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: prominent nvwabase 'take the foundation' section — free for anyone, any agent, any scenario, with quick-start commands
VarFusionb2342195d0ab
diff --git a/README.md b/README.mdindex 1275432..12c8457 100644--- a/README.md+++ b/README.md@@ -70,6 +70,34 @@ still belongs to humans.than us. Piling rules on an AI is a leash; acknowledging its intelligence andgiving it the foundation of a civilization is how it reaches its potential.+### 🏗️ Take the Foundation: nvwabase++The History pillar is independently open-sourced as+**[nvwabase · the Nüwa Foundation](https://github.com/N1nEmAn/nvwabase)** —+**free for anyone, any scenario, any agent**. Not limited to pentest, not+limited to sapper, not limited to Claude Code. Offices, research, engineering,+any long-horizon multi-agent work — iterate your own civilization on it.++```bash+git clone https://github.com/N1nEmAn/nvwabase+cd nvwabase && bash install.sh # pure Python stdlib, zero deps+nvwabase setup --goal "your long-horizon goal" --agents+nvwabase status # board & ready-to-work frontier+```++Three core commands turn any agent into a member of a civilization:+- **`nvwabase fact "confirmed observation"`** — external memory: AI sessions+ die, the graph survives, successors read the graph and take over+- **`nvwabase intent --from f001 "what to do"`** — units of work: new intents+ proposed from existing facts+- **`nvwabase dispatch reason`** — commander proposes / executor works /+ verifier checks; every conclusion is written back to the graph++Any agent that can run shell commands (Claude Code / Codex / Gemini /+custom scripts) can read and write the same graph via the `nvwabase` CLI —+**the foundation doesn't pick agents; agents don't pick scenarios.** See the+[nvwabase README](https://github.com/N1nEmAn/nvwabase).+## 3. From Foundation to Legion: 18 VersionsIterated 18 versions on Tencent's v1bench training ground:diff --git a/README.zh-CN.md b/README.zh-CN.mdindex 0f3a337..3226dac 100644--- a/README.zh-CN.md+++ b/README.zh-CN.md@@ -46,6 +46,24 @@ sapper,就是女娲基座在渗透场景的一次初级阶段实战。**为什么不给它更多规则?** 因为大模型已经比人聪明得多。给 AI 定满规则反而是束缚;承认它的智力,给它文明的地基,才能发挥它最大的潜力。+### 🏗️ 把基座拿去用:nvwabase++这个"历史"支柱已独立开源为 **[nvwabase · 女娲基座](https://github.com/N1nEmAn/nvwabase)**——**任何人、任何场景、任何 agent 都可以免费拿去用**,不限于渗透测试、不限于 sapper、不限于 Claude Code。办公协作、研究实验、工程项目、任何长周期多智能体工作,都可以在其上迭代出你自己的分工与文明。++```bash+git clone https://github.com/N1nEmAn/nvwabase+cd nvwabase && bash install.sh # 纯 Python 标准库,零依赖+nvwabase setup --goal "你的长周期目标" --agents+nvwabase status # 看板与可干前沿+```++三个核心命令把任何 agent 变成文明的成员:+- **`nvwabase fact "确认的观察"`**——外部记忆:AI 个体死了,图还在,继任者读图接岗+- **`nvwabase intent --from f001 "想干什么"`**——工作单元:基于既有事实提出新意图+- **`nvwabase dispatch reason`**——指挥官提议 / 执行者干活 / 验证者复核,结论全部回写图++任何能执行 shell 命令的 agent(Claude Code / Codex / Gemini / 自研脚本)都可以直接调用 `nvwabase` CLI 读写同一张图——**基座不挑 agent,agent 不挑场景**。详见 [nvwabase README](https://github.com/N1nEmAn/nvwabase)。+## 三、从基座到军团:18 个版本在腾讯 v1bench 训练场上迭代 18 版,路径大致是: