《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.

One agent. Every kind of work.

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.

The Architecture Review Agent is an open-source AI agent sample that reviews software architectures and generates interactive diagrams automatically.

Benchmarking the gap between AI agent hype and architecture. Three agent archetypes, 73-point performance spread, stress testing, network resilience, and ensemble coordination analysis with statistical validation.

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.

Universal autonomous agent framework with ReAct loop, multi-provider LLM routing, reasoning graph, and MCP integration, domain-agnostic for building specialized AI agents.

A comprehensive reference for building and organizing AI agent skills across Claude Code, KiloCode, OpenClaw, and OpenAI Codex. Covers SKILL.md specifications, folder structures, mode-scoped skills, agent orchestration, and self-hosted model configuration.

用钱学森工程控制论重塑 AI Agent 架构。前馈、积分控制、层级分离、自监控——让 Agent 真正懂你。—— Feedforward, integral control, hierarchical decomposition, and self-monitoring for a self-evolving agent that truly understands you.

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.

The canonical standard for building production-grade agentic products — autonomy ladder, composition patterns, the 8-layer harness, eval discipline — plus a Claude Code skill set that operationalizes it.

A Recursive Ontological Framework for Cognitive Design, Neurodivergence Modeling, AI Co-Development, and "Structural AI"

Transform your AI from a forgetful junior dev into a Senior Tech Lead. Persistent project memory + specialized agent skills for any AI coding assistant.

OpenClaw source code architecture analysis of a production AI Agent gateway — Agent Loop, memory, tool sandbox, custom WebSocket protocol, 20+ IM adapters. 从 Agent Loop、记忆系统、工具沙箱到自研 WebSocket 协议 —— 拆解一个真正跑在生产环境中的多通道 AI Agent 网关是如何设计与实现的。

An agent-native GTM pipeline runtime that turns a plain-English campaign brief into a qualified, enriched, deduped, sequencer-ready contact list — without locking your workflow into one data provider.

Technical Research: System prompts as governance constitutions for AI developer assistants.

LIFE — Persistent identity architecture for AI agents. 16 MCP servers: drives, heart, memory, patterns, journal, genesis, garden, vision, voice, and more. Zero dependencies. Built across 938 conversations.

Benchmarked agent execution runtime for Python. Sub-10ms cold starts, real-time streaming, time-travel debugging, and self-growing tool libraries. Compare 3 sandbox backends: Docker (OpenSandbox), MicroVM, and in-process AST.