Skip to main content
Glama

Pandaone

🧑‍💼 Pandaone is your codebase's personal manager. / Pandaone 是你代码库的专属经理。

Every AI agent is an employee working in your company — your codebase. Without a personal manager, employees do what they want — edit files, push commits, break production — and you have no idea what they did, when, or why.

Pandaone is the personal manager you hired to protect your code. Every AI agent — Claude, Cursor, Trae, or any tool you adopt tomorrow — must report to Pandaone first. Nothing gets written, nothing gets committed, nothing gets deployed until Pandaone approves it with a signed, auditable receipt:

┌─────────────────────────────────────────────┐
│ [APPROVED]                  2026-09-11 03:47 │
│ File:      src/payment.py                    │
│ Agent:     Claude Code (employee #3)         │
│ Reason:    "Fix rounding"                    │
│ Problem:   "Charge $50,001 on $50,000 bill"  │
│ Approach:  "Round before transfer, not after"│
│ Commit:    a3f7b2c                           │
└─────────────────────────────────────────────┘

Without a personal manager, your agents move money — er, code — without receipts:

Without Pandaone          With Pandaone
──────────────          ──────────────
$50,000 ???            $50,000  src/payment.py
                        Reason:  "Fix rounding"
                        By:      Claude Code
                        When:    2026-09-11 03:47
                        Commit:  a3f7b2c

The left column is how most AI-agent-driven codebases look today. The right column is how yours will look with one command:

pip install pandaone-guard

Your personal manager is on duty 24/7 — before, during, and after every code change. Every AI agent — Claude, Cursor, Trae — operates under one auditable protocol. No exceptions. No bypass.

AI Agent 代码审计门禁 — 让每一次代码改动都留下合规、可追溯的证据链。

PyPI version Downloads Downloads/month Python License Tests Bugs i18n Lint & i18n CI OS Phase CI Lint M8ven Score

English | 中文


Related MCP server: gitmem

中文 / Chinese

是什么? / What is it?

Pandaone 是一个 7 层防御体系,强制 AI Agent(或任何开发者)写代码前必须经过审计: 任何受保护文件的修改都必须通过 pandaone write 命令,留下 reason / problem / approach 三段式审计记录。

适用场景 / Use Cases:

  • 🤖 AI Agent 开发:防止 Agent 绕过审查直接改代码

  • 🏢 企业合规:满足 SOC2 / ISO 27001 等代码变更审计要求

  • 👥 团队协作:所有 PR 必须有审计记录才能合入

核心特性 / Core Features

  • 17 种文本格式 + 24 种二进制格式保护(.py / .md / .json / .yml / .env / .png / .pdf / ...)

  • 7 层防御体系 / 7-Layer Defense System (see Defense Layers)

  • MCP Server 原生支持 — Claude / Cursor / Trae 等 AI IDE 直连

  • 13 种审计日志导出格式(Excel / Word / PDF / SQLite / ...)

  • 纯 Python — Windows / macOS / Linux 通吃,无 C 扩展

  • 右键菜单集成 — 一行命令在 3 大平台安装原生右键菜单(HKCU / Quick Action / Nautilus + Dolphin)

  • i18n 国际化 — zh-CN / en 双语 CLI 自动检测 + --lang 强制 + 持久化偏好

快速开始 / Quick Start

安装 / Installation

方式 A:从 PyPI 安装(最简单)

pip install pandaone-guard

# 一键装上右键菜单(Windows / macOS / Linux 自动检测)
pandaone install-context

方式 B:从源码一键安装(推荐开发者使用,含最新 i18n + CI lint)

git clone https://github.com/hellob1889/Pandaone-AI-Agent.git
cd pandaone

# Windows
powershell -ExecutionPolicy Bypass -File scripts/install.ps1

# macOS / Linux
./scripts/install.sh

方式 C:Windows 一键安装包(推荐 Windows 用户)

下载 PandaoneSetup-<版本>-x64.exe(GitHub Releases),双击安装即可 —— 免管理员权限(装到 %LOCALAPPDATA%\Pandaone),自动完成:

  • 安装 pandaone.exe / pandaone_guard.exe / pandaone-mcp.exe

  • 加入用户 PATH(写 HKCU,不需要管理员)

  • 安装 Windows 右键菜单(文件 / 目录 / 空白处,级联 Init / Lock / Status / Unlock)

  • 可选勾选:把 MCP server 注册进 Claude Desktop / Cursor / Trae

装完直接用:

pandaone setup      # 一键本地部署(git + 仓库 + 审计 + 看门狗 + 右键菜单 + 仪表盘)
pandaone doctor     # 环境体检

安装脚本自动做 / Install script auto-handles:

  1. 检测 Python ≥ 3.10

  2. 探测 git(不在 PATH 时尝试常见安装路径)

  3. 卸载 site-packages 里可能存在的老 pandaone 版本(避免版本冲突)

  4. pip install -e . 本地源码 editable 安装

  5. 验证 pandaone 可用(python -m pandaone --version)

  6. 调用 doctor.py --fix --persist-path 自动修复剩余问题(依赖、setuptools、指纹、PATH 持久化到 HKCU)

  7. 注册 MCP server 到检测到的 IDE 配置(Claude Desktop / Cursor / Trae),写前备份、只合并不覆盖;加 --skip-mcp 可跳过

30 秒上手(第一次用请先看这里)/ 30-Second Start

⚠️ 包名提醒:本包在 PyPI 上的名字是 pandaone-guard。 旧名 pandax-guard 已弃用(停在 0.7.4,不再更新,也不再修 bug)——如果你之前装过它,请先卸载: pip uninstall pandax-guard && pip install pandaone-guard

# 1) 装(10 秒)
pip install pandaone-guard

# 2) 在你的项目里初始化(1 秒)——会生成 .pandaone/ 审计目录
cd your-project && pandaone init --root .

# 3) 把 MCP 接到你的 AI IDE(Claude / Cursor / Trae / ChatGPT 都行)

MCP 配置(/ claude_desktop_config.json、Cursor MCP 配置):

{ "mcpServers": { "pandaone": { "command": "pandaone-mcp" } } }

然后直接对 AI 说一句话就够了:

把 main.py 里的 hi 改成 hello,说明你为什么改。

AI 会被迫走审计通道(pandaone_write):必须填「原因 / 解决什么问题 / 采用什么方法」三件套。合规的改动才被写入 + 自动 git commit + 留痕;不合规的改动被拒绝,同样留痕。

pandaone log --root .      # 查看审计记录(谁改了什么、为什么)
pandaone status --root .   # 查看当前保护状态与 watchdog
pandaone log --root . --export report.html   # 导出 HTML 报告

想先手动挡住 AI 的写操作?pandaone lock --root . 把受保护文件设为只读(OS 级,绕过不了);pandaone unlock --root . 还原。注意:请以普通用户运行,root 下 OS 权限位对其无效。

环境诊断(任何时候都能跑)/ Environment Diagnostics (run anytime)

python scripts/doctor.py                 # 人类可读
python scripts/doctor.py --json          # CI 用(返回 pass/fail)
python scripts/doctor.py --quiet         # 只显示 WARN / FAIL
python scripts/doctor.py --fix           # 自动修复 13 类问题(仅当前会话生效)
python scripts/doctor.py --fix --persist-path   # 持久化 PATH 到 HKCU(重启 shell 生效)
python scripts/doctor.py --fix-only      # 只跑修复 + 重测,跳过详细诊断

检测 9 个项目 + 自动修复 13 类问题(pip / git / pandaone 装在 site-packages / pandaone.exe PATH / 指纹污染 / setuptools / 5 个运行时依赖)。

--fix --persist-path 会做什么:

  • 卸载 site-packages 老版本 → 重装本地源码

  • 删除污染的 ~/.pandaone_fp.txt

  • 自动 pip install 缺失的运行时依赖

  • Windows:用 setx PATH "%PATH%;<Scripts>" 持久化到 HKCU\Environment\Path(新开的 PowerShell 自动看到)

  • macOS / Linux:追加 export PATH="..." 到 ~/.bashrc / ~/.zshrc

初始化项目 / Initialize Project

cd /path/to/your-project
pandaone init --root .
# 自动:
#   - 创建 .pandaone/ 目录
#   - 生成 config.json(17 文本 + 24 二进制扩展名)
#   - 创建 binary_snapshots.json(SHA256 字典)
#   - 初始化 .gitignore 排除

写代码(合规路径)/ Write Code (Compliant Path)

# 修改 Python 文件
pandaone write \
    --file src/main.py \
    --reason "修复 user_id 类型注解" \
    --problem "原代码用 int,实际可能是 None" \
    --approach "改为 Optional[int]" \
    --old 'def get_user(user_id: int):' \
    --new 'def get_user(user_id: Optional[int]):'

# 替换二进制文件(图片/文档/PDF 等)
pandaone write \
    --file assets/logo.png \
    --reason "更新品牌 logo" \
    --problem "旧 logo 与新品牌色不匹配" \
    --approach "用新版 logo 替换" \
    --from-file /tmp/new_logo.png

查看审计日志 / View Audit Log

# 命令行查看
pandaone log --last 10

# 导出为 Excel
pandaone log --format xlsx --output audit_report.xlsx

# 导出为 PDF(含中文支持)
pandaone log --format pdf --output audit_report.pdf

# 全部 13 种格式:text / csv / tsv / json / yaml / md / html / xlsx / docx / pdf / sqlite / rst / asciidoc

项目状态仪表盘 / Project Status Dashboard

pandaone status --root .

显示 / Displays:项目路径、配置摘要、L1 锁定状态、二进制快照、最近审计、版本指纹等。 Project path, configuration summary, L1 lock state, binary snapshots, recent audits, version fingerprints, etc.

🆕 Web 实时仪表盘 / Web Real-time Dashboard:

pandaone serve   # 浏览器打开 http://localhost:8765

防御体系(7 层) / Defense Layers (7 Layers)

层 / Layer

组件 / Component

作用 / Function

被绕过后的兜底 / Fallback if Bypassed

L1

file chmod

文件级只读锁(attrib +r / chmod -w)File-level read-only lock

L2 watchdog

L2

watchdog

实时文件监控 + git checkout 回滚Real-time file monitor + git checkout rollback

L3 hook

L3

pre-commit hook

严格校验每个 staged 文件的 APPROVED 记录Strict validation of APPROVED record for every staged file

L4 / L5

L4

启动读 READMERead README on startup

CLI 启动时加载项目元数据CLI loads project metadata at startup

L5

L5

自指纹Self-fingerprint

CLI 自身 SHA256 检测篡改CLI's own SHA256 detects tampering

L6

L6

二进制 SHA256 snapshotBinary SHA256 snapshot

检测 .png/.pdf 等二进制篡改Detects tampering of .png/.pdf binaries

L7

L7

GitHub Actions CI

PR 合入前审计验证(最终兜底)Audit verification before PR merge (final fallback)

人工 reviewManual review

MCP Server(AI Agent 直连 / AI Agent Native)

// claude_desktop_config.json 或 Cursor MCP 配置
// claude_desktop_config.json or Cursor MCP configuration
{
  "mcpServers": {
    "pandaone": {
      "command": "pandaone-mcp",
      "env": {}
    }
  }
}

暴露 11 个工具:pandaone_init / pandaone_lock / pandaone_unlock / pandaone_write / pandaone_log / pandaone_status / pandaone_install_hook / pandaone_watch / pandaone_install_git / pandaone_fingerprint_update / pandaone_ci

所有 11 个工具都已声明完整的 4 个 MCP annotations(readOnlyHint / destructiveHint / idempotentHint / openWorldHint)—— OpenAI 目录合规(v0.7.14 修复)。

在 ChatGPT 中使用 / Use with ChatGPT

ChatGPT Desktop app 的 Developer Mode(开发者模式)原生支持 MCP server。把 pandaone 加进去:

步骤:

  1. 打开 ChatGPT Desktop app

  2. Settings → Beta features → 开启 Developer Mode

  3. Settings → Connectors → Create new connector

  4. 填入以下 JSON(字段名一字不差):

{
  "name": "pandaone-guard",
  "command": "pandaone-mcp",
  "args": [],
  "env": {}
}
  1. 第一次对话前,ChatGPT 会要求安装 pandaone-guard。如未自动装,在终端手动跑:

# macOS / Linux
pip3 install pandaone-guard

# Windows (PowerShell)
pip install pandaone-guard

进阶(自定义 venv / Python 路径 / 中文界面):

{
  "name": "pandaone-guard",
  "command": "/path/to/venv/bin/python",
  "args": ["-m", "pandaone_mcp"],
  "env": {
    "PANDAX_LANG": "zh"
  }
}

环境变量说明 / Environment variables:

变量

类型

默认

说明

PANDAX_FP_PASSWORD

🔐 secret

"0000"

仅 pandaone_fingerprint_update / pandaone_watch 守护进程鉴权需要;本地设置,不上传

PANDAX_LANG

config

"zh"

界面语言(zh / en)

PANDAONE_SKIP_GIT_CHECK

config

unset

设 1 跳过 git 检测(无 git 环境用)

NO_COLOR

config

unset

设 1 禁用彩色输出

只有一个 secret:PANDAX_FP_PASSWORD。本地配置,永不上传到任何远程。

真实场景测试 / Real-World Validation

完整实战验证报告:实战验证报告.md

包含 / Includes:

  • 7 层防御每层实战证据 / 7-layer defense, each layer with real-world evidence

  • L3 hook 严重 bug 的发现 + 修复

  • 隐藏文件锁定 bug 的发现 + 修复

  • 13 种导出格式实测 / 13 export formats tested

  • MCP 协议完整工作流

详细示例集 / Detailed Examples

  • EXAMPLES.md — 10 个真实工作流 + 终端输出

  • examples/ — 5 个可运行的 Python demo 脚本

  • docs/ — 中英双语文档站(mkdocs)

  • docs/index.html — 交互式 HTML 文档首页(带终端动画)

命令清单 / Command List

命令 / Command

用途 / Purpose

pandaone init

初始化项目

pandaone lock / unlock

锁定 / 解锁所有受保护文件

pandaone write

核心:审计写入(支持文本/二进制)

pandaone log

查询审计历史(13 种导出格式)

pandaone status

项目状态仪表盘

pandaone install-hook

安装 L3 pre-commit hook

pandaone watch

启动 L2 watchdog 守护进程

pandaone serve

🆕 Web 实时仪表盘(浏览器打开 localhost:8765,watchdog + SSE <100ms 推送)

pandaone install-git

自动安装 git

pandaone ci

L7 CI 验证(git diff vs audit log)

pandaone setup

🆕 一键本地部署(Python/git 检查 → PATH 持久化 → git 仓库 + baseline commit → init → 看门狗 → 右键菜单 → 仪表盘 → doctor 体检;不设 remote、不推送)

pandaone upgrade

🆕 一键升级(pip 升级 → 指纹自动刷新 → 重启看门狗 / 仪表盘 → 打印版本对比。exe 形态没有 pip:改为在 exe 同目录找新版安装包 PandaoneSetup-<版本>-x64.exe,加 --launch-installer 可直接启动)

pandaone backup

🆕 纯本地备份(--output x.bundle 生成 git bundle;--mirror DIR 建本地裸仓库镜像;不碰远程)

pandaone install-mcp

🆕 注册 MCP server(探测 Claude Desktop / Cursor / Trae / Windsurf;写前备份、只合并不覆盖、装后回读自检)

pandaone init --with-git

初始化时一并建 git 仓库并提交 baseline commit

pandaone-mcp

启动 MCP server(stdio JSON-RPC)

🆕 指纹密码(默认 0000,可以改成你自己的)

L5 自校验(防止 agent 改了 pandaone 本体来绕过审计)用的密码,默认值保持 0000(本地单用户零摩擦),但你可以随时改:

pandaone --set-fingerprint-password mysecret   # 设成自己的密码(≥4 位)
pandaone --reset-fingerprint-password           # 删掉自设密码,回落到默认 0000
pandaone --reset-fingerprint-lock               # 连续输错被锁了?解锁

优先级:PANDAONE_FP_PASSWORD 环境变量 > ~/.pandaone/fp_password 文件 > 默认 0000。密码比较走 hmac.compare_digest(常量时间,防时序侧信道),连续输错 5 次锁 15 分钟。

开发与测试 / Development & Testing

git clone https://github.com/hellob1889/Pandaone-AI-Agent
cd pandaone
pip install -e .[dev]
pytest tests/ -v

当前测试数:342 passed, 1 skipped(覆盖 i18n / write / status / lock / ci / watchdog / export / init / e2e / serve / desktop-icon / gitignore)

路线图 / Roadmap

版本 / Version

状态 / Status

关键能力 / Key Capability

v0.1.0

✅

Phase 1-3 MVP(5 层防御)

v0.2.0

✅

多格式导出(7 种)

v0.3.0

✅

17 种文本保护

v0.4.0

✅

24 种二进制 SHA256

v0.5.0

✅

MCP Server

v0.6.0

✅

GitHub Actions CI

v0.6.1

✅

L3 hook 强化(实战验证)

v0.6.2

✅

隐藏文件锁定 bug 修复

v0.7.0

✅

Phase 9 OS 右键菜单 + Phase 10 i18n(zh-CN/en)+ doctor.py 环境自检 + auto-fix 13 类 + PATH 持久化

v0.7.1

✅

28 个 bug 全修 + 4 大新功能:P0 安全(#8/#12×2/#22/#23)+ P1(#2/#5/#15/#29)+ P2(#21/#6/#20/#9-#10)+ P3(#13/#4/#26/#39)+ UX(#14/#17/#48/#25/#28)+ 工程化(#版本漂移 / #README 分组标签 / #CRLF 根因)+ 🆕 文件夹熊猫锁图标(desktop.ini + ICO)+ 🆕 Web 实时仪表盘(watchdog + SSE <100ms)+ 🆕 Git 兼容(init 自动写 .gitignore)+ 🆕 右键菜单真实可用验证,298 测试通过

v0.7.2

✅

CI 工程化修复:publish.yml Tests job 在干净 ubuntu-latest 容器 25s exit 1(setuptools pin 缺失)→ pin setuptools==80.10.2 + --no-build-isolation,新增 pytest log artifact 上传。340 测试通过

v0.7.3

✅

agent 身份 + diff 捕获 + 面板 UI:--agent 参数追踪调用方(Claude / Cursor / Trae / user:name)+ --verbose 完整 diff + 彩色面板格式(状态 / 文件 / commit / 行数 / 原因 / 问题 / 方法 / 差异)+ status 加 agent 分组统计 + HTML 导出加卡片布局 + i18n 新增 16 个键。342 测试通过

完整历史:CHANGELOG.md

许可 / License

MIT License — 详见 LICENSE


English

What is it?

Pandaone is a 7-layer defense system that forces every code change through an audit gate. Any modification to a protected file (17 text + 24 binary formats) must go through pandaone write, which records reason / problem / approach as immutable audit evidence.

Use cases

  • 🤖 AI Agent development: prevent agents from bypassing review

  • 🏢 Enterprise compliance: meet SOC2 / ISO 27001 code change audit requirements

  • 👥 Team collaboration: every PR must have audit records before merging

Install

Option A: from PyPI (easiest)

pip install pandaone-guard

Option B: from source (recommended for developers, includes latest i18n + CI lint)

git clone https://github.com/hellob1889/Pandaone-AI-Agent.git
cd pandaone

# Windows
powershell -ExecutionPolicy Bypass -File scripts/install.ps1

# macOS / Linux
./scripts/install.sh

Option C: Windows one-click installer (recommended for Windows users)

Grab PandaoneSetup-<version>-x64.exe from GitHub Releases and double-click it. No administrator rights required (installs into %LOCALAPPDATA%\Pandaone), and it automatically:

  • installs pandaone.exe / pandaone_guard.exe / pandaone-mcp.exe

  • adds them to the user PATH (HKCU — no admin needed)

  • installs the Windows right-click menu (files / folders / background, cascading Init / Lock / Status / Unlock)

  • optionally registers the MCP server into Claude Desktop / Cursor / Trae

Then:

pandaone setup      # one-click local deployment (git + repo + audit + watchdog + context menu + dashboard)
pandaone doctor     # environment check

The install script automatically:

  1. Checks Python >= 3.10

  2. Locates git (scans common install paths if not in PATH)

  3. Removes stale pandaone from site-packages (prevents version conflicts)

  4. pip install -e . local source editable install

  5. Verifies pandaone works (python -m pandaone --version)

  6. Runs doctor.py --fix --persist-path (auto-fix remaining issues: deps / setuptools / fingerprint / persist PATH to HKCU)

  7. Registers the MCP server into detected IDE configs (Claude Desktop / Cursor / Trae) — backs up first, merges without overwriting; pass --skip-mcp to opt out

30-Second Start (start here if you're new)

⚠️ Package name: on PyPI this package is pandaone-guard. The legacy name pandax-guard is deprecated (frozen at 0.7.4, no fixes). If you installed it before, switch now: pip uninstall pandax-guard && pip install pandaone-guard

# 1) Install (10s)
pip install pandaone-guard

# 2) Init inside your project (1s) — creates the .pandaone/ audit directory
cd your-project && pandaone init --root .

# 3) Wire MCP into your AI IDE (Claude / Cursor / Trae / ChatGPT)
{ "mcpServers": { "pandaone": { "command": "pandaone-mcp" } } }

Then just say one sentence to your AI:

Change hi to hello in main.py, and tell me why.

The AI is forced through the audit channel (pandaone_write): it must supply reason / problem / approach. Compliant edits are written, auto-committed and logged; non-compliant ones are rejected — and logged too.

pandaone log --root .      # who changed what, and why
pandaone status --root .   # protection status + watchdog
pandaone log --root . --export report.html   # HTML report

Want to hard-block AI writes first? pandaone lock --root . makes protected files read-only at OS level (unbypassable); pandaone unlock --root . restores them. Run as a normal user — OS permission bits do not apply to root.

Environment diagnostics (run anytime)

python scripts/doctor.py                 # human-readable
python scripts/doctor.py --json          # CI mode (returns pass/fail)
python scripts/doctor.py --quiet         # only WARN / FAIL
python scripts/doctor.py --fix           # auto-fix 13 issue classes (session only)
python scripts/doctor.py --fix --persist-path   # persist PATH to HKCU (new shell)
python scripts/doctor.py --fix-only      # just fix + re-check, skip detailed diagnosis

Checks 9 items + auto-fixes 13 issue classes (pip / git / pandaone-in-site-packages / pandaone.exe PATH / fingerprint pollution / setuptools / 5 runtime dependencies).

What --fix --persist-path does:

  • Uninstall stale site-packages version, reinstall local source

  • Remove polluted ~/.pandaone_fp.txt

  • Auto pip install for missing runtime deps

  • Windows: use setx PATH "%PATH%;<Scripts>" to persist to HKCU\Environment\Path (new PowerShell shells see it automatically)

  • macOS / Linux: append export PATH="..." to ~/.bashrc / ~/.zshrc

Quick start

cd /path/to/your-project
pandaone init --root .

pandaone write \
    --file src/main.py \
    --reason "Fix user_id type annotation" \
    --problem "Original used int, could be None" \
    --approach "Change to Optional[int]" \
    --old 'def get_user(user_id: int):' \
    --new 'def get_user(user_id: Optional[int]):'

7 Defense Layers

Layer

Component

Purpose

L1

file chmod

File-level read-only lock

L2

watchdog

Real-time file monitoring + git checkout rollback

L3

pre-commit hook

Strict per-file APPROVED validation

L4

startup README

CLI loads project metadata on startup

L5

self-fingerprint

CLI's own SHA256 detects tampering

L6

binary SHA256 snapshot

Detect .png/.pdf binary tampering

L7

GitHub Actions CI

Pre-merge audit verification (final backstop)

MCP Server

{
  "mcpServers": {
    "pandaone": {
      "command": "pandaone-mcp",
      "env": {}
    }
  }
}

Exposes 11 tools for AI agents (Claude / Cursor / Trae).

All 11 tools declare the full set of 4 MCP annotations (readOnlyHint / destructiveHint / idempotentHint / openWorldHint) — OpenAI directory compliant (fixed in v0.7.14).

Use with ChatGPT

ChatGPT Desktop app's Developer Mode natively supports MCP servers. To add pandaone:

Steps:

  1. Open ChatGPT Desktop app

  2. Settings → Beta features → enable Developer Mode

  3. Settings → Connectors → Create new connector

  4. Paste this JSON (field names must match exactly):

{
  "name": "pandaone-guard",
  "command": "pandaone-mcp",
  "args": [],
  "env": {}
}
  1. ChatGPT will offer to install pandaone-guard on first use. If it doesn't auto-install, run manually:

# macOS / Linux
pip3 install pandaone-guard

# Windows (PowerShell)
pip install pandaone-guard

Advanced (custom venv / Python path / English interface):

{
  "name": "pandaone-guard",
  "command": "/path/to/venv/bin/python",
  "args": ["-m", "pandaone_mcp"],
  "env": {
    "PANDAX_LANG": "en"
  }
}

Environment variables:

Variable

Type

Default

Purpose

PANDAX_FP_PASSWORD

🔐 secret

"0000"

Only needed for pandaone_fingerprint_update / pandaone_watch daemon auth; set locally, never uploaded

PANDAX_LANG

config

"zh"

UI language (zh / en)

PANDAONE_SKIP_GIT_CHECK

config

unset

Set to 1 to skip git detection (for git-less environments)

NO_COLOR

config

unset

Set to 1 to disable colored output

Only one secret: PANDAX_FP_PASSWORD. Local config only, never sent to any remote.

License

MIT — see LICENSE

Available Tools

11 tools
pandaone_ciA
Read-onlyIdempotent

CI 审计验证:对比 base..head 的所有改动,确认每条变更都通过 pandaone write 审计

Inputs: root (required), base, head.

pandaone_fingerprint_updateA
Idempotent

更新密码指纹(用于 watch 守护进程鉴权)

Inputs: password (required).

pandaone_initB

在指定目录初始化 Pandaone AI Agent(创建 .pandaone/、config.json、pandaone.jsonl、可选 binary_snapshots.json)

Inputs: root (required), ext, no_binary.

pandaone_install_gitA
Idempotent

安装便携版 git(用于项目内 git hook,无需全局 git)

Inputs: probe_only, auto_download.

pandaone_install_hookB
Idempotent

安装/卸载 pre-commit hook

Inputs: root (required), uninstall.

pandaone_lockB
Idempotent

锁定所有受保护扩展名的文件(attrib +r / chmod -w)

Inputs: root (required).

pandaone_logB
Read-onlyIdempotent

查看审计日志(按文件/recent/格式过滤)

Inputs: root (required), file, format, output, +3 more.

pandaone_statusB
Read-onlyIdempotent

查看 Pandaone 状态(保护文件 / 审计次数 / 锁定状态等)

Inputs: root (required).

pandaone_unlockC
Idempotent

解锁所有受保护扩展名的文件

Inputs: root (required).

pandaone_watchB

启动 watchdog 守护进程(监控文件改动)

Inputs: root (required), daemon.

pandaone_writeA
Destructive

审计写入(核心命令):reason/problem/approach 必填;文本用 --old/--new 或 --content;二进制用 --from-file 或 --content-base64。目标文件不存在时视为创建新文件(须提供内容且扩展名受保护,action=create)

Inputs: file (required), reason (required), problem (required), approach (required), +6 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 11 tools

    Disambiguation4/5

    Each tool has a largely distinct purpose: initialization, audited writes, lock/unlock, logging/status, hook/watch setup, portable git install, fingerprint update, and CI verification. Minor boundary overlap exists between status and log viewing, and between hook/git installation tools, but descriptions clarify the intended use.

    Naming Consistency4/5

    All tools consistently use the pandaone_ prefix with snake_case, making the set easy to scan. However, the pattern mixes verbs, nouns, and abbreviations rather than following a strict verb_noun convention.

    Tool Count5/5

    With 11 tools, the set is well-scoped for a file audit and protection system. Each tool appears to earn its place by covering a distinct operational area without excessive fragmentation.

    Completeness4/5

    The surface covers the core lifecycle: init, audited write/create, lock/unlock, logs, status, hooks, watchdog, git setup, fingerprint update, and CI verification. Minor gaps remain around explicit configuration/protected-extension management, manual verification outside CI, and cleanup/uninstall workflows.

    Maintenance

    ActivityActive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Quantitative governance gate for AI agents. Six gates (risk, profit, novelty, complexity, quality, utility) return PROCEED/PAUSE/HALT/ESCALATE with confidence scores and hash-chained, tamper-evident audit trails. Generates NIST AI RMF and EU AI Act Annex IV artifacts. 10 MCP tools; local stdio and hosted Streamable HTTP with a free tier.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Provides MCP tools that give AI agents persistent, append-only memory in a git repository, letting them record observations, decisions, and corrections while retrieving context briefs, current facts, conflicts, and traceable event history without a vector database.
      4 npm
      MIT
    • A
      license
      B
      quality
      B
      maintenance
      Commit-time audit engine for AI coding agents. Scans git diffs with 24 audit rules, writes HMAC-signed tamper-evident audit history, and ships MCP tools for governance aggregation.
      104
      56
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables supervised, crash-resilient autonomous AI pair programming through nine MCP tools that checkpoint task progress in an atomic local DAG ledger, keep the machine awake during long runs, summarize repositories within a token budget, count tokens and costs across models, and rotate accounts before quota runs out. All state stays in a sandboxed project-local directory with zero telemetry, so long multi-step agent sessions survive crashes, context limits, and premature stopping.
      1
      Apache 2.0