A self-hosted dashboard for monitoring OpenClaw API spending and token usage with real-time budget alerts.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install clawmeter
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install clawmeter using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is ClawMeter?
ClawMeter is a self-hosted cost tracking dashboard that transforms raw session logs into actionable financial insights, making it a vital part of your Openclaw Skills library. It calculates token usage and API costs in real-time, providing developers and teams with the visibility needed to optimize model selection and prevent budget overruns.
By integrating directly with your agent workspace, this skill allows for natural language queries about spending and provides a visual dashboard for deep-dive analytics. Whether you are managing a single personal agent or a fleet of production tools, this utility ensures your AI spending remains predictable and transparent.
ClawMeter Use Cases
- Personal budget management to keep monthly AI costs under a specific threshold through automated monitoring.
- Team cost allocation for shared OpenClaw instances to identify which agents or projects are the most expensive.
- Model selection optimization by comparing cost-per-message and token usage across different LLM providers.
- Production monitoring to catch cost spikes immediately and prevent runaway spending in automated environments.
How ClawMeter Works
- The skill monitors the OpenClaw agents directory to detect new session log entries in real-time.
- It ingests usage data including input tokens, output tokens, and model identifiers into a local SQLite database.
- Costs are calculated using a built-in pricing engine that tracks rates for various AI providers and models.
- A web-based dashboard serves real-time analytics and a REST API allows agents to report spending directly in the chat.
- The system automatically compares current spending against configured daily and monthly limits to trigger alerts.
ClawMeter Setup
- Clone the repository: Navigate to your workspace and download the skill source.
cd ~/.openclaw/workspace
git clone https://github.com/yourusername/clawmeter.git
cd clawmeter
- Install dependencies: Install the required Node.js environment.
npm install
- Configuration: Set up your environment variables for paths and budget limits.
cp .env.example .env
# Edit .env to customize paths and limits
- Initialize and Start: Ingest existing session logs and launch the local dashboard.
npm run ingest
npm start
ClawMeter Data Schema & Taxonomy
ClawMeter organizes data using a local SQLite database for maximum efficiency and privacy:
- Sessions Table: Records individual session IDs, associated agents, specific models used, and total calculated costs.
- Daily Aggregates: Summarizes input and output tokens, message counts, and total spending on a per-day basis.
- Model Taxonomy: Categorizes usage by provider (Anthropic, OpenAI, etc.) and specific model tier for granular reporting.
- Alert History: Logs budget threshold breaches, including the timestamp and the notification method used.
ClawMeter Advanced Features
- Proactive budget alerts delivered via Telegram notifications or Email via SMTP.
- Natural language integration allowing OpenClaw agents to answer questions like "How much have I spent today?"
- Custom model pricing support through a configurable pricing manifest for private or fine-tuned models.
- Comprehensive REST API for exporting data to external business intelligence tools or custom scripts.
- Automated data management including background log ingestion and optional archival of historical records.
SKILL.md
Loading
Related Openclaw Skills
Improve Skill: The Meta-Skill
A meta-skill designed to evaluate and optimize other skills by identifying gaps in logic, codebase fit, and output quality.
Ghost Catalog
An intelligent file management system that implements semantic headers and a SQLite database to organize, tag, and validate project assets.
Ghost Catalog
Ghost Catalog provides a semantic file header system and SQLite database to scan, tag, and organize files within any workspace for better discoverability and compliance.
Lobster Trap
A shared digital whiteboard for synchronized management of notes, code snippets, and key labels via API.
Agent Chat
A specialized messaging protocol that enables multiple Openclaw Skills instances to coordinate and exchange data through a shared JSON queue.
Kiro Intercom
Kiro Intercom enables seamless communication and coordination between multiple agent instances through a shared markdown-based chat interface.
Featured*
