Sources Registry

Last reviewed: 2026-08-22

版本敏感事实优先使用规范、官方 SDK 文档和厂商 Engineering 文档。社区资料只作为补充。

01. Agent / Harness Foundations

• Anthropic — Building effective agents
• Anthropic — Scaling Managed Agents: Decoupling the brain from the hands
• OpenAI Agents SDK — Agents
• OpenAI Agents SDK — Agent orchestration

02. Model Layer & Structured Interaction

• OpenAI Agents SDK — Models
• OpenAI Agents SDK — Running agents
• OpenAI Agents SDK — Testing
• OpenAI Agents SDK — Results

03. Prompt & Context Engineering

• Anthropic — Effective context engineering for AI agents
• Anthropic — Advanced tool use
• Anthropic — Effective harnesses for long-running agents

04. Retrieval & RAG

• OpenAI API — Vector stores
• LangChain — Retrieval
• LangGraph — Agentic RAG
• LangChain — Cross encoder reranker

05. Tool Engineering

• Anthropic — Writing effective tools for AI agents
• Anthropic — Advanced tool use
• OpenAI Agents SDK — Tools

06. Planning & Orchestration

• Anthropic — Building effective agents
• OpenAI Agents SDK — Agent orchestration
• OpenAI Agents SDK — Handoffs

07. Execution Runtime

• OpenAI Agents SDK — Running agents
• LangGraph — Persistence
• LangGraph — Interrupts

08. State / Session / Memory

• OpenAI Agents SDK — Sessions
• OpenAI Agents SDK — Agent memory
• LangGraph — Persistence

09. MCP

• MCP — 2026-07-28 Specification
• MCP — Release Candidate technical detail
• Model Context Protocol

10. Reliability & Human Control

• OpenAI Agents SDK — Human-in-the-loop
• OpenAI Agents SDK — Guardrails
• LangGraph — Interrupts

11. Observability, Testing & Evaluation

• OpenAI Agents SDK — Tracing
• OpenAI Agents SDK — Testing
• OpenTelemetry — GenAI semantic conventions
• LangGraph — Persistence

12. Workspace & Coding-Agent Engineering

• OpenAI Agents SDK — Sandbox agents concepts
• OpenAI Agents SDK — Sandbox agents quickstart
• Anthropic — Effective harnesses for long-running agents

13. Security & Sandbox

• Anthropic — How we contain Claude across products
• OWASP — Top 10 for Large Language Model Applications
• OpenAI Agents SDK — Sandbox concepts

14. Performance, Cost & Capacity

• OpenAI Agents SDK — Running agents
• OpenAI Agents SDK — Tracing
• OpenTelemetry — GenAI semantic conventions

15. Python Engineering

• Python 3.14 Documentation
• uv — Project structure and files
• uv — Configuring projects
• Pydantic Documentation
• pytest Documentation

16. Async & Concurrency

• Python 3.14 — Coroutines and Tasks
• Python — asyncio queues
• Python — asyncio synchronization primitives

17. HTTP & Streaming

• FastAPI — WebSockets
• FastAPI — Streaming data
• RFC 9110 — HTTP Semantics

18. Database & Durable Storage

• PostgreSQL 18 — Documentation
• PostgreSQL — Transaction processing
• PostgreSQL — Indexes

19. Cache / Redis / Queue

• Redis Documentation
• Redis data types
• Redis Streams

20. Docker / Linux / Deployment

• Docker Documentation
• Docker — Resource constraints
• Docker — Build cache

21. Shadow Harness Architecture

• Anthropic — Building effective agents
• OpenAI Agents SDK
• LangGraph — Persistence
• MCP — 2026-07-28 Specification