Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

manifest-build

bởi brunobuddy

AI & LLMs
233Lượt tải do clawskills.sh công bố
2Sao
0Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Open-source LLM routing and cost tracking plugin.

Mô tả

Kỹ năng này làm gì

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.

Khi nào nên dùng

  • 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

Quy trình ví dụ

ĐẦU VÀO

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

AGENT
  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

ĐẦU RA

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

Yêu cầu

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

Cài đặt

clawhub install brunobuddy/manifest-build

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết