跳到正文
TakoAPI
返回技能列表

manifest-build

由 brunobuddy 提供

AI & LLMs
233下载量由 clawskills.sh 提供
2星标
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Open-source LLM routing and cost tracking plugin.

描述

该技能的功能

Manifest is an OpenClaw plugin that routes each LLM request to the most cost-effective model using a 23-dimension scoring algorithm with under 2ms added latency. It tracks spend, token usage, and agent activity in a real-time dashboard, and supports hard spending caps with email alerts.

Routing and cost tracking would otherwise require custom code and separate dashboards; Manifest adds both as a no-config plugin with 300+ model coverage.

何时使用

  • Cutting monthly LLM costs by routing simple queries to cheaper models
  • Checking which model is consuming the most budget this week
  • Setting a hard spending cap before a client project starts
  • Asking the agent mid-conversation how many tokens it has used today
  • Diagnosing rate limit errors through the message log and error filters

示例工作流

输入

User asks: how much have I spent this week and which model cost the most?

智能体
  1. 1

    Invokes manifest_costs tool with period set to "week"

  2. 2

    Retrieves cost breakdown by model in USD

  3. 3

    Identifies the highest-cost model from the returned data

  4. 4

    Summarizes total spend and top model for the user

输出

A cost breakdown listing total weekly spend and the most expensive model, pulled from the agent's own usage data

前置要求

  • Manifest API key (mnfst_*) — sign up at app.manifest.build, create an agent, and copy the key

安装

clawhub install brunobuddy/manifest-build

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接