--- title: "AgentCore Runtime — serverless hosting for any-framework agents" date: 2026-05-26 service: "Amazon Bedrock AgentCore" component: "Runtime" tags: [agentcore, runtime, serverless, strands, langgraph, mcp, sessions, arm64, container] source: https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.html verified_on: 2026-05-26 url: https://vanemmerik.ai/aws-ai/2026-05-26.html --- # AWS Bedrock & AgentCore · Tip of the Day · 2026-05-26 ## AgentCore Runtime — serverless hosting for any-framework agents **AgentCore Runtime** is the secure, serverless execution environment at the centre of Amazon Bedrock AgentCore. Bring an agent written in any framework — Strands, LangGraph, LlamaIndex, Google ADK, OpenAI Agents — pointed at any foundation model, and Runtime gives it isolated sessions, fast cold starts, and a long enough timeout to actually finish the job. $ npm install -g @aws/agentcore $ agentcore create --name MyAgent --defaults $ agentcore deploy ≈ 6 min read · Bedrock AgentCore · Inaugural drop --- ## 01 · Why AgentCore Runtime exists Hosting an agent is not the same problem as hosting a web service. Agents hold conversation state, call tools, stream tokens for minutes at a time, and have to be isolated from each other so one user's session never sees another's. AWS Lambda is too short for long reasoning loops; ECS or EKS gives you a cluster to operate; rolling your own EC2 means rolling your own session manager and identity layer. **AgentCore Runtime** removes that whole layer. You give it a container image (or let the CLI build one for you), and it runs your agent behind an HTTP endpoint with these guarantees baked in: - **True session isolation.** Each invocation runs in its own session context; one user's conversation never crosses into another's. - **Fast cold starts** for chat-style real-time interactions, plus extended runtime for asynchronous background agents — up to **8 hours** per session (well past Lambda's 15-minute ceiling). - **Framework-neutral.** Strands, LangChain/LangGraph, Google ADK, OpenAI Agents — Runtime doesn't care. - **Model-neutral.** Anthropic Claude, Amazon Nova, OpenAI, Gemini, Meta Llama, Mistral — pick whichever your agent needs. - **Protocol-neutral.** HTTP for chat, MCP for tool servers, A2A for agent-to-agent. > **The shift.** Runtime is the missing primitive between "Lambda for > short requests" and "a Kubernetes cluster you operate yourself." You > write the agent code; AWS runs the agent lifecycle. --- ## 02 · The fastest path: the AgentCore CLI The official path from "no code" to "deployed agent" is the AgentCore CLI — distributed as an npm package, scaffolds a project, deploys via CDK, and invokes the running endpoint. # Prereqs: Node 20+, Python 3.10+, AWS CDK installed, AWS creds configured npm install -g @aws/agentcore agentcore --help # Scaffold a new Strands agent on Bedrock with no memory agentcore create --name MyAgent --defaults cd MyAgent # Test locally — opens the agent inspector in your browser agentcore dev # Deploy to AWS via CDK agentcore deploy # Invoke it agentcore invoke "Hello, tell me a joke" The `agentcore create` flags worth knowing: - `--framework` — `Strands`, `LangChain_LangGraph`, `GoogleADK`, `OpenAIAgents`. - `--protocol` — `HTTP` (default), `MCP`, `A2A`. - `--build` — `CodeZip` (default) or `Container`. Use `Container` when you need extra system dependencies in the image. - `--model-provider` — `Bedrock`, `Anthropic`, `OpenAI`, `Gemini`. - `--memory` — `none`, `shortTerm`, `longAndShortTerm`. Wires up AgentCore Memory automatically. The scaffold drops you into a project with three things that matter: `agentcore/agentcore.json` (project + agent config), `app/MyAgent/main.py` (your agent code), and `aws-targets.json` (account + region targets). --- ## 03 · The container contract If you bring your own container (the "no CLI" path), Runtime expects a small contract from the image — and the failure modes when you get it wrong are obvious enough to be worth memorising. | Requirement | Why | | --- | --- | | **ARM64** image (`linux/arm64`) | AgentCore Runtime is Graviton. An x86 image fails to start with `exec /bin/sh: exec format error`. | | HTTP listener on `:8080` | Runtime's data-plane invokes your container over HTTP at port 8080. | | `POST /invocations` endpoint | The request path Runtime calls with each user prompt. | | `GET /ping` endpoint | Liveness check. Return 200 OK; anything else and Runtime declares the instance unhealthy. | | `runtimeSessionId` available in request | Use it to tag your downstream resources so multiple concurrent sessions don't collide. | The starter Dockerfile from the docs uses `FROM public.ecr.aws/docker/library/python:3.12-slim` with `--platform=linux/arm64` on the build, then `pip install` for the agent framework plus FastAPI/Uvicorn for the HTTP layer. The CLI's `--build Container` mode generates this for you. --- ## 04 · Sessions, endpoints, versions Three concepts you'll see repeatedly: - **Runtime** — the deployed agent itself. Configuration is immutable per **version**; every time you push a change, AgentCore creates a new version automatically. - **Endpoint** — a named, mutable pointer to a version. The `DEFAULT` endpoint advances to the newest version on every deploy. Create additional endpoints (e.g. `production`) and pin them to a specific version when you need stability. - **Session** — an isolated execution context for one conversation. Identified by `runtimeSessionId`. A session can stay open for up to **8 hours**; cold starts on a new session are designed for chat-level latency. Together: `Runtime → Version → Endpoint → Session`. Endpoints decouple clients ("hit the `production` endpoint") from versions ("v17 is the build we shipped on Tuesday"). --- ## 05 · How Runtime fits with the rest of AgentCore Runtime is one of eleven AgentCore services. It's the host; the others plug in: - **Identity** — handles agent-side OAuth and credential vending so your Runtime container never sees long-lived secrets. - **Memory** — short-term and long-term memory stores Runtime sessions can read and write. - **Gateway** — turns your existing APIs and Lambdas into MCP tools the Runtime agent can call. - **Observability** — every Runtime invocation emits OpenTelemetry spans to CloudWatch Transaction Search; enable it once and the agent inspector lights up automatically. - **Code Interpreter / Browser** — sandboxed tools the Runtime agent invokes when it needs to execute code or drive a webpage. Runtime can run completely standalone — none of the others are required — but the value compounds quickly when you bring two or three of them in. --- ## 06 · Limits worth knowing on day one - **ARM64 only.** No exceptions. Build with `--platform=linux/arm64` or the image won't start. - **8-hour session ceiling.** Long, but not infinite. Plan checkpointing if your agent legitimately needs longer. - **`/invocations` and `/ping` are mandatory.** Both must exist; both must return promptly. CloudWatch logs will tell you when `/ping` starts failing. - **`agent-core` (with a hyphen) shows up in some error messages**, but the boto3 client is `bedrock-agentcore`. Common copy-paste trip. - **Observability is opt-in.** Enable CloudWatch Transaction Search once per account/region or you'll see "spans are missing" in the agent inspector. --- ## 07 · Try it in five minutes If you have Node 20+, Python 3.10+, the AWS CDK installed, and AWS credentials configured, the full happy path is four commands: npm install -g @aws/agentcore agentcore create --name HelloAgent --defaults cd HelloAgent && agentcore dev # local inspector at localhost:8080 agentcore deploy # CDK deploys Runtime + IAM + ECR `agentcore status` shows the deployed endpoint URL; `agentcore invoke "Hello"` sends a prompt; `agentcore logs --tail` streams CloudWatch. Tomorrow we'll look at the **`/invocations` HTTP contract** in detail — what the request and response actually look like on the wire when you bypass the CLI and call Runtime directly with `boto3` or `curl`. --- **Verified against the official docs on 2026-05-26.** Sources: , , , . If the docs change, this lesson is a snapshot of that day — check the sources for current behaviour. --- > **This page — research, writing, verification, and deployment — was built by > Claude Cowork.** No human touched the prose, the layout, or the upload > pipeline. The lesson was generated this morning, cross-checked against the > official AWS docs by an independent verification pass, and published > to Cloudflare R2 on a schedule. > > A daily experiment by Monty van Emmerik · — AWS Bedrock & AgentCore · Tip of the Day · No. 001 · vanemmerik.ai