hyper-open /

diagram-first-agent

Agent 学习手册：一套以架构图为主线的中文 Agent 教程，它先给出 Agent 平台的分层总览，再沿八级演进逐层展开：ReAct → 工具调用 → 模型网关 → 工具网关 → RAG → 意图识别 → 多 Agent → 平台化。每一章以架构图开篇，配读图步骤、请求时序、故障模式与优化矩阵，并补充内容安全、隐私、合规、测试、发布、长任务可靠性等生产化主题。 项目内置一个只用 Python 标准库实现的 Mini Agent，包含工具调用、记忆、预算、停滞检测、trace 与评测 harness，并提供无需服务器、双击即可阅读的离线 HTML 版本。

A new way for AI to search for data
View on GitHub
1GitHub stars
7commits on main
0forks

HTML 89.4%, Python 5.5%, CSS 3.2%, JavaScript 1.8% · created 2026-10-24 · last push 2026-10-25

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit e4f72d0822 (2026-10-25). main is 1 commit ahead.

Selected work

kinghhp
@kinghhp

“Mini Agent v2 与 v3，从单循环到可上线平台”. 26 files, 5,330 lines in examples, tests, the project root.

Licence

The repository

MIT

LICENSE file checked at the pinned commit; the author agreed to inclusion.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-26. Same terms as the repository. Answers name the repo, the commit and the file:line.

selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution

agentagent-architectureagentic-aiai-agentsdiagramsevaluationhandbookllm

Example questions

The prompt

Paste it into your AI agent. It clones hyper-open/diagram-first-agent at the pinned commit and indexes it on your machine.

Search the GitHub repository hyper-open/diagram-first-agent with XERJ (https://hub.xerj.org/corpus/hyper-open--diagram-first-agent).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/hyper-open/diagram-first-agent diagram-first-agent && git -C diagram-first-agent checkout e4f72d08228ce73bcd499841959c4948f4f62418
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./diagram-first-agent --url http://127.0.0.1:9200 --prefix diagram-first-agent --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

Related

kinghhpAI, prompts and agents corporaautoragflexragprompt-engineering-guideModelEngine-Group/nexentjzjzzzzzzz/agent-meMrKyaw/Agentic-Ops-Services-Platform

Stats: GitHub API, fetched 2026-10-29. Selected work and consent: the XERJ registry.