Explore the directory

A curated list of AI agent skills, agent teams, MCP servers and other tools that teach AI coding assistants how to write expert-level Swift and iOS code.

• Agent skills
• Curated lists

A Python library for running and fine-tuning small, task-specific language models on CPU, generating synthetic training data instead of requiring a labeled dataset.

• Models

A native Android app that runs AI coding agents such as OpenCode, Claude Code, Google Antigravity and OpenAI Codex directly on the phone through a touch interface, with no terminal or PC required.

• Coding agents

A fully local voice AI app for iOS that runs speech-to-text, a language model and text-to-speech entirely on an iPhone's Neural Engine, GPU and CPU, with real-time conversation and no cloud calls after setup.

• Speech

A queryable personal knowledge base over scattered notes, docs and chat logs, using hybrid vector-plus-keyword retrieval with section-level citations and an MCP server so AI agents can use the same index.

• Agent memory
• RAG

An open, execution-agnostic Kanban task-management engine shared by humans and AI agents, storing tasks in one git-synced JSON file and exposing them through a CLI, a web dashboard, a REST API, webhooks and an MCP server.

• MCP servers
• CLI tools

A high-performance knowledge graph engine built for LLMs, GraphRAG and AI-native applications, using sparse matrix algebra for sub-millisecond graph traversals and full OpenCypher query support.

• RAG
• Databases

A local AI research agent that answers questions through Ollama by combining web search, open-source intelligence lookups and multi-hop retrieval-augmented reasoning.

• RAG
• Security

An unofficial, community-built Visual Studio 2026 extension that gives the Claude Code CLI a native diff view with accept and reject, a live debugger it can drive, Roslyn code navigation, and Test Explorer integration.

• Editors

A suite of tools for automated benchmarking of retrieval-augmented-generation systems, generating synthetic queries, judging answers with an LLM, and preparing datasets for reproducible testing at scale.

• RAG
• AI evals

An open-source AI browser that operates the web from plain-language commands, reading the page and clicking, typing and scrolling with a real mouse and keyboard, using cloud models such as DeepSeek or a local Ollama model.

• Browser automation

A weekly-updated, community-maintained directory of every connector in Anthropic's Claude Connectors catalog, covering both the curated web directory and the in-app catalog, organized by category with descriptions and use cases.

• MCP servers
• Curated lists

A ComfyUI custom node package that merges two earlier MiniMax H3 integrations into one AI video generation workflow, with a forced unique node namespace to avoid conflicts with other MiniMax node packs.

• Generative media

A local automation loop that discovers, benchmarks and safely upgrades a machine's own LLM inference setup, keeping a stable OpenAI-compatible API address and rolling back automatically if a candidate optimization fails quality checks.

• Inference

A type-safe, declarative Swift framework for building AI agent pipelines out of composable steps, built on Apple's FoundationModels, with structured output, permission and sandbox guardrails, and MCP support.

• Agent frameworks

A Python library for building autonomous negotiation agents embedded in business-like simulations, supporting bilateral and multilateral negotiations under multiple protocols.

• Agent frameworks
• Libraries

A lightweight Python framework for quickly building a specialized AI agent for one industry or task and delivering it as an API service, with built-in retrieval-augmented generation and injectable domain skills.

• Agent frameworks
• RAG

A TypeScript framework for building and deploying conversational AI agents quickly, with a tool and middleware system and one-command hosted deployment.

• Agent frameworks

A private AI chat app for iPhone and iPad that runs entirely on-device using Apple's MLX framework, supporting models such as Llama, Qwen, Gemma and a distilled DeepSeek reasoning model with no internet connection required.

• Inference

A benchmark that measures how well frontier AI models can write Blender Python code that procedurally builds a specific 3D object, scored on executability, image similarity, 3D shape distance and a language-model judge.

• AI evals

A production-focused multi-agent runtime platform, built on FastAPI and LangGraph, that dispatches user requests through a supervisor agent to specialized subagents with session isolation, long-term memory and dynamic model switching.

• Agent frameworks
• Agent memory

A multi-tenant agentic AI platform that coordinates LLM-powered agents to analyze tasks, generate code, review changes and open pull requests autonomously, running on an existing Claude Code or Codex CLI subscription instead of metered API billing.

• Coding agents
• Agent frameworks

An import-compatible fork of the python-docx library for creating and editing Word documents, adding guarded APIs that refuse an operation it cannot represent safely instead of silently corrupting the file.

• Libraries

A chapter-by-chapter playbook on turning an AI demo into a dependable product, using a single running example, an academic research assistant, to make model selection, evaluation and architecture decisions concrete.

• Tutorials
• Books