aws-agentcore-langgraph
Deploy production LangGraph agents on AWS Bedrock AgentCore. Use for (1) multi-agent systems with orchestrator and specialist agent patterns, (2) building stateful agents with persistent cross-session memory, (3) connecting external tools via AgentCore Gateway (MCP, Lambda, APIs), (4) managing shared context across distributed agents, or (5) deploying complex agent ecosystems via CLI with production observability and scaling.
Why use this skill?
Deploy production-ready LangGraph agents on AWS Bedrock with this OpenClaw skill. Manage multi-agent orchestration, persistent memory, and secure gateway tools for enterprise AI.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/killerapp/aws-agentcore-langgraphWhat This Skill Does
The aws-agentcore-langgraph skill provides an integrated environment for building, orchestrating, and deploying production-grade LangGraph agents on AWS Bedrock. It bridges the gap between local prototype development and enterprise-scale deployment by providing a specialized framework to manage multi-agent systems, persistent memory, and external tool gateways. Whether you are building an orchestrator that delegates to specialist agents or implementing a sophisticated stateful workflow, this skill simplifies the complex infrastructure required for observability, scaling, and cross-session context management within the AWS ecosystem.
Installation
To get started, ensure you have your environment prepared for AWS development. Run the following commands to install the required libraries and the AgentCore CLI:
pip install bedrock-agentcore bedrock-agentcore-starter-toolkit langgraph
uv tool install bedrock-agentcore-starter-toolkit
For local development, utilize agentcore dev for hot-reloading. When ready for production, use the agentcore launch command to deploy your agent as a containerized service.
Use Cases
- Multi-Agent Orchestration: Design complex workflows where a primary orchestrator coordinates tasks across multiple specialist agents (e.g., customer service, e-commerce, or healthcare).
- Stateful Memory Management: Utilize Short-Term (STM) and Long-Term (LTM) memory to maintain consistent state across sessions, allowing agents to remember user preferences or past decisions over extended periods.
- Enterprise Tool Connectivity: Connect your agents to external systems such as REST APIs, Lambda functions, or MCP (Model Context Protocol) servers via the secure AgentCore Gateway.
- Production Scaling: Easily deploy your agents with built-in observability tools, scaling them across AWS regions while maintaining strict control over deployment configurations.
Example Prompts
- "Initialize a new LangGraph project with a customer service orchestrator that uses a tools_condition to route between a database lookup specialist and a final responder."
- "Configure my deployed agent to use the persistent memory client, ensuring that session history is stored across multiple user interactions."
- "Launch the current script as a production container in us-east-1 and verify the health check using the local invocation tool."
Tips & Limitations
- Memory Consistency: Keep in mind that the memory subsystem has approximately a 10s window for eventual consistency after writes.
- Gateway Deployment: Always deploy your Gateway stack prior to calling external production tools to ensure environment variables are correctly synchronized.
- State Management: When building stateful graphs, ensure your TypedDict state definitions are clean to prevent serialization errors during production deployment.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-killerapp-aws-agentcore-langgraph": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, external-api, code-execution
Related Skills
agentskills-io
Create, validate, and publish Agent Skills following the official open standard from agentskills.io. Use when (1) creating new skills for AI agents, (2) validating skill structure and metadata, (3) understanding the Agent Skills specification, (4) converting existing documentation into portable skills, or (5) ensuring cross-platform compatibility with Claude Code, Cursor, GitHub Copilot, and other tools.
baml-codegen
Use when generating BAML code for type-safe LLM extraction, classification, RAG, or agent workflows - creates complete .baml files with types, functions, clients, tests, and framework integrations from natural language requirements. Queries official BoundaryML repositories via MCP for real-time patterns. Supports multimodal inputs (images, audio), Python/TypeScript/Ruby/Go, 10+ frameworks, 50-70% token optimization, 95%+ compilation success.
adversarial-coach
Adversarial implementation review based on Block's g3 dialectical autocoding research. Use when validating implementation completeness against requirements with fresh objectivity.
chain-of-density
Iteratively densify text summaries using Chain-of-Density technique. Use when compressing verbose documentation, condensing requirements, or creating executive summaries while preserving information density.
copywriter
Write compelling UX copy, marketing content, and product messaging. Use when writing button labels, error messages, landing pages, emails, CTAs, empty states, tooltips, or any user-facing text.