agent-pulse

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Agent Pulse

Purpose

用途

Use the installed

agent-pulse

CLI as the source of truth for local AI-agent activity. The PyPI package is

agentpulse-cli

, while the command remains

agent-pulse

. Prefer running commands and summarizing their output over reading the Agent Pulse source code.

Always enable UTF-8 on Windows before running commands because Agent Pulse output contains emoji and box drawing:

powershell

$env:PYTHONUTF8='1'
$env:PYTHONIOENCODING='utf-8'

agent-pulse

is not on PATH, install the PyPI package or try running from a local project checkout:

powershell

pip install agentpulse-cli

powershell

python -m agent_pulse.cli --version

将已安装的

agent-pulse

CLI作为本地AI-agent活动的权威数据源。PyPI包名为

agentpulse-cli

，而命令仍为

agent-pulse

。优先选择运行命令并总结其输出，而非读取Agent Pulse的源代码。

在Windows上运行命令前务必启用UTF-8，因为Agent Pulse的输出包含表情符号和方框绘制字符：

powershell

$env:PYTHONUTF8='1'
$env:PYTHONIOENCODING='utf-8'

如果

agent-pulse

不在PATH中，请安装PyPI包或尝试从本地项目检出目录运行：

powershell

pip install agentpulse-cli

powershell

python -m agent_pulse.cli --version

Common Requests

常见请求

Use this command selection table first:

User wants	Run
Current status	`agent-pulse status --json`
Full dashboard	`agent-pulse --json` or `agent-pulse --no-banner`
Demo data	`agent-pulse demo --json`
Setup diagnosis	`agent-pulse doctor --json`
Recent sessions	`agent-pulse --json --hours 24 --limit 20`
Top expensive sessions	`agent-pulse top --sort cost --json`
Model cost analysis	`agent-pulse models --json`
Cost savings	`agent-pulse optimize --json`
Budget status	`agent-pulse budget --json`
Cost forecast	`agent-pulse forecast --json`
Health/CI check	`agent-pulse health --json`
Search sessions	`agent-pulse search "<query>" --json`
Export report	`agent-pulse export -f markdown` or `agent-pulse export-html`
MCP tools	`agent-pulse mcp --list-tools`

If the installed command lacks an option, run

agent-pulse <command> --help

and adapt.

首先参考以下命令选择表：

用户需求	运行命令
当前状态	`agent-pulse status --json`
完整仪表盘	`agent-pulse --json` 或 `agent-pulse --no-banner`
演示数据	`agent-pulse demo --json`
设置诊断	`agent-pulse doctor --json`
近期会话	`agent-pulse --json --hours 24 --limit 20`
高成本会话排行	`agent-pulse top --sort cost --json`
模型成本分析	`agent-pulse models --json`
成本优化建议	`agent-pulse optimize --json`
预算状态	`agent-pulse budget --json`
成本预测	`agent-pulse forecast --json`
健康/CI检查	`agent-pulse health --json`
会话搜索	`agent-pulse search "<query>" --json`
导出报告	`agent-pulse export -f markdown` 或 `agent-pulse export-html`
MCP工具	`agent-pulse mcp --list-tools`

如果已安装的命令缺少某个选项，请运行

agent-pulse <command> --help

并调整使用方式。

Workflow

工作流程

Start with
```
agent-pulse doctor --json
```
if the user asks why data is missing or setup may be broken.
Use JSON output whenever possible, then summarize the fields that matter: sessions, tokens, tools, model breakdown, source breakdown, estimated cost, warnings.
Use time filters for scoped questions:

powershell

agent-pulse status --json --hours 24
agent-pulse --json --hours 168 --limit 50

Use platform filters when the user asks about a specific agent system:

powershell

agent-pulse --json -P codex
agent-pulse --json -P claude
agent-pulse --json -P hermes
agent-pulse --json -P deepseek
agent-pulse --json -P openclaw

For cost questions, pair summary and model views:

powershell

agent-pulse status --json --hours 24
agent-pulse models --json --hours 24
agent-pulse optimize --json

For trend questions, use forecast/history/compare:

powershell

agent-pulse forecast --json
agent-pulse history --json
agent-pulse compare --json

如果用户询问数据缺失或设置可能存在问题的原因，先运行
```
agent-pulse doctor --json
```
。
尽可能使用JSON输出，然后总结关键字段：会话、token、工具、模型细分、来源细分、估算成本、警告信息。
针对范围明确的问题，使用时间过滤器：

powershell

agent-pulse status --json --hours 24
agent-pulse --json --hours 168 --limit 50

当用户询问特定agent系统时，使用平台过滤器：

powershell

agent-pulse --json -P codex
agent-pulse --json -P claude
agent-pulse --json -P hermes
agent-pulse --json -P deepseek
agent-pulse --json -P openclaw

针对成本相关问题，结合概览和模型视图：

powershell

agent-pulse status --json --hours 24
agent-pulse models --json --hours 24
agent-pulse optimize --json

针对趋势相关问题，使用预测/历史/对比功能：

powershell

agent-pulse forecast --json
agent-pulse history --json
agent-pulse compare --json

Interpreting Results

结果解读

Treat
```
total_cost_usd
```
as an estimate based on Agent Pulse's local model pricing table.
Report both cost and token volume; low-cost models can still have very high token usage.
Distinguish sources such as
```
codex
```
,
```
claude
```
,
```
hermes
```
,
```
deepseek
```
, and
```
openclaw
```
.
Mention if
```
doctor
```
reports missing optional sources, missing
```
dev_root
```
, or optional web dependencies.
If no sessions appear, check
```
doctor
```
, then try a wider time window such as
```
--hours 168
```
.

将
```
total_cost_usd
```
视为基于Agent Pulse本地模型定价表的估算值。
同时报告成本和token用量；低成本模型仍可能有极高的token使用量。
区分来源，如
```
codex
```
、
```
claude
```
、
```
hermes
```
、
```
deepseek
```
和
```
openclaw
```
。
如果
```
doctor
```
报告缺少可选来源、缺失
```
dev_root
```
或可选Web依赖项，请提及这些情况。
如果没有显示任何会话，请检查
```
doctor
```
的结果，然后尝试更宽的时间窗口，例如
```
--hours 168
```
。

Reports

报告

For a short human-readable answer, run JSON commands and summarize.

For artifacts, prefer:

powershell

agent-pulse report --period daily
agent-pulse export -f markdown
agent-pulse export-html

Do not invent exact savings or costs. Use the CLI output.

如需简短的易读答案，运行JSON命令并总结结果。

如需生成报告文件，优先选择：

powershell

agent-pulse report --period daily
agent-pulse export -f markdown
agent-pulse export-html

不要编造确切的节省金额或成本数据，以CLI输出为准。

MCP

Use MCP mode when the user wants other AI clients to query Agent Pulse:

powershell

agent-pulse mcp --list-tools
agent-pulse mcp

When explaining MCP, mention that it exposes tools such as status, forecast, top sessions, model analytics, optimization, health, search, and leaderboard.

当用户希望其他AI客户端查询Agent Pulse时，使用MCP模式：

powershell

agent-pulse mcp --list-tools
agent-pulse mcp

解释MCP时，需提及它会暴露多种工具，如状态查询、成本预测、高成本会话排行、模型分析、优化建议、健康检查、会话搜索和排行榜。

Local Helper

本地助手

This skill includes

scripts/run_agent_pulse_snapshot.py

, which runs a compact set of JSON-friendly Agent Pulse checks and prints a combined summary:

powershell

python scripts/run_agent_pulse_snapshot.py

本技能包含

scripts/run_agent_pulse_snapshot.py

，它会运行一组简洁的、支持JSON的Agent Pulse检查，并打印综合总结：

powershell

python scripts/run_agent_pulse_snapshot.py