claude-code-book
《御舆:解码 Agent Harness》42万字拆解 AI Agent 的Harness骨架与神经 —— Claude Code 架构深度剖析,15 章从对话循环到构建你自己的 Agent Harness。在线阅读网站:
- 4.4k
- Python
- 5 d ago
《御舆:解码 Agent Harness》42万字拆解 AI Agent 的Harness骨架与神经 —— Claude Code 架构深度剖析,15 章从对话循环到构建你自己的 Agent Harness。在线阅读网站:
Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning.
A 7×6 framework for agent architecture. 28 patterns, each placed at a coordinate, runnable Python code with verified engineering slices from Claude Code, Aider, OpenHands, DeerFlow. Companion to Designing AI Agents (Manning) by Jia Huang.
Engineering deterministic, production-grade systems around non-deterministic LLMs — FSM, durable execution, retries, DAGs, agent runtimes, model routing, edge inference, RAG, memory, multi-agent orchestration, security, and observability. 14 runnable proof-of-concept phases.
Build production-ready AI agents in Claude Code from natural language. Analyzes your problem, researches best practices, and generates subagents, skills, hooks, commands & MCP configs.
🎙️ Voice-native document intelligence using Gemini, ElevenLabs STT/TTS, and Datadog observability — turning text documents into spoken conversations.
How to design AI agents that work as one: nine parts of an agent and its team, checked against 85 sources. Free guide in Markdown and PDF, with the drawings.
本源计算架构 · An open architecture for persistent AI computers. 模型可换,状态不丢,动作可迁移,经验会复利。
龙虾进化手册:给 OpenClaw / Claude Code 等 AI agent 开发者的中文实战指南,六大核心素养——心跳轮询、三层记忆、子 agent 并行调度、想法农场、降级自愈、冥想反思,每节附 Python 示例、踩坑表和练习题。A Chinese hands-on guide to six AI agent architecture patterns.
A comprehensive defense matrix for autonomous AI agents. Maps out attack vectors (Goal Hijacking, CoT Poisoning, Inter-Agent Spoofing) and corresponding defensive strategies across the agent lifecycle. Inspired by MITRE ATT&CK, tailored for LLMs.
A curated list of classical BDI and procedural-reasoning agent architectures, distinct from modern LLM agent frameworks.
Build production-ready AI agents in Claude Code by automatically generating agents, skills, hooks, and commands from your problem description.
A collection of the messy problems I've hit, the weird fixes I found, and the refactors that finally made things behave. Basically, my debugging diary, but useful.