Explore the directory

A curated, browsable collection of learning resources covering generative AI, machine learning, agentic AI, retrieval-augmented generation, fine-tuning and MLOps.

• Tutorials
• Curated lists

OneResearchClaw is a skill-driven research-automation pipeline that turns meeting recordings, documents, tables, slide decks, archives, or arXiv, YouTube and Bilibili links into structured research reports.

• Agent frameworks

A conversation-aware chatbot that answers questions using retrieval-augmented generation over a folder of Markdown files, running entirely on a local language model.

• RAG

A command-line inspector for Model Context Protocol servers that lists and calls their tools, resources and prompts interactively or from a config file.

• MCP servers
• CLI tools

An agentic AI framework built on Apache Flink, letting agent workflows run as distributed, event-driven Flink jobs.

• Agent frameworks
• Data engineering

A modern attack-surface reconnaissance and asset-intelligence platform, rebuilt from the classic ARL project with an async microservice architecture and a native Model Context Protocol server for AI-assisted analysis.

• MCP servers
• Security

An open-source AI desktop application for working with local language models, files, tools and agents, with local inference as its core and optional connections to cloud models and services.

• Coding agents
• Inference

The communication channel for Anthropic's Model Context Protocol integration in Claude.ai: an announcements and issue tracker for protocol changes, session behavior, and MCP server or integration bugs.

• MCP servers

A collection of reference Model Context Protocol servers for managing and interacting with Oracle products and Oracle Cloud Infrastructure, provided for exploration and prototyping rather than production use.

• MCP servers

A collection of official and community sample apps, model recipes and utilities for LiteRT, Google's on-device machine learning framework formerly known as TensorFlow Lite, and LiteRT-LM, its layer for running language models on-device.

• Inference
• Tutorials

A TypeScript framework that pairs an agent-reasoning core with a production harness of event-backed execution, checkpoints, recovery and audit, so an application's specific behavior is declared separately from the runtime.

• Agent frameworks

A curated list of remote Model Context Protocol servers reachable over a URL, as opposed to servers a user installs and runs locally.

• MCP servers
• Curated lists

Learn Anything generates skill and slash-command files for more than 30 AI coding tools, turning a coding assistant into an interactive tutor with Socratic explanations, TDD-style exercises, spaced repetition and a knowledge dashboard.

• Agent skills
• Tutorials

A gateway that connects chat platforms, starting with WeChat, to a shared Codex engine, so a team can drive Codex sessions, slash commands and approvals from chat instead of a terminal.

• Coding agents

A platform that turns a team's Slack, Discord, Teams and Mattermost conversations into a self-maintaining wiki, extracting facts and building a cited knowledge graph queryable in natural language or through MCP.

• MCP servers
• Agent memory

An open-source toolkit for quantizing and compressing PyTorch and Keras neural networks for efficient, constrained hardware, with post-training quantization, gradient-based fine-tuning and quantization-aware training.

• Models

A browser-based, no-install graphical interface for chatting with Ollama and other local or OpenAI-compatible language model servers, with chats stored only in the browser.

• Inference

A catalog of downloadable, verified model conversions and their conversion recipes for Apple's on-device Core AI runtime on iPhone and Mac, each carrying the recipe and validation evidence used to produce it.

• Models

A plugin for OpenCode that splits a single AI coding session into an architect-led team of specialized agents for implementation, review, testing, security and documentation, with required gates before anything ships.

• Coding agents
• Agent frameworks

An open-source platform that runs a ready-made organization of collaborating AI agents, such as a CEO agent that breaks a goal into tasks and assigns them to department agents, instead of requiring hand-built orchestration.

• Agent frameworks

A full-stack starter built with Vue and Gin that ships built-in retrieval-augmented generation: knowledge bases, vector search, agent orchestration on a visual canvas, and many LLM and vector-store integrations.

• RAG
• Web frameworks

A task board built for autonomous coding agents rather than people, where agents claim and execute tasks through machine-discoverable APIs while humans review and approve the work.

• Coding agents
• Workflow automation

The official Python client for the Pinecone vector database, used to create and manage indexes, upsert and query records, and run inference operations.

• Databases

A spec-driven workflow framework for AI coding agents that turns a request into repository files tracking proposal, design, plan, tasks, review and verification evidence, so any assistant can resume the work.

• Coding agents
• Agent frameworks