Claude Skill

aws-samples/sample-host-openclaw-on-amazon-bedrock-agentcore

Explore a sample Python implementation for hosting the OpenClaw skill on Amazon Bedrock Agent Core. Learn to deploy AI agents with AWS for scalable, intelligent applications.

Overview

Stars164
Forks48
LanguagePython
Last pushed2026-05-23
Last synced2026-06-24
View on GitHub

Repository

Owneraws-samples
Repositorysample-host-openclaw-on-amazon-bedrock-agentcore
Full nameaws-samples/sample-host-openclaw-on-amazon-bedrock-agentcore
Repo ID1,162,268,824

Install this Skill

git clone https://github.com/aws-samples/sample-host-openclaw-on-amazon-bedrock-agentcore.git

Registry

Typeopenclaw_skill
Quality score85/100
Verificationreadme_parsed
Last verified2026-06-24
Platforms
ClaudeOpenClaw
Capabilities
browserpdfmemorysearchimagevideoterminalworkflow
Detected files
README.mddocsrequirements.txttests
Config keys
YOUR_TELEGRAM_BOT_TOKENURLAPI_URLWEBHOOK_SECRETTELEGRAM_TOKENYOUR_TELEGRAM_USER_IDYOUR_BOT_TOKENTOKENSECRETYOUR_MEMBER_IDUSER_IDRUNTIME_ID
Install methods
  • git clone https://github.com/aws-samples/sample-host-openclaw-on-amazon-bedrock-agentcore.git
  • pip install -r requirements.txt
  • pip install bedrock-agentcore-toolkit
  • npx promptfoo@latest view

Summary

This repository provides a sample implementation for hosting the OpenClaw skill on Amazon Bedrock Agent Core, enabling developers to integrate AI-powered agent capabilities into their applications using AWS services.

Key features

  • Sample code for hosting OpenClaw on Amazon Bedrock Agent Core
  • Python-based implementation for easy integration
  • Leverages AWS Bedrock for scalable AI agent deployment
  • Demonstrates agent core configuration and management
  • Open-source reference for building custom AI agents

Use cases

  • Deploying AI agents for customer support automation
  • Building intelligent assistants for enterprise workflows
  • Integrating AI-powered decision-making into applications
  • Prototyping and testing agent-based solutions on AWS
  • Learning how to use Amazon Bedrock Agent Core with custom skills

README excerpt

# OpenClaw on AWS Bedrock AgentCore [![License: MIT-0](https://img.shields.io/badge/License-MIT--0-blue.svg)](LICENSE) [![Status: Experimental](https://img.shields.io/badge/Status-Experimental-orange.svg)]() [![AWS CDK](https://img.shields.io/badge/AWS%20CDK-v2-yellow.svg)]() > **Experimental** — This project is provided for experimentation and learning purposes only. It is **not intended for production use**. APIs, architecture, and configuration may change without notice. Deploy an AI-powered multi-channel messaging bot (Telegram, Slack) on AWS Bedrock AgentCore Runtime using CDK. ## Table of Contents - [Architecture](#architecture) - [Prerequisites](#prerequisites) - [Quick Start](#quick-start) - [Project Structure](#project-structure) - [Configuration](#configuration) - [Channel Setup](#channel-setup) - [How It Works](#how-it-works) - [Operations](#operations) - [Troubleshooting](#troubleshooting) - [Known Limitations](#known-limitations) - [Gotchas](#gotchas) - [Cleanup](#cleanup) - [Security](#security) - [Security Testing](#security-testing) - [License](#license) OpenClaw runs as **per-user serverless containers** on AgentCore Runtime. A Router Lambda handles webhook ingestion from Telegram and Slack, resolves user identity via DynamoDB, and invokes per-user AgentCore sessions. Each user gets their own microVM with workspace persistence (`.openclaw/` directory synced to S3). The agent has built-in tools (web, filesystem, runtime, sessions, automation), custom skills for file storage and cron scheduling, and **EventBridge-based cron scheduling** for recurring tasks. Users can send **text and images** — photos sent via Telegram or Slack are downloaded by the Router Lambda, stored in S3, and passed to Claude as multimodal content via Bedrock's ConverseStream

Topics

No topics yet.

Explore more

Data from GitHub. Synced on 2026-06-24