Passive Cost Memory for Agent Development

Name: Passive Cost Memory for Agent Development
Author: RaleighSF

@RaleighSF

Passive Cost Memory for Agent Development について

Burnwatch detects every paid service in your project, tracks spend across 14 AI-native tools (Anthropic, OpenAI, Vercel, Supabase, Stripe, Scrapfly, Browserbase, and more), and exposes real-time cost data via MCP tools — so any LLM can factor budget into its recommendations. Four

#cost-tracking #spend #billing #finops #budget #saas #developer-tools #agent-development #anthropic #openai #vercel #claude-code

基本情報

カテゴリ

AI とエージェント

トランスポート

stdio

公開者

RaleighSF

投稿者

Raleigh Murch

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "burnwatch": {
      "command": "node",
      "args": [
        "node_modules/burnwatch/dist/mcp-server.js"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Passive Cost Memory for Agent Development?

Passive Cost Memory for Agent Development (burnwatch) is a cost monitoring tool for agent projects that provides spend overviews, service deep dives, and paid-service scans across 14 supported services like Anthropic, OpenAI, and AWS.

How to use Passive Cost Memory for Agent Development?

Install via npm install burnwatch, then add a configuration entry to your MCP client with the command node and args ["node_modules/burnwatch/dist/mcp-server.js"].

Key features of Passive Cost Memory for Agent Development

Full project spend overview with budget alerts
Deep dive on any service with gotchas and alternatives
Scan a project for all paid services
Browse a registry of 14 supported services
Confidence badges (LIVE, CALC, EST, BLIND) indicate data quality

Use cases of Passive Cost Memory for Agent Development

Monitor total project spending and catch budget overruns early
Analyze cost breakdown for individual services to optimize spending
Discover all paid services used across a project
Get alternatives and gotchas for each supported service

FAQ from Passive Cost Memory for Agent Development

What services does it support?

Anthropic, OpenAI, Vercel, Supabase, Stripe, Scrapfly, Browserbase, Upstash, Resend, Inngest, PostHog, Google Gemini, Voyage AI, and AWS, with more coming.

How are spend figures categorized?

Each spend figure has a confidence badge: LIVE (real billing API data), CALC (fixed monthly cost, projected), EST (estimated from usage patterns), or BLIND (detected but not yet tracked).

How do I install it?

Run npm install burnwatch and add the MCP server configuration to your client as shown in the README.

What tools does it provide?

Four tools: get_spend_brief, get_service_spend, detect_paid_services, and list_registry_services.

How do I scan a project for paid services?

Use the detect_paid_services tool to scan a project and identify all paid services it uses.

「AI とエージェント」の他のコンテンツ

欢迎来到智言平台

Shy2593666979

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

797