Explore the directory

An open-source book, written in Burmese for Myanmar developers, explaining agentic AI concepts such as tool calling, RAG, MCP, context engineering, and coding agents from a practical angle.

• Books

A curated list of tools and frameworks for running, building, and deploying AI privately on-prem, air-gapped, or self-hosted, spanning inference engines, model serving, and privacy tooling.

• Curated lists

An official OWASP project that screens an AI agent's memory writes against a policy, blocking prompt-injection-style attempts to poison persistent memory that survive a context reset.

• Agent memory
• AI evals

A Swift reimplementation of a Claude Code-style coding agent, rebuilt one stage at a time to test which architectural choices actually make a coding agent work well.

• Coding agents
• Tutorials

A four-course, hands-on learning path, with free accompanying videos, for building AI agents with AWS's Strands Agents framework from fundamentals through production deployment.

• Tutorials

A set of runnable, graded example agents for the telecom industry, built to run on Red Hat OpenShift AI, showing how to turn a proven experiment into a governed agent workload.

• Tutorials

A Java code-completion library for Swing text components, with extra features when used with RSyntaxTextArea, offering a live completion list, documentation popups, and parameter assistance.

• Editors
• Libraries

An AI agent skills marketplace combining a web catalog, a semantic and keyword search engine, and a CLI, so an agent can find and run a matching skill for a task.

• Agent skills

A VS Code extension that brings the Pi coding agent into a sidebar and editor tabs, reusing the user's existing Pi configuration, extensions, skills, and models.

• Coding agents

A maintained paper list and taxonomy accompanying a TMLR survey on using LLMs to automate phone interfaces, covering prompting, training-based methods, datasets, and benchmarks.

• Papers

A growing series of blog posts and videos teaching AI agent concepts step by step, from function calling and agent loops to multi-agent orchestration and evaluation.

• Tutorials

A collection of model-specific prompt-engineering skills and guides for Claude Code, ChatGPT, and Gemini, covering text, image, video, research, and slide-writing patterns.

• Agent skills

A ComfyUI custom node set that adds text and image generation from Gemini, OpenAI, Claude, Ollama, and Qwen, along with several image-editing and object-detection models, in one extension.

• Generative media

An Android app and reference project that performs on-device face recognition by comparing FaceNet embeddings against a local vector database of known faces.

• Mobile
• Databases

A companion code library for a Manning book that teaches how LLM agents and multi-agent systems work by building one from first principles, without relying on an existing framework.

• Tutorials
• Books

A library of more than 150 agent skills that teach AI coding assistants how to plan, generate, and check image, video, audio, and voice production work.

• Agent skills
• Generative media

A local research assistant that searches Semantic Scholar for a topic, filters and summarizes the papers it finds, and answers questions grounded only in that retrieved set.

• RAG

A curated list of inference engines, vendor SDKs, and research papers for running machine learning models, including large language models, efficiently on mobile and edge devices.

• Inference
• Curated lists

A Windows-first desktop AI workbench that turns chat requests into inspectable local tasks, producing artifacts, runtime receipts, and a record of what actually changed.

• Agent frameworks
• Desktop

A command-line tool that redesigns an existing HTML page using only the content already in it, its headings, facts, numbers, and colors, and outputs a single standalone HTML file.

• CLI tools
• Design tools

A community-maintained Chinese documentation and guide site for OpenClaw, an open-source, self-hostable personal AI agent, covering installation, chat channels, and configuration.

• Books
• Documentation tools

A local LLM server, wrapping llama.cpp, built as a drop-in replacement for Ollama that reuses a shared prompt's KV cache across concurrent requests instead of reprocessing it each time.

• Inference

A searchable catalog of plugins, skills, and MCP servers for the DeepSeek Harness AI coding tool, each checked individually to confirm it is a real plugin.

• Curated lists

An open survey and evidence map for judging whether an AI agent system genuinely improves itself from feedback, rather than only appearing smarter in a demo.

• Curated lists
• Papers