diff --git a/README.md b/README.md
index d1a811c9..084f2ccf 100644
--- a/README.md
+++ b/README.md
@@ -1,65 +1,123 @@
+
+ English | 简体中文
+
+
+
+ 
+
+
- 
+ 
ByteMind
- 
- 
- 
- 
- 
+ A terminal-native AI coding agent for real repositories.
- 一个用 Go 实现的 AI Coding CLI，目标是提供更接近 OpenCode / ClaudeCode 的工作流能力。
+ Let AI inspect code, search files, run commands, edit files, plan tasks, and operate under configurable human approval.
- 核心能力 •
- 快速开始 •
- 配置文件 •
- 目录结构
+
+
+ 
+
-> [!NOTE]
-> 当前版本已具备多轮会话、流式输出、工具调用循环、Shell 执行审批、执行预算控制与重复调用检测等核心能力。
+
+ 
+ 
+ 
+ 
+ 
+
-> [!TIP]
-> 长任务建议提高 `-max-iterations`，到达预算后会返回阶段性总结，不会直接失败退出。
+
+ Documentation
+ ·
+ Why ByteMind
+ ·
+ Use Cases
+ ·
+ Quick Start
+ ·
+ Feature Matrix
+ ·
+ Architecture
+ ·
+ Skills / MCP / SubAgents
+
-
+---
-## 🎯 核心能力
+## Why ByteMind
-| 模块 | 说明 | 状态 |
-| --- | --- | --- |
-| 会话系统 | 多轮会话 + 会话持久化 |  |
-| 对话交互 | 纯 CLI 聊天 + 流式终端输出 |  |
-| Provider 适配 | OpenAI-compatible / Anthropic 双适配层 |  |
-| 工具执行 | 文件读写搜索、补丁替换、命令执行审批 |  |
-| 运行稳定性 | `max_iterations` 预算控制 + 重复调用检测 |  |
+ByteMind is built for developers who want AI to work **inside the repository**, not outside it.
+
+Instead of stopping at suggestions, ByteMind can participate in the actual engineering loop:
+
+```text
+Prompt → Plan → Tool Call → Observation → Code Change → Verification → Result
+```
+
+
+ 
+ 
+ 
+
+
+
+
+
+ 🧠 Plan
+ Use Plan mode for higher-risk tasks. Review the approach before making changes.
+ |
+
+ 🛠 Execute
+ Inspect files, search code, apply patches, run commands, and fetch external context when needed.
+ |
+
+ 🧭 Control
+ Keep sensitive actions behind approval policies and runtime boundaries.
+ |
+
+
+
+---
-
+## Use Cases
-## 🚀 快速开始
+| Scenario | What ByteMind can do |
+| --- | --- |
+| Understand a new repository | Inspect structure, find entrypoints, and map key modules and call paths |
+| Debug failing tests | Read failures, locate related code, patch the issue, and verify again |
+| Review or refine changes | Check correctness, regression risk, and missing test coverage |
+| Generate technical plans and RFCs | Turn repository context into an actionable implementation proposal |
+| Automate repeated engineering tasks | Encode common workflows through Skills, MCP, or SubAgents |
+| Collaborate under approval | Read and write files, run commands, and advance tasks while preserving approval boundaries |
-### 0) 一键安装（无需 Go）
+---
-macOS / Linux：
+## Quick Start
+
+### Install
+
+**macOS / Linux**
```bash
curl -fsSL https://raw.githubusercontent.com/1024XEngineer/bytemind/main/scripts/install.sh | bash
```
-Windows PowerShell：
+**Windows PowerShell**
```powershell
iwr -useb https://raw.githubusercontent.com/1024XEngineer/bytemind/main/scripts/install.ps1 | iex
```
-安装指定版本（将 `vX.Y.Z` 替换为要安装的发布标签）：
+**Install a specific version**
```bash
curl -fsSL https://raw.githubusercontent.com/1024XEngineer/bytemind/main/scripts/install.sh | BYTEMIND_VERSION=vX.Y.Z bash
@@ -69,45 +127,166 @@ curl -fsSL https://raw.githubusercontent.com/1024XEngineer/bytemind/main/scripts
$env:BYTEMIND_VERSION='vX.Y.Z'; iwr -useb https://raw.githubusercontent.com/1024XEngineer/bytemind/main/scripts/install.ps1 | iex
```
-更多安装方式见：[docs/installation.md](docs/installation.md)
+### Configure
-### 1) 准备配置
+```bash
+mkdir -p .bytemind
+cp config.example.json .bytemind/config.json
+```
-先复制示例配置，再把 `api_key` 等字段改成你自己的值：
+### Run
-```powershell
-New-Item -ItemType Directory -Force .bytemind | Out-Null
-Copy-Item config.example.json .bytemind/config.json
+```bash
+bytemind chat
+```
+
+```bash
+bytemind run -prompt "Analyze this repository and summarize the architecture"
```
-> 兼容说明：工作区 `config.json` 也会被识别；这里推荐 `.bytemind/config.json` 方便与源码分离。
+```bash
+bytemind run -prompt "Refactor this module and update tests" -max-iterations 64
+```
-### 2) 运行 ByteMind
+---
-聊天模式：
+## Terminal Preview
-```powershell
-go run ./cmd/bytemind chat
-```
+
+ 
+
-单次任务：
+---
-```powershell
-go run ./cmd/bytemind run -prompt "分析当前项目并生成改进建议"
+
+
+## Feature Matrix
+
+| Category | Capability | Notes |
+| --- | --- | --- |
+| **Terminal UX** | Terminal-first interaction | Built for repository-centric workflows |
+| **Streaming** | Real-time output | Useful for long-running tasks |
+| **Agent Loop** | Multi-step tool use + observations | More than a one-shot reply |
+| **Build / Plan** | Separate planning and execution modes | Better for high-risk changes |
+| **Files** | Read, search, write, replace, patch | Core repository operations |
+| **Shell** | Run commands under approval | Keep execution visible and controlled |
+| **Web** | Search and fetch external content | Useful when external context is needed |
+| **Sessions** | Persist and resume tasks | Suitable for long-running work |
+| **Skills** | Reusable workflows | Bug investigation, review, RFC, onboarding |
+| **MCP** | External tool / context integration | Extend the runtime beyond local tools |
+| **SubAgents** | Focused delegated work | Reduce noise in the main context |
+| **Safety** | Approval, allowlists, writable roots | Human-in-the-loop execution |
+| **Providers** | OpenAI-compatible / Anthropic | Configurable runtime support |
+
+---
+
+## Built-in Tools
+
+| Tool | Purpose |
+| --- | --- |
+| `list_files` | Inspect repository structure and candidate file scopes |
+| `read_file` | Read source code, docs, config, and test content |
+| `search_text` | Locate symbols, error messages, or call sites by keyword |
+| `write_file` | Create or fully rewrite files |
+| `replace_in_file` | Make small text replacements in existing files |
+| `apply_patch` | Apply incremental file changes through patches |
+| `run_shell` | Run commands inside the approval boundary and read results |
+| `web_search` | Search external sources when local context is insufficient |
+| `web_fetch` | Fetch a specific page as supplemental context |
+
+---
+
+## Core Experience
+
+
+
+
+ ✅ What ByteMind is good at
+
+ - Understanding unfamiliar repositories
+ - Debugging code and failing tests
+ - Planning and applying small refactors
+ - Reviewing correctness and regression risk
+ - Writing RFC-style implementation plans
+ - Automating repetitive coding workflows
+
+ |
+
+ ⚙️ What makes it practical
+
+ - Approval before sensitive actions
+ - Execution budget via
max_iterations
+ - Session persistence
+ - Provider-agnostic runtime
+ - Extensible skills and external tools
+ - SubAgent-based context isolation
+
+ |
+
+
+
+---
+
+## How It Works
+
+```mermaid
+graph TD
+ A["User Prompt"] --> B["Build Runtime Context"]
+ B --> C["LLM decides: answer or tool call"]
+ C --> D{"Tool Call?"}
+ D -- "No" --> E["Final Answer"]
+ D -- "Yes" --> F["Approval / Policy Check"]
+ F --> G["Execute Tool"]
+ G --> H["Observation appended to session"]
+ H --> I{"Done?"}
+ I -- "No" --> C
+ I -- "Yes" --> E
```
-提高执行预算：
+---
-```powershell
-go run ./cmd/bytemind chat -max-iterations 64
-go run ./cmd/bytemind run -prompt "refactor this module" -max-iterations 64
+
+
+## Architecture
+
+```mermaid
+graph TD
+ User["User"] --> CLI["cmd/bytemind"]
+ CLI --> App["App Bootstrap"]
+ App --> Runner["Runner"]
+
+ Runner --> Engine["Agent Engine"]
+ Engine --> Provider["Provider Runtime"]
+ Provider --> Model["LLM Provider"]
+
+ Engine --> Tools["Tool Registry"]
+ Tools --> FileTools["File Tools"]
+ Tools --> PatchTools["Patch Tools"]
+ Tools --> Shell["Shell Tool"]
+ Tools --> Web["Web Search / Fetch"]
+ Tools --> TaskTools["Task Output / Stop"]
+ Tools --> Delegate["Delegate SubAgent"]
+
+ Runner --> Session["Session Store"]
+ Runner --> Config["Config"]
+ Runner --> Skills["Skills Manager"]
+ Runner --> SubAgents["SubAgent Gateway"]
+ Runner --> Safety["Approval / Sandbox / Allowlist"]
```
-
+---
+
+## Configuration
-## ⚙️ 配置文件
+ByteMind normally merges three configuration layers: built-in defaults, user-level `~/.bytemind/config.json` (or `BYTEMIND_HOME/config.json`), and project-level `/.bytemind/config.json`.
-默认配置（OpenAI-compatible）：
+The example below is a **project-level config** and only affects the current workspace. Provider credentials reused across repositories usually belong in user-level config or environment variables. Passing `-config` uses that explicit config file.
+
+```text
+.bytemind/config.json
+```
+
+### OpenAI-compatible example
```json
{
@@ -115,26 +294,16 @@ go run ./cmd/bytemind run -prompt "refactor this module" -max-iterations 64
"type": "openai-compatible",
"base_url": "https://api.openai.com/v1",
"model": "gpt-5.4-mini",
- "api_key": "your-api-key-here"
+ "api_key_env": "BYTEMIND_API_KEY"
},
"approval_policy": "on-request",
- "notifications": {
- "desktop": {
- "enabled": true,
- "on_approval_required": true,
- "on_run_completed": true,
- "on_run_failed": true,
- "on_run_canceled": false,
- "cooldown_seconds": 3
- }
- },
+ "approval_mode": "interactive",
"max_iterations": 32,
"stream": true
}
```
-
-Anthropic 配置示例
+### Anthropic example
```json
{
@@ -142,67 +311,114 @@ go run ./cmd/bytemind run -prompt "refactor this module" -max-iterations 64
"type": "anthropic",
"base_url": "https://api.anthropic.com",
"model": "claude-sonnet-4-20250514",
- "api_key": "your-api-key-here",
+ "api_key_env": "ANTHROPIC_API_KEY",
"anthropic_version": "2023-06-01"
- }
+ },
+ "approval_policy": "on-request",
+ "approval_mode": "interactive"
+}
+```
+
+
+ Runtime boundary example
+
+```json
+{
+ "approval_policy": "on-request",
+ "approval_mode": "interactive",
+ "writable_roots": [],
+ "exec_allowlist": [],
+ "network_allowlist": [],
+ "system_sandbox_mode": "off"
}
```
-
+---
-## 🧱 目录结构
+
+
+## Skills, MCP and SubAgents
+
+### Skills
+
+The CLI currently exposes reusable workflow helpers through the registered slash commands below.
```text
-cmd/bytemind CLI 入口
-internal/agent 对话循环、系统提示词模板、流式输出
-internal/config 配置加载与环境变量覆盖
-internal/llm 通用消息与工具类型
-internal/provider 多 provider 适配层
-internal/session 会话持久化
-internal/tools 文件工具、patch 工具、shell 工具
+/help Show available commands
+/session Show the current session
+/sessions [limit] List recent sessions
+/agents [name] List available subagents or show one definition
+/explorer Show the builtin explorer subagent definition
+/review Show the builtin review subagent definition
+/resume Resume a recent session by id or prefix
+/new Start a new session in the current workspace
+/quit Exit the CLI
```
-## 🧭 交互命令
+### MCP
+
+Use MCP to connect ByteMind to external tools and context beyond local repository operations.
-- `/help`
-- `/session`
-- `/sessions`
-- `/quit`
+### SubAgents
-## 🧰 已实现工具
+SubAgents provide isolated execution contexts for focused work:
-- `list_files`
-- `read_file`
-- `search_text`
-- `write_file`
-- `replace_in_file`
-- `apply_patch`
-- `run_shell`
+- broad repository discovery
+- file targeting
+- read-only exploration
+- bug scope reduction
+- review / analysis subtasks
-## 📝 系统提示词维护
+
+ 
+ 
+ 
+
+
+---
+
+## Safety Model
+
+| Action | Typical behavior |
+| --- | --- |
+| Read files | Usually allowed automatically |
+| Search files | Usually allowed automatically |
+| Write files | Requires approval |
+| Run shell commands | Requires approval or allowlist |
+| High-risk actions | Shown before execution |
-系统提示词模板在：
+> ByteMind is designed around a simple principle:
+> **AI can execute, but humans should keep the final control boundary.**
-- `internal/agent/prompts/system.md`
+---
+
+## Project Structure
+
+```text
+cmd/bytemind CLI entrypoint
+internal/app Application bootstrap
+internal/agent Agent loop, prompts, streaming, subagent execution
+internal/config Config loading, defaults, environment overrides
+internal/llm Common message and tool types
+internal/provider Provider adapters and provider runtime
+internal/session Session persistence
+internal/tools File / patch / shell / web tools
+internal/skills Skills discovery and loading
+internal/subagents SubAgent manager and preflight gateway
+internal/sandbox Runtime boundary and sandbox-related logic
+```
-运行时由 `internal/agent/prompt.go` 通过 `go:embed` 内嵌 Markdown，并替换 `{{WORKSPACE}}`、`{{APPROVAL_POLICY}}` 占位符。
+---
-## 🌍 Environment Variables
+## Links
-See [docs/environment-variables.md](docs/environment-variables.md) for runtime TUI env vars:
+- Documentation:
+- GitHub:
-- `BYTEMIND_ENABLE_MOUSE`
-- `BYTEMIND_WINDOWS_INPUT_TTY`
-- `BYTEMIND_MOUSE_Y_OFFSET`
-- `BYTEMIND_DESKTOP_NOTIFY`
-- `BYTEMIND_NOTIFY_APPROVAL`
-- `BYTEMIND_NOTIFY_RUN_COMPLETED`
-- `BYTEMIND_NOTIFY_RUN_FAILED`
-- `BYTEMIND_NOTIFY_RUN_CANCELED`
-- `BYTEMIND_NOTIFY_COOLDOWN_SECONDS`
+---
-## 📄 License
+## License
This project is licensed under the [MIT License](LICENSE).
diff --git a/README.zh-CN.md b/README.zh-CN.md
new file mode 100644
index 00000000..91d44504
--- /dev/null
+++ b/README.zh-CN.md
@@ -0,0 +1,430 @@
+
+ English | 简体中文
+
+
+
+
+
+
+
+ 
+
+
+ByteMind
+
+
+ 面向真实代码仓库的终端原生 AI Coding Agent。
+
+
+
+ 让 AI 在终端中读代码、搜文件、执行命令、修改代码、规划任务，并在关键操作前保持可控审批。
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 文档
+ ·
+ 为什么是 ByteMind
+ ·
+ 使用场景
+ ·
+ 快速开始
+ ·
+ 功能矩阵
+ ·
+ 架构
+ ·
+ Skills / MCP / SubAgents
+
+
+---
+
+
+
+## 为什么是 ByteMind
+
+ByteMind 面向的是这样一类开发者：希望 AI **直接在代码仓库内部工作**，而不是停留在外部聊天窗口中。
+
+它不只给建议，而是尝试进入真实工程闭环：
+
+```text
+需求输入 → 制定计划 → 调用工具 → 观察结果 → 修改代码 → 执行验证 → 输出结果
+```
+
+
+ 
+ 
+ 
+
+
+
+
+
+ 🧠 先规划
+ 对于高风险任务，可以先进入 Plan 模式，先审阅方案，再决定是否执行。
+ |
+
+ 🛠 再执行
+ 检查文件、搜索代码、应用补丁、执行命令，并在需要时获取外部上下文。
+ |
+
+ 🧭 保持控制
+ 通过审批策略和运行边界，让关键动作始终处于可见、可控的范围内。
+ |
+
+
+
+---
+
+
+
+## 使用场景
+
+| 场景 | ByteMind 可以做什么 |
+| --- | --- |
+| 理解新代码仓库 | 浏览目录、定位入口、梳理关键模块和调用链 |
+| 排查失败测试 | 读取失败信息、定位相关代码、修改后再次验证 |
+| 审查或优化改动 | 从正确性、回归风险和测试覆盖角度检查变更 |
+| 生成技术方案和 RFC | 基于仓库上下文生成可执行的实现方案 |
+| 自动化重复工程任务 | 把常见流程沉淀为 Skills、MCP 或 SubAgent 工作流 |
+| 协作编码 | 在保留审批边界的前提下读写文件、执行命令、推进任务 |
+
+---
+
+
+
+## 快速开始
+
+### 安装
+
+**macOS / Linux**
+
+```bash
+curl -fsSL https://raw.githubusercontent.com/1024XEngineer/bytemind/main/scripts/install.sh | bash
+```
+
+**Windows PowerShell**
+
+```powershell
+iwr -useb https://raw.githubusercontent.com/1024XEngineer/bytemind/main/scripts/install.ps1 | iex
+```
+
+**安装指定版本**
+
+```bash
+curl -fsSL https://raw.githubusercontent.com/1024XEngineer/bytemind/main/scripts/install.sh | BYTEMIND_VERSION=vX.Y.Z bash
+```
+
+```powershell
+$env:BYTEMIND_VERSION='vX.Y.Z'; iwr -useb https://raw.githubusercontent.com/1024XEngineer/bytemind/main/scripts/install.ps1 | iex
+```
+
+### 配置
+
+```bash
+mkdir -p .bytemind
+cp config.example.json .bytemind/config.json
+```
+
+### 运行
+
+```bash
+bytemind chat
+```
+
+```bash
+bytemind run -prompt "分析当前仓库并总结架构"
+```
+
+```bash
+bytemind run -prompt "重构这个模块并更新测试" -max-iterations 64
+```
+
+---
+
+## 终端预览
+
+
+
+
+
+---
+
+
+
+## 功能矩阵
+
+| 分类 | 能力 | 说明 |
+| --- | --- | --- |
+| **终端体验** | 终端优先交互 | 面向真实仓库工作流 |
+| **流式输出** | 实时观察执行过程 | 适合长任务 |
+| **Agent Loop** | 多步骤工具调用 + 观察结果 | 不只是一次性问答 |
+| **Build / Plan** | 规划与执行分离 | 更适合高风险改动 |
+| **文件能力** | 读取、搜索、写入、替换、补丁 | 核心仓库操作 |
+| **Shell** | 在审批下执行命令 | 让执行过程可控 |
+| **Web** | 搜索和抓取外部内容 | 需要外部上下文时使用 |
+| **会话管理** | 持久化和恢复任务 | 适合长期工作 |
+| **Skills** | 可复用工作流 | Bug 排查、审查、RFC、onboarding |
+| **MCP** | 外部工具 / 上下文集成 | 让运行时能力更丰富 |
+| **SubAgents** | 聚焦型委托执行 | 降低主上下文噪声 |
+| **安全控制** | 审批、allowlist、可写目录 | 人类在环执行 |
+| **Provider** | OpenAI-compatible / Anthropic | 可配置运行时支持 |
+
+---
+
+## 内置工具
+
+| 工具 | 用途 |
+| --- | --- |
+| `list_files` | 检查仓库结构和候选文件范围 |
+| `read_file` | 读取源码、文档、配置和测试内容 |
+| `search_text` | 按关键词定位符号、错误信息或调用点 |
+| `write_file` | 创建或完整写入文件 |
+| `replace_in_file` | 对已有文件做小范围文本替换 |
+| `apply_patch` | 以补丁方式增量修改文件 |
+| `run_shell` | 在审批边界内执行命令并读取结果 |
+| `web_search` | 本地上下文不足时搜索外部资料 |
+| `web_fetch` | 抓取指定页面内容作为补充上下文 |
+
+---
+
+## 核心体验
+
+
+
+
+ ✅ ByteMind 擅长的事情
+
+ - 理解陌生代码仓库
+ - 排查代码与失败测试
+ - 规划并执行小范围重构
+ - 审查正确性与回归风险
+ - 撰写 RFC 风格实现方案
+ - 自动化重复工程工作流
+
+ |
+
+ ⚙️ 它为什么实用
+
+ - 敏感动作先审批
+ - 通过
max_iterations 控制执行预算
+ - 支持会话持久化
+ - Provider 无关运行时
+ - 可扩展 Skills 与外部工具
+ - 基于 SubAgent 的上下文隔离
+
+ |
+
+
+
+---
+
+## 工作原理
+
+```mermaid
+graph TD
+ A["用户输入"] --> B["构建运行时上下文"]
+ B --> C["LLM 决定：回答或调用工具"]
+ C --> D{"是否调用工具"}
+ D -- "否" --> E["最终回答"]
+ D -- "是" --> F["审批 / 策略检查"]
+ F --> G["执行工具"]
+ G --> H["观察结果写回会话"]
+ H --> I{"是否完成"}
+ I -- "否" --> C
+ I -- "是" --> E
+```
+
+---
+
+
+
+## 架构
+
+```mermaid
+graph TD
+ User["User"] --> CLI["cmd/bytemind"]
+ CLI --> App["App Bootstrap"]
+ App --> Runner["Runner"]
+
+ Runner --> Engine["Agent Engine"]
+ Engine --> Provider["Provider Runtime"]
+ Provider --> Model["LLM Provider"]
+
+ Engine --> Tools["Tool Registry"]
+ Tools --> FileTools["File Tools"]
+ Tools --> PatchTools["Patch Tools"]
+ Tools --> Shell["Shell Tool"]
+ Tools --> Web["Web Search / Fetch"]
+ Tools --> TaskTools["Task Output / Stop"]
+ Tools --> Delegate["Delegate SubAgent"]
+
+ Runner --> Session["Session Store"]
+ Runner --> Config["Config"]
+ Runner --> Skills["Skills Manager"]
+ Runner --> SubAgents["SubAgent Gateway"]
+ Runner --> Safety["Approval / Sandbox / Allowlist"]
+```
+
+---
+
+## 配置
+
+ByteMind 默认合并三层配置：内置默认值、用户级 `~/.bytemind/config.json`（或 `BYTEMIND_HOME/config.json`）和项目级 `/.bytemind/config.json`。
+
+下方示例是**项目级配置**，只影响当前工作区；跨仓库复用的 provider 凭证更适合放在用户级配置或环境变量中。显式传入 `-config` 时，会使用指定配置文件。
+
+```text
+.bytemind/config.json
+```
+
+### OpenAI-compatible 示例
+
+```json
+{
+ "provider": {
+ "type": "openai-compatible",
+ "base_url": "https://api.openai.com/v1",
+ "model": "gpt-5.4-mini",
+ "api_key_env": "BYTEMIND_API_KEY"
+ },
+ "approval_policy": "on-request",
+ "approval_mode": "interactive",
+ "max_iterations": 32,
+ "stream": true
+}
+```
+
+### Anthropic 示例
+
+```json
+{
+ "provider": {
+ "type": "anthropic",
+ "base_url": "https://api.anthropic.com",
+ "model": "claude-sonnet-4-20250514",
+ "api_key_env": "ANTHROPIC_API_KEY",
+ "anthropic_version": "2023-06-01"
+ },
+ "approval_policy": "on-request",
+ "approval_mode": "interactive"
+}
+```
+
+
+ 运行边界示例
+
+```json
+{
+ "approval_policy": "on-request",
+ "approval_mode": "interactive",
+ "writable_roots": [],
+ "exec_allowlist": [],
+ "network_allowlist": [],
+ "system_sandbox_mode": "off"
+}
+```
+
+
+
+---
+
+
+
+## Skills、MCP 与 SubAgents
+
+### Skills
+
+当前 CLI 通过下列已注册的斜杠命令暴露可复用工作流相关能力。
+
+```text
+/help 显示可用命令
+/session 显示当前会话
+/sessions [limit] 列出最近会话
+/agents [name] 列出可用 SubAgent 或查看某个定义
+/explorer 显示内置 explorer SubAgent 定义
+/review 显示内置 review SubAgent 定义
+/resume 按 id 或前缀恢复最近会话
+/new 在当前工作区开始新会话
+/quit 退出 CLI
+```
+
+### MCP
+
+MCP 用于把 ByteMind 连接到本地仓库之外的外部工具和上下文。
+
+### SubAgents
+
+SubAgents 提供聚焦型隔离执行上下文，适用于：
+
+- 大范围仓库探索
+- 文件定位
+- 只读探索
+- Bug 范围收敛
+- 审查 / 分析子任务
+
+
+ 
+ 
+ 
+
+
+---
+
+## 安全模型
+
+| 动作 | 默认行为 |
+| --- | --- |
+| 读取文件 | 通常自动允许 |
+| 搜索文件 | 通常自动允许 |
+| 写入文件 | 需要审批 |
+| 执行 shell 命令 | 需要审批或受 allowlist 约束 |
+| 高风险动作 | 执行前展示确认 |
+
+> ByteMind 的设计原则很简单：
+> **AI 可以执行，但最终控制边界必须掌握在人手里。**
+
+---
+
+## 项目结构
+
+```text
+cmd/bytemind CLI 入口
+internal/app 应用启动装配
+internal/agent Agent loop、prompt、streaming、subagent execution
+internal/config 配置加载、默认值、环境变量覆盖
+internal/llm 通用消息与工具类型
+internal/provider Provider 适配与 provider runtime
+internal/session 会话持久化
+internal/tools 文件 / patch / shell / web 工具
+internal/skills Skills 发现与加载
+internal/subagents SubAgent 管理与 preflight gateway
+internal/sandbox 运行边界与沙箱相关逻辑
+```
+
+---
+
+## 链接
+
+- 文档：
+- GitHub：
+
+---
+
+## License
+
+This project is licensed under the [MIT License](LICENSE).
diff --git a/docs/assets/bytemind-terminal-preview.webp b/docs/assets/bytemind-terminal-preview.webp
new file mode 100644
index 00000000..352e256c
Binary files /dev/null and b/docs/assets/bytemind-terminal-preview.webp differ