[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-1851":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":14,"stars7d":17,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":19,"compositeScore":20,"rankGlobal":10,"rankLanguage":10,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":24,"hasPages":22,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":46,"readmeContent":47,"aiSummary":48,"trendingCount":16,"starSnapshotCount":16,"syncStatus":49,"lastSyncTime":50,"discoverSource":51},1851,"agent-systems-handbook","Prompthon-IO\u002Fagent-systems-handbook","Prompthon-IO","A practical AI agents handbook covering agent systems, agentic workflows, LangGraph, MCP\u002FA2A, context engineering, agent memory, evaluation, observability, and multi-agent architecture. Current trend focus: open agent training environments, emerging agent runtimes, and production AI workflow patterns.","https:\u002F\u002Flabs.prompthon.io\u002F",null,"MDX",314,53,20,6,0,65,122,60,5.2,"Other",false,"main",true,[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"a2a","agent-framework","agent-memory","agentic-ai","agentic-workflow","ai-agent","ai-agents","autonomous-agents","context-engineering","deep-research","developer-tools","generative-ai","langgraph","llm-agents","llm-applications","mcp","multi-agent-systems","prompt-engineering","rag","workflow-automation","2026-06-12 02:00:33","\u003Cdiv align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FPrompthon-IO\">\n    \u003Cimg src=\"https:\u002F\u002Fgithub.com\u002FPrompthon-IO.png?size=160\" alt=\"Prompthon IO\" width=\"96\" height=\"96\" \u002F>\n  \u003C\u002Fa>\n\n  \u003Ch1>Agent Systems Handbook by Prompthon\u003C\u002Fh1>\n\n  \u003Cp>\n    \u003Ca href=\"https:\u002F\u002Flabs.prompthon.io\u002F\">\n      \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVisit-Live%20Site-0A66C2?style=for-the-badge\" alt=\"Visit Live Site\" \u002F>\n    \u003C\u002Fa>\n  \u003C\u002Fp>\n  \n  \u003Cp>\u003Cstrong>AI-agent demos are easy to find. Production-ready agent systems are harder to understand.\u003C\u002Fstrong> This handbook maps the workflows, tools, memory systems, context engineering, MCP\u002FA2A interoperability, evaluation, observability, and multi-agent architecture behind real-world AI agents.\u003C\u002Fp>\n\n  \u003Cp>Use it to understand, design, build, and operate production-minded AI agents — from first principles to framework choices and implementation patterns.\u003C\u002Fp>\n\n  \u003Cp>\n    \u003Cimg src=\".\u002Fassets\u002Fagentic-ai-blueprint.png\" alt=\"Blueprint-style agentic AI system map showing core agent loop concepts\" width=\"100%\" \u002F>\n  \u003C\u002Fp>\n  \n  \u003Cp>\n    \u003Ca href=\"https:\u002F\u002Flabs.prompthon.io\u002F\">\u003Cstrong>labs.prompthon.io\u003C\u002Fstrong>\u003C\u002Fa>\n  \u003C\u002Fp>\n\n  \u003Cp>\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FPrompthon-IO\">\u003Cstrong>Organization\u003C\u002Fstrong>\u003C\u002Fa>\n    ·\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FPrompthon-IO\u002Fagent-systems-handbook\">\u003Cstrong>Repository\u003C\u002Fstrong>\u003C\u002Fa>\n    ·\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FPrompthon-IO\u002Fagent-systems-handbook\">\u003Cstrong>Star\u003C\u002Fstrong>\u003C\u002Fa>\n    ·\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FPrompthon-IO\u002Fagent-systems-handbook\u002Fsubscription\">\u003Cstrong>Watch updates\u003C\u002Fstrong>\u003C\u002Fa>\n    ·\n    \u003Ca href=\".\u002FCONTRIBUTING.md\">\u003Cstrong>Contribute source\u003C\u002Fstrong>\u003C\u002Fa>\n    ·\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FPrompthon-IO\u002Fagent-systems-handbook\u002Fissues\">\u003Cstrong>Issues\u003C\u002Fstrong>\u003C\u002Fa>\n    ·\n    \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FsDE2HhGTg4\">\u003Cstrong>Discord\u003C\u002Fstrong>\u003C\u002Fa>\n  \u003C\u002Fp>\n\n  \u003Cp>\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FPrompthon-IO\u002Fagent-systems-handbook?style=flat-square\" alt=\"Last commit\" \u002F>\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FPrompthon-IO\u002Fagent-systems-handbook?style=flat-square\" alt=\"GitHub stars\" \u002F>\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FPrompthon-IO\u002Fagent-systems-handbook?style=flat-square\" alt=\"GitHub forks\" \u002F>\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues\u002FPrompthon-IO\u002Fagent-systems-handbook?style=flat-square\" alt=\"GitHub issues\" \u002F>\n  \u003C\u002Fp>\n\u003C\u002Fdiv>\n\n---\n\n## Overview\n\nPrompthon Agentic Labs publishes the Agent Systems Handbook by Prompthon: an AI-native field guide for students, practitioners, and builders exploring modern agent systems from different angles.\n\nBuilt on **learn, question, and innovate**, the lab is shaped by learners and grounded in real industry practice. It helps readers understand the space, apply AI effectively, or build real systems through parallel paths rather than a single track.\n\n## Why This Lab Fits AI-Native Learners, Practitioners, And Builders\n\n### Built on learn, question, and innovate\n\nThis repository encourages active learning, critical thinking, and experimentation rather than passive consumption.\n\n### Built by learners, not only for learners\n\nMany contributors are learners themselves. That keeps the material close to the questions, habits, and learning paths that students, new grads, and next-generation AI-native builders actually have.\n\n### Guided by real industry practice\n\nThrough Prompthon programs and industry-facing guidance, the lab remains connected to how frontier teams think, build, iterate, and evaluate in real settings.\n\n### AI-native by design\n\nThe content is created through an AI-native workflow that combines AI-assisted drafting, synthesis, iteration, and refinement with expert guidance and review.\n\n### Designed for different paths, not a single track\n\nThe lab is organized for different kinds of learners and different intentions. Some people want broad understanding and trend awareness. Some want to apply AI tools to daily work and study. Some want to build real systems and applications. This repository supports all three without forcing one sequence.\n\n## What This Handbook Covers\n\n- AI agent foundations and agent-system mental models\n- Agentic workflows, planning, reflection, tool use, and function calling\n- Agent memory, retrieval, context engineering, and agentic RAG\n- MCP, A2A, protocol interoperability, and agent communication boundaries\n- LangGraph, agent frameworks, hosted builders, and low-code platforms\n- Multi-agent orchestration, evaluation, observability, reliability, and safety\n- Deep research agents, customer-support agents, source projects, and starter examples\n\n## Start Here\n\nChoose the path that best matches what you want from AI right now. These are parallel tracks for different types of learners and builders, not a required sequence.\n\n\u003Ctable>\n  \u003Ctr>\n    \u003Ctd valign=\"top\" width=\"50%\">\n      \u003Ch3>Explorer\u003C\u002Fh3>\n      \u003Cp>For students, newcomers, and curious AI-native readers who want a broad view of AI, agents, trends, and foundational ideas without needing to become engineers.\u003C\u002Fp>\n      \u003Cp>\u003Cstrong>What you get:\u003C\u002Fstrong> a curated set of high-signal reads that help you learn core concepts, follow important shifts, test ideas with your own thinking, and build a grounded first-hand understanding of the space.\u003C\u002Fp>\n      \u003Cp>\u003Ca href=\".\u002Freading-paths\u002Fexplorer.mdx\">\u003Cstrong>Open the Explorer guide\u003C\u002Fstrong>\u003C\u002Fa>\u003C\u002Fp>\n    \u003C\u002Ftd>\n    \u003Ctd valign=\"top\" width=\"50%\">\n      \u003Ch3>Practitioner\u003C\u002Fh3>\n      \u003Cp>For people who want to use AI tools, agents, and workflows to enhance daily life, study, and real work without needing to become full-time engineers.\u003C\u002Fp>\n      \u003Cp>\u003Cstrong>What you get:\u003C\u002Fstrong> a practical path for learning how to apply AI effectively, choose the right tools and workflows, and operate with leverage in real scenarios, including one-person-company style use cases where AI expands what one person can do without requiring full builder depth.\u003C\u002Fp>\n      \u003Cp>\u003Ca href=\".\u002Freading-paths\u002Fpractitioner.mdx\">\u003Cstrong>Open the Practitioner guide\u003C\u002Fstrong>\u003C\u002Fa>\u003C\u002Fp>\n    \u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd valign=\"top\" width=\"50%\">\n      \u003Ch3>Builder\u003C\u002Fh3>\n      \u003Cp>For engineering-minded learners, new grads, and developers who want to build with AI more directly, from agent applications and workflows to startup-style products and technically deeper implementations.\u003C\u002Fp>\n      \u003Cp>\u003Cstrong>What you get:\u003C\u002Fstrong> a build-oriented path through concepts, patterns, systems, architecture choices, technical details, and concrete examples for people who want to create their own applications and go deeper into implementation.\u003C\u002Fp>\n      \u003Cp>\u003Ca href=\".\u002Freading-paths\u002Fbuilder.mdx\">\u003Cstrong>Open the Builder guide\u003C\u002Fstrong>\u003C\u002Fa>\u003C\u002Fp>\n    \u003C\u002Ftd>\n    \u003Ctd valign=\"top\" width=\"50%\">\n      \u003Ch3>Contributor\u003C\u002Fh3>\n      \u003Cp>For people who want to shape the lab by adding, revising, curating, or maintaining pages, notes, examples, and outward-facing extensions.\u003C\u002Fp>\n      \u003Cp>\u003Cstrong>What you get:\u003C\u002Fstrong> a public path into the editorial workflow, templates, review rules, placement standards, and portfolio-relevant open-source contribution.\u003C\u002Fp>\n      \u003Cp>\u003Ca href=\".\u002Freading-paths\u002Fcontributor.mdx\">\u003Cstrong>Open the Contributor guide\u003C\u002Fstrong>\u003C\u002Fa>\u003C\u002Fp>\n    \u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\n\n## Contributor Guide\n\nIf you want to contribute to Prompthon Agentic Labs, start from the contributor docs rather than ad hoc internal working material.\n\nPublic contributions in this repository currently fit into these paths:\n\n- lab articles in `foundations\u002F`, `patterns\u002F`, `systems\u002F`, `ecosystem\u002F`, or\n  `case-studies\u002F`\n- radar notes in [`radar\u002F`](.\u002Fradar\u002F)\n- source projects in lane-local `examples\u002F` folders\n- practitioner skill packages in [`skills\u002F`](.\u002Fskills\u002Findex.mdx)\n- curated reference notes in\n  [`contributor-kit\u002Freference-notes\u002F`](.\u002Fcontributor-kit\u002Freference-notes\u002FREADME.md)\n- publication extensions in [`publications\u002F`](.\u002Fpublications\u002FREADME.md) once a\n  lab page is ready for an outward-facing article or distribution surface\n\nStart with [Contributing](.\u002FCONTRIBUTING.md) and the [Contributor Kit](.\u002Fcontributor-kit\u002Findex.mdx). Those pages define the public workflow, templates, review standards, and placement rules for lab articles, notes, and code that belong in this repository.\n","Prompthon-IO\u002Fagent-systems-handbook 是一本实用的AI代理系统手册，涵盖了代理系统、代理工作流、LangGraph、MCP\u002FA2A互操作性、上下文工程、代理内存、评估、可观测性和多代理架构等内容。该项目通过深入研究和实际案例，帮助读者理解、设计、构建和运营生产级AI代理系统。它适合于希望从基础原理到框架选择再到实现模式全面了解AI代理系统的开发者和研究人员。此外，该手册还关注当前趋势，如间接提示注入防御、新兴代理运行时和生产AI工作流模式等，为实践者提供了宝贵的资源。",2,"2026-06-11 02:46:24","CREATED_QUERY"]