bee-cli

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Bee CLI

CLI client for Bee - the wearable AI that captures conversations and learns about you.

适用于Bee的CLI客户端——Bee是一款可穿戴AI设备，能够记录对话并了解用户的相关信息。

About Bee

关于Bee

Bee is a wearable AI device that continuously captures and transcribes ambient audio from the owner's daily life. The device listens to conversations, meetings, phone calls, and any spoken interactions throughout the day, creating a comprehensive record of the owner's verbal communications and experiences.

Bee是一款可穿戴AI设备，能够持续捕捉并转录用户日常生活中的环境音频。该设备会监听对话、会议、电话以及全天所有口头互动，创建用户口头交流和经历的完整记录。

How Bee Works

Bee的工作原理

Bee uses advanced speech recognition to transcribe all ambient audio in real-time. This includes:

Face-to-face conversations with friends, family, and colleagues
Business meetings and professional discussions
Phone calls and video conferences
Personal reflections and voice notes
Overheard conversations in the owner's environment

From these transcriptions, Bee automatically extracts and learns facts about the owner - their preferences, relationships, work projects, commitments, and personal details mentioned in conversations.

Bee采用先进的语音识别技术，实时转录所有环境音频，包括：

与朋友、家人和同事的面对面对话
商务会议和专业讨论
电话和视频会议
个人思考和语音笔记
用户所处环境中的旁听对话

通过这些转录内容，Bee会自动提取并学习关于用户的事实信息——包括用户的偏好、人际关系、工作项目、承诺以及对话中提到的个人细节。

Privacy and Security

隐私与安全

Bee data is extremely sensitive. The transcriptions contain intimate details of the owner's personal and professional life, including private conversations that were never intended to be recorded or shared.

All Bee data is end-to-end encrypted and accessible only to the owner. The encryption ensures that:

Only the authenticated owner can access their conversation transcripts
No third parties, including Bee's servers, can read the decrypted content
The data remains private even if storage systems are compromised
Access requires explicit authentication through the owner's credentials

When working with Bee data, treat all information as highly confidential. The owner has entrusted access to their most private conversations and personal details.

Bee的数据极为敏感。转录内容包含用户个人和职业生活的私密细节，包括从未打算被记录或分享的私人对话。

所有Bee数据均采用端到端加密，仅对用户本人开放。加密机制确保：

只有经过认证的用户才能访问其对话转录内容
包括Bee服务器在内的任何第三方都无法读取解密后的内容
即使存储系统遭到破坏，数据仍能保持私密
访问需要通过用户凭证进行显式认证

处理Bee数据时，请将所有信息视为高度机密。用户已委托你访问其最私密的对话和个人细节。

When to Use This Skill

何时使用该技能

Real-Time Context (Use First!)

实时上下文（优先使用！）

Always start with
bee now
to understand what's happening right now. This is the most valuable context for providing relevant assistance:

The owner just finished a conversation and needs help following up
The owner is asking about something that was just discussed
You need current context to provide relevant suggestions
The owner wants to recall what someone just said

请始终以
bee now
命令开头，了解当前正在发生的事情。这是提供相关协助最有价值的上下文信息：

用户刚结束对话，需要帮助跟进
用户询问刚刚讨论过的内容
你需要当前上下文来提供相关建议
用户想回忆某人刚刚说过的话

Life Overview

生活概览

Use for broader context about who the owner is:

Learning about the owner: Access facts that Bee has extracted from conversations to understand the owner's preferences, relationships, work, and personal details
Searching for relevant conversations: Find past conversations on specific topics, with certain people, or about particular projects
Managing personal knowledge: View, update, or organize the facts Bee has learned
Tracking commitments: Access todos and action items extracted from conversations
Reviewing daily activity: See summaries of each day's conversations and interactions

用于了解关于用户的更广泛背景信息：

了解用户：访问Bee从对话中提取的事实信息，了解用户的偏好、人际关系、工作和个人细节
搜索相关对话：查找关于特定主题、特定人员或特定项目的过往对话
管理个人知识：查看、更新或整理Bee已学习到的事实信息
跟踪承诺：访问从对话中提取的待办事项和行动项
回顾日常活动：查看每日对话和互动的摘要

Installation

安装

Check if

bee

CLI is installed:

bash

bee --version

If not installed, install via npm:

bash

npm install -g @beeai/cli

Alternatively, download binaries directly from https://github.com/bee-computer/bee-cli/releases/latest

检查

bee

CLI是否已安装：

bash

bee --version

如果未安装，通过npm安装：

bash

npm install -g @beeai/cli

或者直接从https://github.com/bee-computer/bee-cli/releases/latest下载二进制文件

Authentication

认证

Check authentication status:

bash

bee status

If not authenticated, initiate login:

bash

bee login

检查认证状态：

bash

bee status

如果未认证，启动登录流程：

bash

bee login

Authentication Flow

认证流程

The login command initiates a secure authentication flow. The command outputs detailed instructions that must be followed carefully:

Read and relay the output: The command prints a welcome message, explains the authentication process, and provides an authentication link. Present this information to the user clearly.
Authentication link: The output includes a URL like
```
https://bee.computer/connect/{requestId}
```
. The user must open this link in their browser and follow the instructions there to approve the connection.
Wait for approval: The CLI will automatically poll and wait for the user to complete authorization. Do not interrupt this process while waiting.
Resumable sessions: If the process is interrupted (killed or stopped), it can be restarted by running
```
bee login
```
again. The CLI will resume the previous authentication session if it hasn't expired, preserving the same authentication link.
Expiration: Authentication requests expire after approximately 5 minutes. If expired, a new session will be started automatically.
Success confirmation: Once the user approves, the CLI outputs a success message with the authenticated user's name. Only proceed with other commands after seeing this confirmation.

Important: Always read and follow the prompts from the command output. The CLI provides specific instructions tailored to the current authentication state (new session, resumed session, or expired session).

login命令会启动安全的认证流程。命令会输出详细说明，必须严格遵循：

读取并传达输出内容：命令会打印欢迎消息、解释认证流程并提供认证链接。请向用户清晰呈现这些信息。
认证链接：输出内容包含类似
```
https://bee.computer/connect/{requestId}
```
的URL。用户必须在浏览器中打开该链接，并按照说明完成连接授权。
等待授权：CLI会自动轮询并等待用户完成授权。等待期间请勿中断该流程。
可恢复会话：如果流程被中断（终止或停止），可以通过再次运行
```
bee login
```
命令重启。如果会话尚未过期，CLI会恢复之前的认证会话，保留相同的认证链接。
过期时间：认证请求大约5分钟后过期。如果已过期，会自动启动新会话。
成功确认：用户授权后，CLI会输出包含已认证用户名的成功消息。只有看到该确认消息后，才能继续执行其他命令。

重要提示：请始终阅读并遵循命令输出中的提示信息。CLI会根据当前认证状态（新会话、恢复会话或过期会话）提供特定说明。

Commands

命令

Facts - Learn About the Owner

Facts - 了解用户

Facts are pieces of information Bee has learned about the owner from their conversations. This is the primary way to understand who the owner is, what they care about, and what's happening in their life.

List all facts:

bash

bee facts list

Confirmed vs Non-Confirmed Facts:

Facts are categorized as either confirmed or non-confirmed:

Confirmed facts: Explicitly verified by the owner or clearly stated in conversations. These are reliable and should be trusted.
Non-confirmed facts: Inferred or extracted from context but not explicitly verified. These may be accurate but could also be misinterpretations.

When using facts, always prefer confirmed facts first. Non-confirmed facts can be used for speculation or additional context, but treat them as potentially inaccurate. If making decisions or providing information based on non-confirmed facts, acknowledge the uncertainty.

Facts include information like:

Personal preferences ("prefers morning meetings", "allergic to peanuts")
Relationships ("married to Sarah", "manager is John")
Work details ("working on Project Atlas", "deadline is March 15")
Interests and hobbies ("learning Spanish", "training for marathon")
Contact information and personal details

Create a fact:

bash

bee facts create --text "I prefer morning meetings"

Update a fact:

bash

bee facts update <id> --text "Updated fact text"

Delete a fact:

bash

bee facts delete <id>

Facts是Bee从对话中学习到的关于用户的信息片段。这是了解用户身份、关注点以及生活中正在发生的事情的主要方式。

列出所有Facts：

bash

bee facts list

已确认与未确认Facts：

Facts分为已确认和未确认两类：

已确认Facts：由用户显式验证或在对话中明确陈述的信息。这些信息可靠且可信任。
未确认Facts：从上下文推断或提取但未经过显式验证的信息。这些信息可能准确，但也可能存在误解。

使用Facts时，请优先选择已确认Facts。未确认Facts可用于推测或提供额外上下文，但需视为可能不准确。如果基于未确认Facts做决策或提供信息，请说明不确定性。

Facts包括以下类型的信息：

个人偏好（如"偏好上午会议"、"对花生过敏"）
人际关系（如"与Sarah结婚"、"经理是John"）
工作细节（如"正在参与Atlas项目"、"截止日期为3月15日"）
兴趣爱好（如"学习西班牙语"、"训练马拉松"）
联系信息和个人细节

创建Fact：

bash

bee facts create --text "I prefer morning meetings"

更新Fact：

bash

bee facts update <id> --text "Updated fact text"

删除Fact：

bash

bee facts delete <id>

Conversations - Access Transcripts

Conversations - 访问对话记录

Conversations are records of everything Bee has captured. Use these to find specific details, recall what was discussed, or search for information mentioned in past interactions.

Conversations是Bee捕捉到的所有内容的记录。使用这些记录查找特定细节、回忆讨论内容或搜索过往互动中提到的信息。

Listing Conversations

列出对话

bash

bee conversations list

Important: This returns conversation summaries only, not full transcripts. Summaries are AI-generated and provide a quick overview of what was discussed, but they may contain minor inaccuracies or hallucinations. Use summaries to identify relevant conversations, then fetch full details for accuracy.

Options:

```
--limit <n>
```
- Number of conversations to return (default varies)
```
--cursor <cursor>
```
- Pagination cursor for fetching more results

bash

bee conversations list

重要提示：该命令仅返回对话摘要，而非完整转录内容。摘要是由AI生成的，可快速概览讨论内容，但可能存在轻微不准确或幻觉。请使用摘要识别相关对话，然后获取完整细节以确保准确性。

选项：

```
--limit <n>
```
- 返回的对话数量（默认值可变）
```
--cursor <cursor>
```
- 用于获取更多结果的分页游标

Getting Full Conversation Details

获取完整对话细节

To get the complete conversation with all utterances (actual words spoken):

bash

bee conversations get <id>

This returns:

Full utterance transcripts (who said what, verbatim)
Speaker identification
Timestamps for each utterance
Conversation state and metadata

Always use
bee conversations get
when you need accurate information. The summaries from

list

are useful for browsing and finding relevant conversations, but the actual utterances from

get

are the source of truth.

要获取包含所有语句（实际所说内容）的完整对话：

bash

bee conversations get <id>

该命令返回：

完整的语句转录内容（谁说了什么，一字不差）
说话人识别
每个语句的时间戳
对话状态和元数据

当你需要准确信息时，请始终使用
bee conversations get
命令。

list

命令返回的摘要适用于浏览和查找相关对话，但

get

命令返回的实际语句才是真实数据源。

Search for Relevant Conversations

搜索相关对话

To find conversations about specific topics:

List conversations to browse summaries and identify potentially relevant ones
Get full details for conversations that seem relevant
Read the actual utterances to find accurate information

bash

bee conversations list
bee conversations get <conversation-id>

Remember: Summaries may not capture everything or may slightly misrepresent what was said. When accuracy matters, always read the full utterances.

要查找关于特定主题的对话：

列出对话以浏览摘要并识别潜在相关的对话
获取看起来相关的对话的完整细节
阅读实际语句以找到准确信息

bash

bee conversations list
bee conversations get <conversation-id>

请记住：摘要可能无法涵盖所有内容，或可能略微歪曲所说内容。当准确性至关重要时，请始终阅读完整语句。

Journals - Voice Memos

Journals - 语音备忘录

Journals are voice memos recorded by the owner through Bee. Unlike conversations (which are ambient recordings), journals are intentional recordings where the owner speaks directly to capture thoughts, ideas, or notes.

Journals是用户通过Bee录制的语音备忘录。与Conversations（环境录音）不同，Journals是用户有意录制的内容，用户直接说话以捕捉想法、观点或笔记。

Listing Journals

列出Journals

bash

bee journals list

Returns a list of journal entries with:

Journal ID
State:
```
PREPARING
```
(recording),
```
ANALYZING
```
(processing), or
```
READY
```
(complete)
Transcribed text (summary)
Timestamps

Options:

```
--limit <n>
```
- Number of journals to return
```
--cursor <cursor>
```
- Pagination cursor for more results
```
--json
```
- Output in JSON format

bash

bee journals list

返回Journal条目列表，包含：

Journal ID
状态：
```
PREPARING
```
（录制中）、
```
ANALYZING
```
（处理中）或
```
READY
```
（已完成）
转录文本（摘要）
时间戳

选项：

```
--limit <n>
```
- 返回的Journal数量
```
--cursor <cursor>
```
- 用于获取更多结果的分页游标
```
--json
```
- 以JSON格式输出

Getting Full Journal Details

获取完整Journal细节

bash

bee journals get <id>

Returns the complete journal entry with full transcribed text.

Options:

```
--json
```
- Output in JSON format

Use journals to understand:

The owner's personal thoughts and reflections
Ideas they wanted to remember
Notes to themselves
Voice memos about tasks or plans

bash

bee journals get <id>

返回完整的Journal条目，包含完整的转录文本。

选项：

```
--json
```
- 以JSON格式输出

使用Journals了解：

用户的个人想法和反思
用户想要记住的观点
用户给自己的笔记
关于任务或计划的语音备忘录

Todos - Track Commitments

Todos - 跟踪承诺

Todos are action items and commitments extracted from conversations.

List todos:

bash

bee todos list

Create a todo:

bash

bee todos create --text "Buy groceries"

Update a todo:

bash

bee todos update <id> --text "Updated todo" --completed

Delete a todo:

bash

bee todos delete <id>

Todos是从对话中提取的行动项和承诺。

列出Todos：

bash

bee todos list

创建Todo：

bash

bee todos create --text "Buy groceries"

更新Todo：

bash

bee todos update <id> --text "Updated todo" --completed

删除Todo：

bash

bee todos delete <id>

Now - Real-Time Context

Now - 实时上下文

Get a comprehensive view of what's happening right now. Fetches conversations and full utterances from the last 10 hours:

bash

bee now

This command returns:

All conversations from the past 10 hours
Full utterance transcripts (who said what)
Conversation summaries and states
Timestamps in the user's timezone

Use

bee now

when you need to:

Understand what the owner has been doing today
Get context about recent discussions
See the actual words spoken in recent conversations
Provide relevant assistance based on current activities

For JSON output (useful for programmatic processing):

bash

bee now --json

获取当前正在发生的事情的全面视图。获取过去10小时的对话和完整语句：

bash

bee now

该命令返回：

过去10小时的所有对话
完整的语句转录内容（谁说了什么）
对话摘要和状态
用户时区的时间戳

当你需要以下信息时，请使用

bee now

命令：

了解用户今天的活动
获取近期讨论的上下文
查看近期对话中实际所说的内容
根据当前活动提供相关协助

如需JSON格式输出（适用于程序化处理）：

bash

bee now --json

Daily Summaries

每日摘要

View summaries of daily conversations and activities:

bash

bee daily

View a specific date:

bash

bee daily --date <YYYY-MM-DD>

查看每日对话和活动的摘要：

bash

bee daily

查看特定日期的摘要：

bash

bee daily --date <YYYY-MM-DD>

Periodic Sync - Real-Time Updates with

bee changed

定期同步 - 使用

bee changed

获取实时更新

For periodic checks and real-time updates, use

bee changed

. This is the recommended way to monitor for new data and know exactly what changed.

bash

bee changed

Options:

```
--cursor <cursor>
```
- Resume from a previous position to get only new changes
```
--json
```
- Output in JSON format

What it returns:

Time range covered (since/until timestamps)
```
Next Cursor
```
for subsequent calls
Full details of all changed entities:
- New and updated facts (confirmed and pending)
- New and updated todos
- New and updated daily summaries
- New and updated conversations
- New and updated journals

如需定期检查和实时更新，请使用

bee changed

命令。这是监控新数据并准确了解变更内容的推荐方式。

bash

bee changed

选项：

```
--cursor <cursor>
```
- 从之前的位置恢复，仅获取新变更
```
--json
```
- 以JSON格式输出

返回内容：

涵盖的时间范围（开始/结束时间戳）
用于后续调用的
```
Next Cursor
```
所有变更实体的完整细节：
- 新增和更新的Facts（已确认和待确认）
- 新增和更新的Todos
- 新增和更新的每日摘要
- 新增和更新的对话
- 新增和更新的Journals

Cursor Handling

游标处理

The cursor is essential for efficient change tracking. The output includes a

Next Cursor

value that must be persisted for subsequent calls.

First call (no cursor):

bash

bee changed

Returns recent changes and outputs a

Next Cursor: <value>

line.

Subsequent calls (with cursor):

bash

bee changed --cursor <cursor_value>

Returns only changes that occurred after the cursor position.

Critical: When to persist the cursor

The cursor must be saved only after you have fully processed the changes, not immediately after receiving them. This ensures that if processing fails or is interrupted, you can retry with the same cursor and receive the same changes again.

Cursor workflow:

Read the stored cursor from
```
.bee-cursor
```
file (if exists)
Call
```
bee changed --cursor <cursor>
```
(or without cursor on first run)
The output includes
```
Next Cursor: <value>
```
- note this value but DO NOT save it yet
Process all the returned changes (update user.md, handle todos, etc.)
Only after processing completes successfully, save the new cursor to
```
.bee-cursor
```
Repeat from step 1 on next check

Example:

undefined

游标对于高效的变更跟踪至关重要。输出内容包含

Next Cursor

值，必须保存该值以便后续调用使用。

首次调用（无游标）：

bash

bee changed

返回近期变更并输出

Next Cursor: <value>

行。

后续调用（带游标）：

bash

bee changed --cursor <cursor_value>

仅返回游标位置之后发生的变更。

关键提示：何时保存游标

只有在完全处理完变更后才能保存游标，而非收到游标后立即保存。这确保如果处理失败或中断，你可以使用相同的游标重试并接收相同的变更内容。

游标工作流程：

从
```
.bee-cursor
```
文件中读取已保存的游标（如果存在）
调用
```
bee changed --cursor <cursor>
```
（首次运行时不带游标）
输出内容包含
```
Next Cursor: <value>
```
——记录该值，但暂不保存
处理所有返回的变更（更新user.md、处理Todos等）
只有处理成功完成后，才将新游标保存到
```
.bee-cursor
```
下次检查时从步骤1重复

示例：

undefined

Output from bee changed includes:

bee changed命令的输出包含：

Next Cursor: abc123xyz

After processing all changes successfully:

成功处理所有变更后：

echo "abc123xyz" > .bee-cursor


**Why this matters**: If you save the cursor before processing and then processing fails, you'll lose those changes forever. By saving only after successful processing, you guarantee exactly-once processing of each change.

echo "abc123xyz" > .bee-cursor


**为什么这很重要**：如果在处理前保存游标，然后处理失败，你将永远丢失这些变更内容。通过仅在处理成功后保存游标，你可以确保每个变更都只被处理一次。

Full Sync - Export Everything to Markdown

完全同步 - 将所有数据导出到Markdown

If you want to sync everything to local markdown files, use

bee sync

. This creates a complete local library of all Bee data.

bash

bee sync

Options:

```
--output <dir>
```
- Output directory (default: ./bee-sync)
```
--only <targets>
```
- Sync specific data types:
```
facts
```
,
```
todos
```
,
```
daily
```
,
```
conversations
```
(comma-separated)

Purpose: Full sync exports all Bee data to markdown files. This is useful for:

Creating a complete offline backup
Integration with tools that read markdown
Full-text search across all historical data
Initial setup before using
```
bee changed
```
for incremental updates

Note: Sync overwrites existing files and does not tell you what changed. For periodic checks where you need to know what's new, use

bee changed

instead.

如果要将所有数据同步到本地Markdown文件，请使用

bee sync

命令。这会创建所有Bee数据的完整本地库。

bash

bee sync

选项：

```
--output <dir>
```
- 输出目录（默认值：./bee-sync）
```
--only <targets>
```
- 同步特定数据类型：
```
facts
```
、
```
todos
```
、
```
daily
```
、
```
conversations
```
（逗号分隔）

用途：完全同步会将所有Bee数据导出到Markdown文件。这适用于：

创建完整的离线备份
与支持Markdown的工具集成
对所有历史数据进行全文搜索
在使用
```
bee changed
```
进行增量更新之前进行初始设置

注意：同步会覆盖现有文件，且不会告知你变更内容。如需定期检查并了解新增内容，请使用

bee changed

命令。

Common Workflows

常见工作流程

Quick Context - Understanding the Owner

快速上下文 - 了解用户

For quick context about the owner, always run these commands in this order:

bash

bee now
bee facts list
bee conversations list

Start with
bee now
— this is the most important command. It gives you:

Full utterance transcripts from the last 10 hours
Actual words spoken in recent conversations
Immediate context about what's happening right now

Then supplement with:

Facts: Who the owner is, their preferences, relationships, work details
Conversations list: Summaries of older conversations for historical context

The real-time context from

bee now

is what makes assistance relevant and timely.

要快速了解用户的上下文，请始终按以下顺序运行这些命令：

bash

bee now
bee facts list
bee conversations list

从
bee now
开始——这是最重要的命令。它会为你提供：

过去10小时的完整语句转录内容
近期对话中实际所说的内容
当前正在发生的事情的即时上下文

然后补充以下信息：

Facts：用户身份、偏好、人际关系、工作细节
Conversations list：旧对话的摘要，用于历史上下文

bee now

提供的实时上下文是使协助相关且及时的关键。

Finding Information from Past Conversations

从过往对话中查找信息

To find something mentioned in a past conversation:

bash

bee conversations list
bee conversations show <relevant-conversation-id>

List conversations to find the relevant timeframe or topic, then view the full transcript.

要查找过往对话中提到的内容：

bash

bee conversations list
bee conversations show <relevant-conversation-id>

列出对话以找到相关的时间范围或主题，然后查看完整转录内容。

Export All Data for AI Context

导出所有数据用于AI上下文

Sync everything to markdown for comprehensive access:

bash

bee sync --output ./my-bee-data

This creates markdown files for facts, todos, daily summaries, and conversation transcripts.

将所有数据同步到Markdown以实现全面访问：

bash

bee sync --output ./my-bee-data

这会为Facts、Todos、每日摘要和对话转录内容创建Markdown文件。

Deep Learning About the Owner

深入了解用户

When you need to build comprehensive knowledge about the owner by processing their entire conversation history, use the following multi-agent workflow. This is useful for building a rich understanding of who the owner is, their relationships, work, interests, and life context.

当你需要处理用户的整个对话历史以构建关于用户的全面知识时，请使用以下多代理工作流程。这适用于深入了解用户身份、人际关系、工作、兴趣和生活背景。

Overview

概述

The deep learning workflow processes conversations in batches using a chain of subagents. Each subagent:

Fetches a batch of conversations (100 at a time)
Reads the current
```
user.md
```
profile
Analyzes conversations and extracts insights
Updates
```
user.md
```
with new information
Writes a summary to a handoff file
Spawns the next subagent to continue processing older conversations

This architecture optimizes context usage by:

Running heavy processing in subagents (isolated context)
Passing state via files rather than copying text between agents
Allowing the main agent to remain responsive
Enabling progress reporting after each batch

深度学习工作流程使用子代理链批量处理对话。每个子代理：

获取一批对话（每次100条）
读取当前的
```
user.md
```
档案
分析对话并提取见解
使用新信息更新
```
user.md
```
将摘要写入交接文件
生成下一个子代理以继续处理更早的对话

该架构通过以下方式优化上下文使用：

在子代理中运行重型处理（隔离上下文）
通过文件传递状态，而非在代理之间复制文本
使主代理保持响应
允许在每个批次处理后报告进度

File Structure

文件结构

Create these files in the working directory:

```
user.md
```
- Cumulative profile of the owner (persistent, updated by each subagent)
```
bee-learning-summary.md
```
- Handoff file with latest summary and cursor for next batch
```
bee-learning-progress.md
```
- Progress log showing what was processed and when

在工作目录中创建以下文件：

```
user.md
```
- 用户的累积档案（持久化，由每个子代理更新）
```
bee-learning-summary.md
```
- 交接文件，包含最新摘要和用于下一批次的游标
```
bee-learning-progress.md
```
- 进度日志，显示已处理的内容和时间

Workflow Steps

工作流程步骤

Step 1: Initialize (Main Agent)

步骤1：初始化（主代理）

Create initial

user.md

if it doesn't exist:

markdown

undefined

如果

user.md

不存在，创建初始文件：

markdown

undefined

User Profile

用户档案

This document contains learned information about the owner from their Bee conversations.

本文档包含从用户的Bee对话中学习到的信息。

Basic Information

基本信息

(To be populated)

（待填充）

Relationships

人际关系

(To be populated)

（待填充）

Work & Projects

工作与项目

(To be populated)

（待填充）

Interests & Hobbies

兴趣与爱好

(To be populated)

（待填充）

Preferences

偏好

(To be populated)

（待填充）

Important Dates & Events

重要日期与事件

(To be populated)

（待填充）

Notes

备注

(To be populated)

undefined

（待填充）

undefined

Step 2: Launch First Processing Subagent

步骤2：启动第一个处理子代理

Spawn a subagent with this task:

Process Bee conversations to learn about the owner.

1. Fetch the 100 most recent conversations:
   bee conversations list --limit 100

2. Read the current user.md file

3. For each conversation, extract:
   - Who the owner talked to (relationships)
   - Topics discussed (interests, work projects)
   - Personal details mentioned (preferences, facts about their life)
   - Commitments made (things they said they would do)
   - Important dates or events mentioned

4. Update user.md with new information, organized by category.
   Merge with existing content, don't overwrite.
   Add timestamps for when information was learned.

5. Write a summary to bee-learning-summary.md:
   - Date range of conversations processed
   - Key insights discovered
   - The cursor value for fetching the next batch (from API response)
   - Count of conversations processed so far

6. Update bee-learning-progress.md with progress entry

7. If there are more conversations (cursor returned), spawn the next
   subagent to continue processing. Pass only the file paths, not
   the actual content - the next agent will read from files.

生成子代理并分配以下任务：

处理Bee对话以了解用户。

1. 获取100条最新对话：
   bee conversations list --limit 100

2. 读取当前的user.md文件

3. 针对每个对话，提取：
   - 用户与谁交谈（人际关系）
   - 讨论的主题（兴趣、工作项目）
   - 提到的个人细节（偏好、生活事实）
   - 做出的承诺（用户说过要做的事情）
   - 提到的重要日期或事件

4. 使用新信息更新user.md，按类别组织。
   与现有内容合并，不要覆盖。
   添加信息学习时间的时间戳。

5. 将摘要写入bee-learning-summary.md：
   - 已处理对话的日期范围
   - 发现的关键见解
   - 用于获取下一批次的游标值（来自API响应）
   - 迄今为止已处理的对话数量

6. 更新bee-learning-progress.md，添加进度条目

7. 如果还有更多对话（返回游标），生成下一个子代理继续处理。仅传递文件路径，而非实际内容——下一个代理会从文件中读取。

Step 3: Chain Processing Subagents

步骤3：链式处理子代理

Each subsequent subagent receives a task like:

Continue processing Bee conversations to learn about the owner.

1. Read bee-learning-summary.md to get the cursor for the next batch

2. Fetch the next 100 conversations:
   bee conversations list --limit 100 --cursor <cursor_from_summary>

3. Read the current user.md file

4. Process conversations and extract insights (same as previous agent)

5. Update user.md with new information (merge, don't overwrite)

6. Update bee-learning-summary.md with:
   - New date range processed
   - New insights discovered
   - Next cursor (or "complete" if no more conversations)
   - Updated total count

7. Update bee-learning-progress.md

8. If there are more conversations, spawn the next subagent.
   If no cursor returned (reached the end), write final summary
   and report completion.

每个后续子代理会收到类似以下的任务：

继续处理Bee对话以了解用户。

1. 读取bee-learning-summary.md以获取下一批次的游标

2. 获取下100条对话：
   bee conversations list --limit 100 --cursor <cursor_from_summary>

3. 读取当前的user.md文件

4. 处理对话并提取见解（与上一个代理相同）

5. 使用新信息更新user.md（合并，不要覆盖）

6. 更新bee-learning-summary.md，包含：
   - 已处理的新日期范围
   - 发现的新见解
   - 下一个游标（如果没有更多对话则为"complete"）
   - 更新后的总数量

7. 更新bee-learning-progress.md

8. 如果还有更多对话，生成下一个子代理。
   如果未返回游标（已处理完所有对话），写入最终摘要并报告完成。

Step 4: Progress Reporting

步骤4：进度报告

After processing each week's worth of conversations (approximately), the subagent should report back to the main conversation with:

Summary of what was learned in that time period
Notable events or conversations
Any significant changes to the user profile

This keeps the user informed of progress without overwhelming them with details.

大约处理完每周的对话后，子代理应向主对话返回以下内容：

该时间段内学到的内容摘要
值得注意的事件或对话
用户档案的任何重大变更

这使用户能够了解进度，而不会被细节淹没。

Conversation List API

对话列表API

Fetch conversations with pagination:

bash

undefined

使用分页功能获取对话：

bash

undefined

First batch (most recent)

第一批次（最新对话）

bee conversations list --limit 100

Subsequent batches using cursor from previous response

使用上一次响应中的游标获取后续批次

bee conversations list --limit 100 --cursor <cursor_value>


The API returns:
- `conversations`: Array of conversation objects
- `cursor`: Pagination cursor for next batch (null when no more data)

bee conversations list --limit 100 --cursor <cursor_value>


API返回：
- `conversations`：对话对象数组
- `cursor`：用于下一批次的分页游标（无更多数据时为null）

Best Practices

最佳实践

File-based handoff: Always pass state between subagents via files (
```
bee-learning-summary.md
```
), never by copying large amounts of text into the task prompt. This preserves context window for actual processing.
Incremental updates: Each subagent should merge new information into
```
user.md
```
, not replace it. Use clear section headers and timestamps.
Progress tracking: Maintain
```
bee-learning-progress.md
```
as a log so you can resume if interrupted and track what's been processed.
Weekly summaries: Report meaningful summaries to the user periodically (e.g., after each week of conversations processed) rather than after every batch.
Graceful completion: When the cursor is null (no more conversations), write a final summary and notify the user that deep learning is complete.
Error handling: If a subagent fails, the next attempt can read the progress files and resume from where it left off.

基于文件的交接：始终通过文件（
```
bee-learning-summary.md
```
）在子代理之间传递状态，切勿将大量文本复制到任务提示中。这为实际处理保留了上下文窗口。
增量更新：每个子代理应将新信息合并到
```
user.md
```
中，而非替换它。使用清晰的章节标题和时间戳。
进度跟踪：维护
```
bee-learning-progress.md
```
作为日志，以便在中断后恢复并跟踪已处理的内容。
每周摘要：定期向用户报告有意义的摘要（例如，每处理完一周的对话后），而非每个批次处理完后都报告。
优雅完成：当游标为null（无更多对话）时，写入最终摘要并通知用户深度学习已完成。
错误处理：如果子代理失败，下一次尝试可以读取进度文件并从中断的位置恢复。

Example Progress File

示例进度文件

markdown

undefined

markdown

undefined

Bee Learning Progress

Bee学习进度

Session: 2024-01-15

会话：2024-01-15

14:30 - Started deep learning process
14:32 - Processed conversations from Jan 10-15 (87 conversations)
14:35 - Processed conversations from Jan 5-10 (92 conversations)
14:38 - Processed conversations from Dec 28 - Jan 5 (78 conversations)
14:40 - Week 1 summary reported to user
14:42 - Processed conversations from Dec 21-28 (65 conversations) ...
15:30 - Completed processing all conversations (1,247 total)

undefined

14:30 - 启动深度学习流程
14:32 - 处理了1月10日至15日的对话（87条）
14:35 - 处理了1月5日至10日的对话（92条）
14:38 - 处理了12月28日至1月5日的对话（78条）
14:40 - 向用户报告了第一周的摘要
14:42 - 处理了12月21日至28日的对话（65条） ...
15:30 - 完成了所有对话的处理（共1,247条）

undefined

When to Use Deep Learning

何时使用深度学习

Use this workflow when:

First establishing a relationship with a new user
User explicitly requests comprehensive analysis of their history
Building context for a long-term assistant relationship
User wants to understand patterns in their own conversations

Do not use for:

Quick questions about recent events (use
```
bee daily
```
or recent conversations)
Looking up specific facts (use
```
bee facts list
```
)
Finding a particular conversation (use
```
bee conversations list
```
and search)

在以下场景使用该工作流程：

首次与新用户建立关系时
用户明确要求对其历史记录进行全面分析时
为长期助手关系构建上下文时
用户想要了解其对话中的模式时

请勿在以下场景使用：

关于近期事件的快速问题（使用
```
bee daily
```
或近期对话）
查找特定事实（使用
```
bee facts list
```
）
查找特定对话（使用
```
bee conversations list
```
并搜索） ",

bee-cli

Original

Translation

Bee CLI

Bee CLI

About Bee

关于Bee

How Bee Works

Bee的工作原理

Privacy and Security

隐私与安全

When to Use This Skill

何时使用该技能

Real-Time Context (Use First!)

实时上下文（优先使用！）

Life Overview

生活概览

Installation

安装

Authentication

认证

Authentication Flow

认证流程

Commands

命令

Facts - Learn About the Owner

Facts - 了解用户

Conversations - Access Transcripts

Conversations - 访问对话记录

Listing Conversations

列出对话

Getting Full Conversation Details

获取完整对话细节

Search for Relevant Conversations

搜索相关对话

Journals - Voice Memos

Journals - 语音备忘录

Listing Journals

列出Journals

Getting Full Journal Details

获取完整Journal细节

Todos - Track Commitments

Todos - 跟踪承诺

Now - Real-Time Context

Now - 实时上下文

Daily Summaries

每日摘要

Periodic Sync - Real-Time Updates with bee changed

定期同步 - 使用bee changed获取实时更新

Cursor Handling

游标处理

Output from bee changed includes:

bee changed命令的输出包含：

After processing all changes successfully:

成功处理所有变更后：

Full Sync - Export Everything to Markdown

完全同步 - 将所有数据导出到Markdown

Common Workflows

常见工作流程

Quick Context - Understanding the Owner

快速上下文 - 了解用户

Finding Information from Past Conversations

从过往对话中查找信息

Export All Data for AI Context

导出所有数据用于AI上下文

Deep Learning About the Owner

深入了解用户

Overview

概述

File Structure

文件结构

Workflow Steps

工作流程步骤

Step 1: Initialize (Main Agent)

步骤1：初始化（主代理）

User Profile

用户档案

Basic Information

基本信息

Relationships

Periodic Sync - Real-Time Updates with
`bee changed`

定期同步 - 使用
`bee changed`
获取实时更新