serithemage/serverless-openclaw

Registry

Summary

Run OpenClaw AI agent on-demand on AWS serverless infrastructure with Web UI and Telegram interfaces. Cost target ~$1/month.

Key features

• Serverless AWS deployment for on-demand AI agent execution
• Web UI and Telegram bot interfaces included
• Cost-efficient design targeting ~$1/month
• Built with TypeScript for reliability and maintainability

Use cases

• Run AI agents without managing servers
• Integrate AI agent capabilities into Telegram workflows
• Experiment with OpenClaw on a low-cost budget

README excerpt

# Serverless OpenClaw [](LICENSE) [](https://www.typescriptlang.org/) [](https://aws.amazon.com/cdk/) [](https://nodejs.org/) [](#contributing) [](#) > **⚠️ Alpha — Development in Progress** > > This project is in an early alpha stage and has **not been fully tested** in production environments. > It involves LLM API calls, which can incur **unexpected costs** and may expose **security risks** if misconfigured. > **Use for development and testing purposes only.** The authors are not responsible for any costs or damages arising from its use. An open-source project that runs [OpenClaw](https://github.com/openclaw/openclaw) on-demand on AWS serverless infrastructure, providing a web UI and Telegram as interfaces. Inspired by the architecture of [Cloudflare MoltWorker](https://github.com/cloudflare/moltworker), this project delivers an independent serverless solution optimized for the AWS ecosystem. ## Key Features - **Serverless On-demand Execution**: Minimizes cost (~$1/month) with dual compute — Lambda Container (default, zero idle cost) or ECS Fargate Spot (fallback) - **Lambda Agent Runtime**: Runs OpenClaw directly in Lambda with 1.35s cold start, $0 idle cost, and S3 session persistence - **Predictive Pre-Warming**: Optional EventBridge-scheduled container pre-warming eliminates cold start during active hours (0s first response) - **Web Chat UI**: Real-time chat interface buil

Topics

No topics yet.