Bedrock AgentCore Runtime for agents
AgentCore Runtime is Amazon Bedrock's serverless environment for deploying AI agents. It works with CrewAI, LangGraph, LlamaIndex, and Strands Agents.
Key features
- Deploys agents on AgentCore Runtime, a serverless environment with isolated sessions
- Run agents from LangChain, OpenAI, Claude, Strands, or custom frameworks
- Connect agents to MCP servers, knowledge bases, APIs, and Lambda
- Handle authentication and access control for agent tool calls
- Show agent steps, tool calls, and where they went off track
- Test agent variations against real traffic
- Category
- Agents
- Who it's for
- Developers building production AI agents.
- Tags
- awsbedrockragtool-callingserverlesshostingauthtesting
- Website
- aws.amazon.com
- Listed
- 2026-10-08
Frequently asked questions
What is Amazon Bedrock AgentCore used for?
Serverless AgentCore Runtime in Amazon Bedrock for deploying and scaling AI agents. Typical uses: deploys agents on AgentCore Runtime, a serverless environment with isolated sessions; run agents from LangChain, OpenAI, Claude, Strands, or custom frameworks; connect agents to MCP servers, knowledge bases, APIs, and Lambda.
Related news
Related in Agents
See all →- Agensh Self-organized multi-agent harness. Agents claim sub-tasks and merge progress without a central orchestrator. MIT.
- Agentic Batch Changes Describe a change in plain language. The agent scopes it across your indexed codebase and tracks it through to merge.
- Agno Python framework for agents, formerly Phidata.
- Alter Privileged access for AI agents. Vaulted credentials, per-call policy, and an audit log. Free tier is 10,000 API calls a month.
- AutoGen Microsoft's framework for multi-agent conversations.
- Browser Use Library for letting an agent drive a browser.