Skip to content

Entry

AI Agents in Depth

Appears in 4 awesome lists

《深入理解 AI Agent:设计原理与工程实践》开源项目是一座将前沿大模型智能体理论转化为可落地代码的工程化知识库,精准击穿了当前开发者在从理论认知迈向实际部署过程中资料割裂、缺乏系统实践指引的痛点。该项目彻底打破了传统技术图书“重概念轻实操”或社区仓库“碎片化拼凑”的固有困境,凭借单一线性叙事构建的知识体系与标准化交付形态,为学习者铺设了一条从底层逻辑到上层应用的平滑过渡路径。其核心优势在于高度一体化的内容编排、严丝合缝的章节配套代码生态以及贯穿始终的工程化思维导向,这不仅有效规避了多源资料整合时的环境冲突风险,更通过标准化的技术栈封装大幅降低了上手门槛,使初学者无需在海量…

Open github.combojieli/ai-agent-book

Found in these lists

Awesome Open Source AI

Section: 14. Resources & Learning · Open-source textbook and code repository covering AI agent design principles, architectures, and engineering practice. Apache 2.0 licensed.

FreshScore 89

Awesome Roadmaps

Section: Articles & Books · Open-source book on AI agent design and engineering, with bilingual (Chinese/English) text and per-chapter code covering context engineering, tools, evaluation, and multi-agent systems.

FreshScore 83

目录

Section: 大语言对话模型及数据 · 《深入理解 AI Agent:设计原理与工程实践》开源项目是一座将前沿大模型智能体理论转化为可落地代码的工程化知识库,精准击穿了当前开发者在从理论认知迈向实际部署过程中资料割裂、缺乏系统实践指引的痛点。该项目彻底打破了传统技术图书“重概念轻实操”或社区仓库“碎片化拼凑”的固有困境,凭借单一线性叙事构建的知识体系与标准化交付形态,为学习者铺设了一条从底层逻辑到上层应用的平滑过渡路径。其核心优势在于高度一体化的内容编排、严丝合缝的章节配套代码生态以及贯穿始终的工程化思维导向,这不仅有效规避了多源资料整合时的环境冲突风险,更通过标准化的技术栈封装大幅降低了上手门槛,使初学者无需在海量…

FreshScore 81

awesome-python

Section: Other · 《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码

FreshScore 81

Awesome Machine Learning

The definitive curated list of machine learning frameworks, libraries and software organized by language. Covers Python, C++, Java, JavaScript, and more with comprehensive coverage of the ML ecosystem. CC0-1.0 licensed.

In 15 listsDetails

Awesome Artificial Intelligence

Curated list of artificial intelligence courses, books, video lectures, and papers for developers and researchers. MIT licensed.

In 7 listsDetails

wanshuiyin/Auto-claude-code-research-in-sleep

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

In 7 listsDetails

Awesome DESIGN.md

Curated collection of DESIGN.md files representing popular design systems to guide AI coding agents in consistent UI generation. MIT licensed.

In 2 listsDetails

Orca

The AI orchestrator for running Codex, Claude Code, OpenCode, and Pi side-by-side in isolated git worktrees. It turns fleet-of-agents execution into a polished desktop IDE with a mobile companion, making parallel agent harness design accessible beyond shell-scripting teams.

In 6 listsDetails

Claude Cookbooks

Anthropic's official notebook collection covering orchestrator-worker patterns, parallel tool calling, programmatic tool calling (PTC), context compaction, and Agent SDK examples. The patterns/agents/ directory is the reference implementation of every orchestration pattern described in Building…

In 6 listsDetails

Effective Context Engineering for AI Agents

Anthropic's systematic guide to managing the full context state—system prompts, tools, MCP, and message history—as a finite, curated resource. Reframes harness design as "what configuration of context produces the desired behavior?" rather than just prompt wording.

In 5 listsDetails

Claude Squad

smtg-ai/claude-squad 是一个专为管理多AI终端代理(如Claude Code、Codex、OpenCode等)设计的开源调度框架,其核心解决了开发者需同时调用不同AI服务时面临的协作效率低与资源分配混乱的痛点。通过统一的任务分发与响应聚合机制,该项目让异构AI代理能像“协同作战的小队”一样各司其职,显著提升复杂场景下的自动化处理能力。项目的核心亮点在于其三大设计优势:首先,它采用动态负载均衡策略,可实时监测各代理的性能状态,类似交通导航系统智能分配车流,避免单一代理过载而其他闲置的浪费;其次,内置的容错与重试机制能自动识别代理的异常响应,像经验丰富的指挥官临时调整战术,确…

In 5 listsDetails