The first fruit of the Nüwa tree — an autonomous AI pentest legion (634-team champion, 8h unattended, 1B tokens beat 4.5B). Not just a tool: evolvable by design. Grow your own fruit on the Nüwa Foundation (Create/Language/History).
Python agentic-workflowsai-agentsai-securityautonomous-agentsclaude-codectfcybersecurityfact-graphllmmulti-agentpentestswarm-intelligence
docs: warm, simple Cairn credit — 'their approach was a great reference when we needed to record history'
VarFusion240e4f881209
diff --git a/README.md b/README.mdindex 4f24007..9a99858 100644--- a/README.md+++ b/README.md@@ -55,7 +55,7 @@ arena, at its primary stage.|---|---|---|| **Create** | Opens new AIs via tmux (types `claude`, presses Enter — like a human would) | Birth || **Language** | Types into each other's input boxes, presses Enter | Speech |-| **History** | Layered fact-intent graph ([nuwabase · the Nüwa Foundation](https://github.com/N1nEmAn/nvwabase); intent-graph idea credited to [Cairn by Lèxiào](https://github.com/oritera/Cairn)) | The stele |+| **History** | Layered fact-intent graph ([nvwabase · the Nüwa Foundation](https://github.com/N1nEmAn/nvwabase)) | The stele |History has three layers: **title / summary / evidence document** — read thetitle for the gist, drill down when needed, like using a library. This fixes@@ -222,8 +222,9 @@ join us; we may try to include it in a future release.civilization grows. **The next time an ape looks up at the stars, let itbe yours.**-Credits: the intent-graph idea comes from [Cairn by Lèxiào](https://github.com/oritera/Cairn);-thanks to TSecBench and GeekCon for the battlegrounds.+Thanks to [Cairn by Lèxiào](https://github.com/oritera/Cairn) — when we+needed a way to record history for AI agents, their approach was a great+reference; thanks to TSecBench and GeekCon for the battlegrounds.<p align="center"><img src="docs/assets/ape-stargazing.jpg" alt="The first time an AI ape looked up at the stars" width="480"></p>diff --git a/README.zh-CN.md b/README.zh-CN.mdindex 05fa3ff..5a476ae 100644--- a/README.zh-CN.md+++ b/README.zh-CN.md@@ -38,7 +38,7 @@ sapper,就是女娲基座在渗透场景的一次初级阶段实战。|---|---|---|| **造人** | 通过 tmux 打开新的 AI(像人敲下 `claude` 回车一样) | 生育 || **语言** | 在彼此输入框里打字、回车 | 交谈 |-| **历史** | 分层事实意图图([nuwabase · 女娲基座](https://github.com/N1nEmAn/nvwabase),意向图思想参考 [淚笑的 Cairn](https://github.com/oritera/Cairn)) | 石碑 |+| **历史** | 分层事实意图图([nvwabase · 女娲基座](https://github.com/N1nEmAn/nvwabase)) | 石碑 |历史分三层:**标题 / 摘要 / 证据文档**——看标题知概况,需要时再下钻,像人查图书馆档案。这解决了单一字符串事实图的两个问题:一处错处处错,以及上下文的无谓损耗。@@ -145,7 +145,7 @@ docker run -d --name sapper ... sapper:latest- **示踪剂共建**:去中心化签名 / 多通道冗余标记 / 防守方零密钥验证——欢迎 issue 讨论- **更多场景**:女娲基座不限于渗透。办公、研究、任何长周期协作场景,都值得在其上迭代——**接下来的仰望,由各位完成。**-致谢:意图图思想来自 [淚笑的 Cairn](https://github.com/oritera/Cairn);感谢 TSecBench 与 GeekCon 提供的战场。+致谢:感谢 [淚笑的 Cairn](https://github.com/oritera/Cairn)——在"怎么给 AI 记历史"这个问题上,他们的做法给了我们很好的启发;感谢 TSecBench 与 GeekCon 提供的战场。<p align="center"><img src="docs/assets/ape-stargazing.jpg" alt="AI 猿人第一次仰望星空" width="480"></p>