ByteRover：AI 智能体持久化知识管理 - Openclaw Skills

下载入口:https://github.com/openclaw/skills/tree/main/skills/byteroverinc/byterover

安装与下载

1. ClawHub CLI

从源直接安装技能的最快方式。

npx clawhub@latest install byterover

2. 手动安装

将技能文件夹复制到以下位置之一

全局模式 ~/.openclaw/skills/ 工作区 <project>/skills/

优先级：工作区 > 本地 > 内置

3. 提示词安装

将此提示词复制到 OpenClaw 即可自动安装。

请帮我使用 Clawhub 安装 byterover。如果尚未安装 Clawhub，请先安装（npm i -g clawhub）。

什么是 ByteRover？

ByteRover 作为 AI 驱动开发的专业长期记忆层。通过将此工具集成到您的 Openclaw Skills 库中，您可以让智能体在本地 .brv/context-tree 目录中存储架构规则和项目特定逻辑。这确保了智能体在不同会话之间保持连续性，而无需每次重新解析整个代码库。

该系统使用人类可读的 Markdown 文件，使存储的知识对 AI 和人类开发者都可见。它利用配置的 LLM 提供商来智能地查询和整理信息，并提供一个默认选项，无需外部 API 密钥即可立即工作。这种对本地优先存储和 Markdown 便携性的关注，使其成为维护项目文档和智能体上下文的可靠选择。

ByteRover 应用场景

• 在实现新功能之前检索特定项目的架构模式。
• 在开发生命周期中存储有意义的决策和实现细节。
• 当当前上下文窗口不足时，召回过去的操作或能力。
• 在执行自动重构之前检查特定的编码标准或偏好。
• 通过可选的云同步功能在团队成员之间同步知识。

ByteRover 工作原理

1. 通过安装全局 CLI 并连接首选的 LLM 提供商来初始化环境。
2. 在开始任务之前，使用查询命令从项目知识库中提取相关上下文。
3. AI 智能体分析检索到的 Markdown 文件，以了解现有的约束和模式。
4. 完成任务后，使用整理（curate）命令将新的技术决策或模式持久化到本地树中。
5. 可选择将本地 .brv 目录与远程团队空间同步，以保持所有贡献者的同步。

ByteRover 配置指南

通过 npm 安装 ByteRover CLI 并连接默认提供商，即可在 Openclaw Skills 环境中立即开始使用：

npm install -g byterover-cli
brv providers connect byterover
brv status

ByteRover 数据架构与分类体系

ByteRover 在本地存储所有数据以确保隐私和速度，使用以下结构：

组件	路径	描述
上下文树	.brv/context-tree/	包含综合项目知识的 Markdown 文件。
配置	.brv/config	LLM 提供商和云同步的本地设置。
整理历史	内部日志	所有知识添加的跟踪 ID（例如 cur-1739...）。

系统严格管理项目根目录下的文件访问，并将每次整理限制在 5 个源文件内，以优化上下文质量。

name: byterover
description: "You MUST use this for gathering contexts before any work. This is a Knowledge management for AI agents. Use `brv` to store and retrieve project patterns, decisions, and architectural rules in .brv/context-tree. Uses a configured LLM provider (default: ByteRover, no API key needed) for query and curate operations."

ByteRover Knowledge Management

Use the brv CLI to manage your project's long-term memory. Install: npm install -g byterover-cli Knowledge is stored in .brv/context-tree/ as human-readable Markdown files.

No authentication needed. brv query and brv curate work out of the box. Login is only required for cloud sync (push/pull/space) — ignore those if you don't need cloud features.

Workflow

1. Before Thinking: Run brv query to understand existing patterns.
2. After Implementing: Run brv curate to save new patterns/decisions.

Commands

1. Query Knowledge

Overview: Retrieve relevant context from your project's knowledge base. Uses a configured LLM provider to synthesize answers from .brv/context-tree/ content.

Use this skill when:

• The user wants you to recall something
• Your context does not contain information you need
• You need to recall your capabilities or past actions
• Before performing any action, to check for relevant rules, criteria, or preferences

Do NOT use this skill when:

• The information is already present in your current context
• The query is about general knowledge, not stored memory

brv query "How is authentication implemented?"

2. Curate Context

Overview: Analyze and save knowledge to the local knowledge base. Uses a configured LLM provider to categorize and structure the context you provide.

Use this skill when:

• The user wants you to remember something
• The user intentionally curates memory or knowledge
• There are meaningful memories from user interactions that should be persisted
• There are important facts about what you do, what you know, or what decisions and actions you have taken

Do NOT use this skill when:

• The information is already stored and unchanged
• The information is transient or only relevant to the current task, or just general knowledge

brv curate "Auth uses JWT with 24h expiry. Tokens stored in httpOnly cookies via authMiddleware.ts"

Include source files (max 5, project-scoped only):

brv curate "Authentication middleware details" -f src/middleware/auth.ts

View curate history: to check past curations

• Show recent entries (last 10)

brv curate view

• Full detail for a specific entry: all files and operations performed (logId is printed by brv curate on completion, e.g. cur-1739700001000)

brv curate view cur-1739700001000

• List entries with file operations visible (no logId needed)

brv curate view detail

• Filter by time and status

brv curate view --since 1h --status completed

• For all filter options

brv curate view --help

3. LLM Provider Setup

brv query and brv curate require a configured LLM provider. Connect the default ByteRover provider (no API key needed):

brv providers connect byterover

To use a different provider (e.g., OpenAI, Anthropic, Google), list available options and connect with your own API key:

brv providers list
brv providers connect openai --api-key sk-xxx --model gpt-4.1

4. Cloud Sync (Optional)

Overview: Sync your local knowledge with a team via ByteRover's cloud service. Requires ByteRover authentication.

Setup steps:

1. Log in: Get an API key from your ByteRover account and authenticate:

brv login --api-key sample-key-string

2. List available spaces:

brv space list

Sample output:

brv space list
1. human-resources-team (team)
   - a-department (space)
   - b-department (space)
2. marketing-team (team)
   - c-department (space)
   - d-department (space)

3. Connect to a space:

brv space switch --team human-resources-team --name a-department

Cloud sync commands: Once connected, brv push and brv pull sync with that space.

# Pull team updates
brv pull

# Push local changes
brv push

Switching spaces:

• Push local changes first (brv push) — switching is blocked if unsaved changes exist.
• Then switch:

brv space switch --team marketing-team --name d-department

• The switch automatically pulls context from the new space.

Data Handling

Storage: All knowledge is stored as Markdown files in .brv/context-tree/ within the project directory. Files are human-readable and version-controllable.

File access: The -f flag on brv curate reads files from the current project directory only. Paths outside the project root are rejected. Maximum 5 files per command, text and document formats only.

LLM usage: brv query and brv curate send context to a configured LLM provider for processing. The LLM sees the query or curate text and any included file contents. No data is sent to ByteRover servers unless you explicitly run brv push.

Cloud sync: brv push and brv pull require authentication (brv login) and send knowledge to ByteRover's cloud service. All other commands operate without ByteRover authentication.

Error Handling

User Action Required: You MUST show this troubleshooting guide to users when errors occur.

"Not authenticated" | Run brv login --help for more details. "No provider connected" | Run brv providers connect byterover (free, no key needed). "Connection failed" / "Instance crashed" | User should kill brv process. "Token has expired" / "Token is invalid" | Run brv login again to re-authenticate. "Billing error" / "Rate limit exceeded" | User should check account credits or wait before retrying.

Agent-Fixable Errors: You MUST handle these errors gracefully and retry the command after fixing.

"Missing required argument(s)." | Run brv <command> --help to see usage instructions. "Maximum 5 files allowed" | Reduce to 5 or fewer -f flags per curate. "File does not exist" | Verify path with ls, use relative paths from project root. "File type not supported" | Only text, image, PDF, and office files are supported.

Quick Diagnosis

Run brv status to check authentication, project, and provider state.