server that gives AI coding agents a persistent, server-enforced work item graph with quality gates, dependency tracking and actor attribution, instead of relying on the model to follow prompted rules.

• MCP servers
• Workflow automation

An open-source terminal coding agent with Plan, Agent and YOLO modes, MCP and LSP support, and bring-your-own-key routing across 28 built-in model providers with a transparent cost meter.

• Coding agents
• Terminals

A native AI and agent client for iOS and Apple Watch that connects to OpenAI, Anthropic Claude and Google Gemini, or runs local GGUF models offline through llama.cpp, with local RAG and MCP tools.

• Inference
• Mobile

A curated, cross-linked map of AI agent frameworks, coding agents, MCP and protocol tooling, memory and knowledge-graph systems, and on-chain identity and payment infrastructure for building agents.

• Curated lists

A post-training quantization toolkit for LiteRT and LiteRT-LM models, letting developers shrink vision and LLM models for deployment on mobile CPUs, GPUs and NPUs.

• Inference
• Mobile

An open-source AI customer support system that answers from a knowledge base first, hands off to a human when needed, and tracks the conversation through to a support ticket.

• Backend

An open-source desktop app that runs a team of specialist AI coding agents on your machine, carrying project memory between sessions, using a built-in model, Ollama or any OpenAI-compatible endpoint.

• Coding agents
• Agent memory

A self-hosted, single-container dashboard for a home lab and AI rig, showing GPU usage and cost, container and disk health, and uptime across every machine over SSH, with a read-only MCP server for AI agents.

• MCP servers
• Monitoring

A macOS desktop workbench for the pi coding agent, offering parallel chat sessions in isolated git worktrees, session forking, checkpoints and a visual review of every diff and tool call.

• Coding agents
• Desktop

A native macOS app for benchmarking and comparing local large language models across any OpenAI-compatible backend, with real-time hardware telemetry alongside inference performance history.

• Inference
• AI evals

A VS Code extension that mirrors a running Google Antigravity IDE AI session to a phone over the local network, so a developer can read streamed responses, send messages, stop generation and upload files remotely.

• Coding agents
• Editors

A Go client library for the Chroma vector database, tracking specific Chroma server versions across its release lines.

• Databases

A local-first retrieval-augmented question-answering system that combines semantic and keyword search with a ReAct agent loop, citation checking, and task recovery after a restart.

• Agent frameworks
• RAG

A C# client for the Ollama API, auto-generated from its OpenAPI specification, covering chat, streaming completions, embeddings, model management and tool calling for .NET applications.

• Inference
• Libraries

A self-hostable Streamlit chat application that talks to local Ollama models (or optionally OpenAI), with document RAG over PDFs, image chat and Whisper-based voice input.

• RAG
• Inference

An installable, agent-agnostic external memory system for Claude Code, Codex, Cursor, Hermes and similar agents, archiving sessions and building long-term recall without modifying the agent itself.

• Agent memory

A PHP client library for the Ollama API, covering chat and text completion (including streaming), model management and embeddings, for PHP 8.1 and above.

• Inference
• Libraries

A fast, lightweight vector database with a Python API, offering an in-memory HNSW-based index for low-latency search and an on-disk quantized graph index for billion-scale datasets that exceed RAM.

• Databases

A quantization-aware distillation method that shrinks an 8B vision-language model into a 2B student and deploys it as genuine packed INT4 weights, retaining most of the teacher's accuracy.

• Models