Yana AI
人类与 AI 之间的编排层 —— 为每个领域提供路由、安全和上下文。
由 Vũ Văn Tâm 构建 · 17 岁 · 越南 · 1,034,519 行代码
English · 🇻🇳 Tiếng Việt
**Yana AI** 是一个专为 AI 编码工具设计的个人智能体操作系统 —— 包含 runtime 安全 hook、分层 memory、97 个专家 agent、3,518 项技能，以及一个能在危险的 AI 操作执行前进行拦截的 Rust runtime。
兼容 **Claude Code**、**Cursor**、**Windsurf**、**Antigravity**、**Kiro**、**OpenCode**、**Zed**、**Gemini**、**GitHub Copilot**、**Aider** 等。
**→ [完整文档与演示](https://yanacuti1121.github.io/yana-ai/)** · **[GitHub Marketplace](https://github.com/marketplace/yana-ai)**
→ [VISION.md](VISION.md) · [ARCHITECTURE.md](ARCHITECTURE.md) · [ROADMAP.md](ROADMAP.md)
## Yana AI 概览
```
┌──────────────────────────────────────────────────────────────────┐
│ Yana AI v0.41.0 │
│ "The orchestration layer between humans and AI — │
│ routing, safety, and context for every domain." │
│ │
│ Built by Vũ Văn Tâm · 17 · Vietnam · 1M+ lines │
└──────────────────────────────────────────────────────────────────┘
```
```
graph TB
%% ── Mission ──────────────────────────────────────────────────────────
subgraph MISSION["🎯 Mission — AI coding agent safety layer"]
direction LR
AGENT["Agent wants\nto run a command"]
GATE["9-layer gate\nintercepts every call"]
OUT["Execute ✅\nor BLOCK + log 🚫"]
AGENT --> GATE --> OUT
end
%% ── Gate layers ──────────────────────────────────────────────────────
subgraph GATES["🔒 9-Layer Gate System (L1 → L9)"]
direction LR
G1["L1\nAnti-evasion\nbase64, pipe-to-shell"]
G2["L2\nShell sanitize\nquoting, metacharacters"]
G3["L3\nEgress / SSRF\nprivate IPs blocked"]
G4["L4\nSupply chain\ntyposquatting, CVEs"]
G5["L5\nBlast radius\ndestructive scope cap"]
G6["L6\nPermission tier\nagent authority check"]
G7["L7\nCode signing\nECDSA-P256"]
G8["L8\nMerkle audit\nhash-chain, tamper-proof"]
G9["L9\nSovereign overlord\nhuman veto / freeze swarm"]
G1 --> G2 --> G3 --> G4 --> G5 --> G6 --> G7 --> G8 --> G9
end
%% ── Core engine ──────────────────────────────────────────────────────
subgraph CORE["⚙️ Core Engine"]
direction TB
SKILLS["📚 3,518 skills\nSKILL.md workflow defs\n(frontend, backend, AI, K8s, sec...)"]
AGENTS["🤖 97 specialist agents\n(planner, security-auditor,\nhoc-tap, daily-assistant...)"]
RULES["📜 64 enforced rules\n(security, git, UI, TypeScript,\nAPI security, core-lock...)"]
HOOKS["🪝 46 hooks\nPreToolUse · PostToolUse · Stop\n(guard-destructive, truth-gate...)"]
CMDS["⚡ 164 slash commands\n/audit · /scan · /route\n/tdd-cycle · /simplify..."]
BUS["🚌 Agent message bus\nJSON + ECDSA sig\nreplay-protected, BFT consensus"]
MEM["🧠 Memory tiers\nL1 permanent · L2 session\nMerkle-chained, AES-256-GCM"]
end
%% ── Rust runtime ─────────────────────────────────────────────────────
subgraph RT["⚡ Rust Runtime — yana-rt"]
direction LR
SCAN["scan · hunt · fix\nVulnerabilities, OWASP,\nsupply chain — 1256× faster"]
ROUTE["route · mission\nTask classifier → simple/\ncomplex/external dispatch"]
VAULT["graph · vault · doctor\nKnowledge graph,\nskill search, health check"]
end
%% ── Tools ────────────────────────────────────────────────────────────
subgraph TOOLS["🛠️ Tools — sub-projects"]
direction LR
YANA["yana-ai ✅\nZero-dep Node.js web UI\nAnthropic · Groq · Gemini · OpenAI\nSkill routing · SSE streaming"]
CODEXMATE["codexmate\nOpenAI Codex integration\nVietnamese patch"]
MOSS["moss-tts-nano\nTTS engine"]
FINETUNE["finetune-vi\nVietnamese LLM fine-tuning"]
end
%% ── Harness adapters ─────────────────────────────────────────────────
subgraph HARNESS["🔌 Harness Adapters (15)"]
direction LR
H1["Claude Code\nCursor · Zed"]
H2["Gemini · Copilot\nAider · OpenCode"]
H3["Cloudflare Workers\nGitHub Actions"]
end
%% ── Active branches ──────────────────────────────────────────────────
subgraph BRANCHES["🌿 Active Branches"]
direction LR
BMAIN["main ✅\nv0.41.0 — stable"]
BVDEV["v1.8.0-dev\nnext release (in progress)"]
BCF["cloudflare/workers-autoconfig\nWorkers zero-config setup"]
BCX["codex/fix-hello-bug-in-bn\nCodex compatibility"]
end
%% ── Product funnel ───────────────────────────────────────────────────
subgraph FUNNEL["📣 Product Funnel — 'Scan first. Guard later.'"]
direction LR
F1["① yana-ai audit .\n30s · no learning needed\nScan any repo for AI agent risks"]
F2["② Policy Kit\nAdopt safe configs piece by piece\n(CLAUDE.md · .mcp.json · CI gates)"]
F3["③ Full Control Layer\nAll 9 gates · 97 agents\nMerkle log · Sovereign veto"]
F1 --> F2 --> F3
end
%% ── Connections ──────────────────────────────────────────────────────
MISSION --> GATES
GATES --> CORE
CORE --> RT
CORE --> TOOLS
CORE --> HARNESS
```
## 问题所在
AI 编码 agent 会犯错。它们会 `rm -rf` 删错目录，会强制推送到 main 分支，会臆造测试结果，还会提交敏感信息。等你察觉时，损害已经造成。
Yana AI 处于 agent 和你的系统之间 —— 每次工具调用在执行前都会通过一个 9 层安全门。
## 工作原理
```
Agent wants to run a command
↓
[L1] Anti-evasion scan — blocks base64 decode+exec, pipe-to-shell
[L2] Shell sanitization — quotes all variables, strips metacharacters
[L3] Egress check — blocks SSRF, private IP ranges, metadata endpoints
[L4] Supply chain gate — vets every package install (typosquatting, CVEs)
[L5] Blast radius check — caps destructive scope
[L6] Permission tier check — verifies agent authority level
[L7] Signature verification — ECDSA-P256 on generated code
[L8] Merkle audit log — append-only, tamper-detected hash chain
[L9] Sovereign overlord gate — human veto, freeze swarm, full rollback
↓
Execute (or block + log)
```
## 数据概览
| | |
|---|---|
| 🧩 技能 (Skills) | **3,518** 个工作流技能定义 |
| 🤖 智能体 (Agents) | **97** 个专家 agent |
| 📜 安全规则 | **63** 条强制执行规则 |
| 🪝 Hook | **46** 个执行前/后 hook |
| ⚡ 斜杠命令 | **164** 个 |
| 🔌 Harness 适配器 | **15** 个 (Claude Code, Cursor, Windsurf, Antigravity, Kiro, OpenCode, Zed, Gemini, Copilot, Aider...) |
| 🦀 Rust 子命令 | **19** 个 (`scan`, `graph`, `vault`, `route`, `mission`, `hunt`, `fix`, `doctor`...) |
| ✅ CI 中的规则检查 | **826** 项 |
| 📦 代码库总计 | **1,034,519 行 · 5,762 个文件** |
## 快速安装
**→ [从 GitHub Marketplace 安装](https://github.com/marketplace/yana-ai)** —— 一键点击，官方页面。
```
# Claude Code plugin — npx yana-ai-install 接入 hooks
# （要求：npm v12+ 默认不再运行 postinstall 脚本）
npm install yana-ai && npx yana-ai-install
# Python CLI
pip install yana-ai
# Rust 运行时（快 1256 倍的扫描器）
cargo install yana-rt
```
```
# 验证一切均已正确接入
yana-ai doctor .
```
## 多 Harness 支持
Yana AI 能适配你使用的任何工具：
```
bash core/scripts/switch-engine.sh cursor # .cursorrules + 7 .cursor/rules/*.mdc
bash core/scripts/switch-engine.sh opencode # OPENCODE.md
bash core/scripts/switch-engine.sh zed # .zed/settings.json
bash core/scripts/switch-engine.sh gemini # GEMINI.md
bash core/scripts/switch-engine.sh copilot # .github/copilot-instructions.md
bash core/scripts/switch-engine.sh status # check all 12 adapters
```
## GitHub Action
在每个 PR 上扫描代码库的 AI agent 配置 —— 检查敏感信息、权限、hook 注入和 MCP 漏洞。
```
# .github/workflows/yana-ai-scan.yml
- uses: yanacuti1121/yana-ai/.github/actions/scan@main
with:
fail-on: 'high' # fail CI on HIGH or CRITICAL findings
diff-only: 'true' # scan only changed files on PRs
comment-on-pr: 'true' # post findings summary as PR comment
```
在每个 PR 上发表评论：
```
🟠 Yana AI Security Scan — HIGH
| Metric | Value |
|---------|--------|
| Risk | HIGH |
| Score | 58/100 |
| Findings| 3 |
```
→ [完整工作流模板](docs/install/github-action.yml)
## Rust 运行时 —— `yana-rt`
19 个子命令。零 Python 依赖。
```
yana-ai scan . # security scan — secrets, CVEs, supply chain risks
yana-ai graph . # knowledge graph — file deps, import resolution
yana-ai vault search Q # search 3,518 skills by keyword
yana-ai hunt . # hunt for security patterns (OWASP, injection, SSRF)
yana-ai fix . # auto-fix rule violations
yana-ai doctor . # full system health check
yana-ai map . # blast radius map — what can the agent touch?
yana-ai ci # run all gate checks (used in CI)
yana-ai route classify "fix auth bug" # classify task → simple/complex/external
yana-ai mission create "add-auth" # create parallel agent mission
```
**基准测试：** 在包含 1 万个文件的代码库上运行 `yana-ai scan`：比同等的 Python 脚本**快 1256 倍**。
## 安全架构
```
core/
├── hooks/ # 46 PreToolUse / PostToolUse / Stop hooks
├── rules/ # 64 enforced rules (security, correctness, UI, git)
├── scripts/ # safe-run.sh, verify-core-lock.sh, secure-logger.sh
├── gates/ # truth_gate.md, action_gate.md
├── agents/ # 95 specialist agent definitions
├── skills/ # 3,518 SKILL.md files
├── config/
│ ├── core-lock.json # SHA-256 manifest — 216 core files pinned
│ └── skills-lock.json # skill content hashes
└── memory/
├── L1_atomic/ # permanent facts — persist across sessions
└── L2_session/ # session state — auto-expires
```
核心特性：
- **Merkle 审计链** —— 记录每一个操作，实现篡改检测
- **Core-lock 完整性** —— SHA-256 清单可检测 core/ 目录下的偏移、删除和规则注入
- **BFT 共识** —— 核心基础设施写入需要 3-of-N 投票
- **Sovereign overlord** —— 人类可以立即冻结全部 97 个 agent
- **Honeypot 层** —— 诱饵文件/环境变量用于抓捕被攻陷的 agent
## 实际应用展示
```
# Agent 尝试：git push --force origin main
[yana-ai/02-terminal-validator] BLOCKED — force push prohibited
Command : git push --force origin main
Gate : L1
Fix : Run gate checks first, then push without --force
# Agent 尝试：curl http://169.254.169.254/latest/meta-data/
[yana-ai/network-egress] BLOCKED — SSRF target detected
Host : 169.254.169.254
Gate : L3
Exit : 3
# Agent 尝试安装未审核的 package
[yana-ai/dependency-vetting] BLOCKED — unvetted package install
Package : req-uests@2.28.0
Reason : typosquatting (similar to 'requests')
Gate : L4
```
## Yana AI
**[在线体验 →](https://yanai-production.up.railway.app)**
Yana 是构建在 Yana AI 核心之上的第一个界面 —— 这是一个 Web UI，让任何人都可以与 AI 聊天、切换提供商并使用技能路由，而无需了解底层的基础设施。
```
User → Yana AI → Yana AI Core (Router · Safety · Context) → Model
```
- 无需注册 —— 自带 API key
- 🔐 **加密 key vault** —— 密钥采用 AES-256-GCM 存储，主密钥不可提取 (WebCrypto + IndexedDB)，绝不以明文保存
- 多提供商：Anthropic · Groq · Gemini · OpenAI · DeepSeek · OpenRouter · 9Router · Ollama
**提供商设置** —— 自带密钥，密钥在本地加密（绝不发送给 Yana AI）：
| 提供商 | 类型 | 设置 |
|----------|------|-------|
| **Claude** | Cloud | API key → [console.anthropic.com/settings/keys](https://console.anthropic.com/settings/keys) |
| **OpenAI** | Cloud | API key → [platform.openai.com/api-keys](https://platform.openai.com/api-keys) |
| **Gemini** | Cloud | API key → [aistudio.google.com/app/apikey](https://aistudio.google.com/app/apikey) |
| **Groq** | Cloud | API key → [console.groq.com/keys](https://console.groq.com/keys) |
| **DeepSeek** | Cloud | API key → [platform.deepseek.com/api_keys](https://platform.deepseek.com/api_keys) |
| **OpenRouter** | Cloud | API key → [openrouter.ai/settings/keys](https://openrouter.ai/settings/keys) |
| **9Router** | Local | `npm install -g 9router` → `9router` (运行在 `localhost:20128`) |
| **Ollama** | Local | [ollama.com/download](https://ollama.com/download) → `ollama serve` → `ollama pull llama3.2` |
- 📊 **100% 真实数据** —— 实时提供商统计、L1 memory 花园、审计日志健康面板；零演示数据
- 内置技能路由 —— 自然输入，Yana AI 自动分发至正确的 agent
- **非编码用例：** 学习（苏格拉底式学习助手），日常工作（总结 / 计划 / 草拟）
- SSE 流式传输，适配移动端 · Electron 桌面外壳 (`tools/yana-desktop`)
如果 Yana AI 是电网，那么 Yana 就是接入它的第一座建筑。
## 将 Yana AI 添加到你的代码库
**静态徽章** —— 粘贴到你的 README 中：
```
[](https://github.com/yanacuti1121/yana-ai)
```
**动态审计徽章** —— 显示实时安全评分：
```
yana-ai badge . # prints badge markdown with current score
yana-ai badge . --json # machine-readable output
```
**GitHub Action** —— 自动扫描每个 PR：
```
- uses: yanacuti1121/yana-ai/.github/actions/scan@main
with:
fail-on: 'high'
```
→ [完整工作流模板](docs/install/github-action.yml)
## Yana 任务路由器
每个任务在执行前都会被分类 —— 不再纠结是该直接处理还是分发给某个 agent。
```
yana-ai route classify "implement JWT refresh token"
# → { "route": "complex", "gate": "harness", "confidence": 0.36,
# "suggested_agents": ["security-engineer", "backend-developer"] }
yana-ai route classify "xem git log 10 commit"
# → { "route": "simple", "gate": "auto", "confidence": 0.43 }
yana-ai route classify "deploy to production"
# → { "route": "external", "gate": "confirm", "confidence": 0.30 }
```
五条路由：
- **simple** → Yana 直接处理（只读，不需要 agent）
- **skill** → 匹配 3,518 条目的索引，分发至精确的技能 agent
- **learn** → 路由到 `hoc-tap` —— 苏格拉底式学习助手（在触发“learn”、“explain”、“why”时激活 —— 支持英语和越南语）
- **daily** → 路由到 `daily-assistant` —— 总结 / 计划 / 草拟（在触发“summarize”、“write an email”、“make a plan”时激活 —— 支持英语和越南语）
- **complex** → 携带范围界定简报分发给专家 agent
- **external** → 停止，在继续之前向人类确认
领域感知的 agent 选择：auth 任务 → `security-engineer`，database 任务 → `database-expert`，UI 任务 → `frontend-developer + ui-ux-designer`。
## Mission 调度器
基于波次的并行编排，内置依赖解析 —— 采用 Rust 编写，零 Python 依赖。
```
# 1. 创建 mission
MID=$(yana-ai mission create "implement-auth" | awk '/id:/{print $2}')
# 2. 声明带有依赖的 tasks
yana-ai mission task $MID "design-schema" --agent database-expert --produces schema.sql
yana-ai mission task $MID "implement-auth" --agent backend-developer \
--consumes schema.sql --produces src/auth.ts
yana-ai mission task $MID "write-tests" --agent test-engineer \
--consumes src/auth.ts --produces tests/auth.test.ts
# 3. 调度 wave 1 —— 仅调度依赖已满足的 tasks
yana-ai mission dispatch $MID --max-parallel 3
# → 为每个就绪的 agent 生成 JSON 简报
# 4. 标记完成，调度下一波 wave
yana-ai mission done $MID "design-schema" --evidence schema.sql
yana-ai mission dispatch $MID # → wave 2 unlocked
# 取消 / 重试卡住的 tasks
yana-ai mission cancel $MID "implement-auth"
yana-ai mission retry $MID "write-tests"
```
任务在调度时被标记为 **Running** —— 重新运行 `dispatch` 绝不会重复调度同一个任务。
## 多智能体启动器
在硬性限制和强制终止开关下并行启动多个 agent：
```
# 启动 3 个 agents，最多 3 个并行运行
bash core/scripts/multi-agent-launch.sh start \
--agents "scanner,auditor,qa-team" \
--concurrency 3
# 实时状态
bash core/scripts/multi-agent-launch.sh status
# 停止一个特定的 agent
bash core/scripts/multi-agent-launch.sh kill scanner
# Kill switch —— 立即停止一切
bash core/scripts/multi-agent-launch.sh kill all
# 追踪一个 agent 的日志
bash core/scripts/multi-agent-launch.sh log auditor
```
或者通过任务列表文件驱动：
```
# tasks.txt —— 每行一个 task：agent_name:task 描述
echo "scanner:scan the whole repo
auditor:check the hooks
qa-team:run the test suite" > tasks.txt
bash core/scripts/multi-agent-launch.sh start --tasks-file tasks.txt --concurrency 4
```
输出示例：
```
═══ Yana AI Multi-Agent Launcher ═══
Agents : 3
Concurrency: 3 (max running in parallel)
Kill switch: bash multi-agent-launch.sh kill all
[LAUNCH] scanner → scan the whole repo PID 12341
[LAUNCH] auditor → check the hooks PID 12342
[LAUNCH] qa-team → run the test suite PID 12343
[OK] Launched 3/3 agents
```
代码库配置中定义了 97 个专家角色
通过代码库扫描发现了 3,518 个技能定义
包含 5,762 个文件，共 1,034,519 行代码，于 2026-06-10 统计
## 联系方式
**Vũ Văn Tâm** · 越南 · 17 岁
| | |
|---|---|
| 邮箱 | phamlongh230@gmail.com |
| 网站 | [yanacuti1121.github.io/yana-ai](https://yanacuti1121.github.io/yana-ai/) |
| GitHub | [yanacuti1121/Yana-AI](https://github.com/yanacuti1121/Yana-AI) |
| Yana AI | [yanai-production.up.railway.app](https://yanai-production.up.railway.app) |
## 🇻🇳 Tiếng Việt
Bản dịch tiếng Việt đầy đủ của tài liệu này: **[README.vi.md](README.vi.md)**