10 source-led articles, briefings and references for Thailand. Every item links to its original source.
* Repository Management: Browse and query code, search files, analyze commits, and understand project structure across any repository you have access to. * Issue & PR Automation: Create, update, and manage issues and pull requests. Let
Read article →
Microsoft Agent Framework (MAF) is an open, multi-language framework for building **production-grade AI agents and multi-agent workflows** in **.NET and Python**. Microsoft Agent Framework is built for teams taking agents from prototype to
Read article →
* **Digital and Physical Worlds:** Magma is the first-ever foundation model for multimodal AI agents, designed to handle complex interactions across both virtual and real environments! * **Versatile Capabilities:** Magma as a single mo
Read article →
**`mcp-agent`** is a simple, composable framework to build effective agents using [Model Context Protocol](https://modelcontextprotocol.io/introduction). mcp-agent's vision is that _MCP is all you need to build agents, and that simple patt
Read article →
Any agent client that speaks **MCP (Streamable HTTP or stdio)**: * **Cursor**, **Windsurf**, **Cline**, **Continue** — via the [`akb-mcp`](https://www.npmjs.com/package/akb-mcp) stdio proxy * Custom agents — direct HTTP `POST /mcp/` w
Read article →
This repository contains [Syllabus](https://github.com/mac999/LLM-RAG-Agent-Tutorial/blob/main/1-1.prepare/syllabus-llm-rag-agent.docx) for LLM(large language model), RAG(retrieval augmented generation), AI Agent and MCP(Model Context Proto
Read article →* Repository Management: Browse and query code, search files, analyze commits, and understand project structure across any repository you have access to. * Issue & PR Automation: Create, update, and manage issues and pull requests. Let
Read article →
Most agent memory is flat retrieval — cosine similarity over text chunks. polyg-mcp is a multi-graph memory system that traces cause-effect chains, reconstructs timelines, maps entity dependencies, and answers "why" with confidence-scored c
Read article →
| "What breaks if I change this model?" | Blast radius across languages + risk score + linked architectural decisions | `get_change_impact` — reverse dependency graph + decision memory | | "Why was auth implemented this way?" | The actual
Read article →
LangChain is a framework for building agents and LLM-powered applications. It helps you chain together interoperable components and third-party integrations to simplify AI application development — all while future-proofing decisions as the
Read article →