원클릭으로
agentsight
// 通过命令行或 Dashboard(前端) 查询 AgentSight 平台的 token 消耗数据、token 节省(优化)数据、审计事件和会话中断事件。当用户询问 token 用量、花费、消耗趋势、token 节省、优化效果、LLM 调用、进程行为审计,或询问会话中断、Agent 异常、LLM 错误等中断事件时使用此技能。
// 通过命令行或 Dashboard(前端) 查询 AgentSight 平台的 token 消耗数据、token 节省(优化)数据、审计事件和会话中断事件。当用户询问 token 用量、花费、消耗趋势、token 节省、优化效果、LLM 调用、进程行为审计,或询问会话中断、Agent 异常、LLM 错误等中断事件时使用此技能。
工作区快照管理。用户说"保存一下"、"存个快照"时创建 checkpoint; 说"回滚"、"撤销"、"恢复到之前"时 rollback;说"删掉快照"时 delete; 说"看看快照"、"有哪些快照"时 list;说"查看快照状态"、"查看快照剩余空间"时 status。
Skill 安全状态查看、快速扫描认证与可选深度扫描。支持用户主动查看或扫描单个/全部 Skill;当用户要求 agent 安装 Skill 且安装成功后,必须自动对最终本地目录执行快速扫描认证。
One-click installation and configuration of Hermes Agent by Nous Research. Handles installing Hermes from scratch, adding LLM providers (OpenRouter, Anthropic, OpenAI, z.ai/GLM, Kimi, DeepSeek, Alibaba Qwen, Ollama, etc.), setting up messaging platforms (Telegram, Discord, Slack, DingTalk, Feishu/Lark, Weixin, WeCom), installing Hermes Workspace web UI, and migrating from OpenClaw. Use when the user asks about installing Hermes, setting up a provider, configuring a messaging platform, adding a bot, or any Hermes setup task.
Search, install, uninstall, update and manage agent skills. Use when the user asks to find/search/install/uninstall/update/list/explore skills, asks "how do I do X" or "find a skill for X", or wants to extend agent capabilities in a specific domain.
Open, create, read, analyze, edit, or validate Excel/spreadsheet files (.xlsx, .xlsm, .csv, .tsv). Use when the user asks to create, build, modify, analyze, read, validate, or format any Excel spreadsheet, financial model, pivot table, or tabular data file. Covers: creating new xlsx from scratch, reading and analyzing existing files, editing existing xlsx with zero format loss, formula recalculation and validation, and applying professional financial formatting standards.
Install and configure Claude Code on RPM-based Linux systems (e.g., Alibaba Cloud Linux) with multiple fallback methods (native installer, npm, nvm+npm). Includes DashScope/Qwen API configuration template. Use when the user asks to install Claude Code CLI, set up Claude Code CLI, or configure Claude Code with a custom API endpoint on RPM-based Linux systems.
| name | agentsight |
| description | 通过命令行或 Dashboard(前端) 查询 AgentSight 平台的 token 消耗数据、token 节省(优化)数据、审计事件和会话中断事件。当用户询问 token 用量、花费、消耗趋势、token 节省、优化效果、LLM 调用、进程行为审计,或询问会话中断、Agent 异常、LLM 错误等中断事件时使用此技能。 |
AgentSight 提供 Web Dashboard(前端) 用于可视化查看 token 消耗和会话历史。
访问方式:
http://<server-ip>:7396(需确保安全组已开放该端口)http://127.0.0.1:7396功能:
启动服务:
# 如果服务未运行,启动它
sudo systemctl start agentsight
# 查看服务状态
sudo systemctl status agentsight
| 命令 | 说明 |
|---|---|
/usr/local/bin/agentsight token --period today | 今天消耗 |
/usr/local/bin/agentsight token --period yesterday | 昨天消耗 |
/usr/local/bin/agentsight token --hours 3 | 最近 3 小时 |
/usr/local/bin/agentsight token --period today --compare | 今天 vs 昨天对比 |
今天共消耗 125,000 tokens,比昨天(98,000)增长 27%。
输入: 125,000 | 输出: 85,000
| 命令 | 说明 |
|---|---|
/usr/local/bin/agentsight audit | 最近 24 小时事件 |
/usr/local/bin/agentsight audit --last 48 | 最近 48 小时 |
/usr/local/bin/agentsight audit --pid 12345 | 指定进程 |
/usr/local/bin/agentsight audit --type llm | 仅 LLM 调用 |
/usr/local/bin/agentsight audit --type process | 仅进程行为 |
/usr/local/bin/agentsight audit --summary | 汇总统计 |
/usr/local/bin/agentsight audit --summary --last 72 | 最近 72 小时汇总 |
/usr/local/bin/agentsight audit --json | JSON 格式 |
汇总输出:
=== Audit Summary (last 24 hours) ===
LLM calls: 42
Process actions: 128
Providers:
OpenAI: 35 calls
Anthropic: 7 calls
Top commands:
python agent.py: 25 times
node server.js: 17 times
事件列表(JSON):
{"event_type":"llm_call","pid":1234,"comm":"python",
"extra":{"provider":"OpenAI","model":"gpt-4o","input_tokens":1500,"output_tokens":800}}
| 类型 | 字段 |
|---|---|
llm_call | provider, model, input_tokens, output_tokens, request_path, response_status, is_sse |
process_action | filename, args, exit_code |
数据库:/var/log/sysak/.agentsight/interruption_events.db
中断类型:llm_error、sse_truncated、context_overflow、agent_crash、token_limit
严重级别:critical > high > medium > low
使用 /usr/local/bin/agentsight interruption --help 查看所有子命令和参数。
GET /api/token-savings — 参数:start_ns、end_ns、agent_name;数据源:genai_events.db + ~/.tokenless/stats.db
GET /api/agent-names — 获取可选的 agent_name 值列表
/var/log/sysak/.agentsight/agentsight.db(SQLite)