[langchain]: Update the AgentCore Runtime section on the AWS provider page for the new AgentCore CLI

Open Beginner friendly
#6,091 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
2/5
Estimated time
1-3 hours
Newbie friendliness
88/100
Issue type
Documentation
Clarity
Clearly specified
Activity status
Active
Tech stack
aws, node.js, python
Domain
cloud, documentation

Research direction

Update src/oss/python/integrations/providers/aws.mdx, focusing on the “Amazon Bedrock AgentCore Runtime” section. Compare its installation, CLI workflow, command-name conflict note, and observability guidance with the linked AWS references. Done means the documented flow uses the new CLI and includes the required tracing guidance so readers can follow the section successfully.

Written by the indexing model from the issue text.

Description

external
Type of issue

issue / bug

Language

Python

Description

Page: https://docs.langchain.com/oss/python/integrations/providers/aws (section "Amazon Bedrock AgentCore Runtime")

Source: src/oss/python/integrations/providers/aws.mdx

Three items in that section need an update for Amazon Bedrock AgentCore's new CLI.

1. The CLI is never installed. The section installs bedrock-agentcore (the Python SDK), then calls agentcore configure and agentcore launch. Those commands come from a separate CLI that the page does not install, so following it as written returns command not found. The CLI installs with npm install -g @aws/agentcore.

2. The commands shown are not in the new CLI. configure and launch are not part of its command set, so adding the install line alone does not make the section runnable. For a new project the flow is agentcore create --framework LangChain_LangGraph --model-provider Bedrock, then agentcore dev, agentcore deploy, and agentcore invoke. For an existing agent file, add it to a project with agentcore add agent --type byo --code-location <dir> --entrypoint <file>, then agentcore deploy. Reference: https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-get-started-cli.html

3. No observability guidance. A hand written LangGraph deployment renders no traces without the OpenTelemetry dependencies. Adding aws-opentelemetry-distro>=0.18.0 and opentelemetry-instrumentation-langchain>=0.55.0, then running the entrypoint under opentelemetry-instrument, covers it. ADOT discovers the instrumentor at startup, so no instrumentation code is needed. References: https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/observability-configure.html and https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/supported-frameworks-langgraph.html

One additional note for the page: if a Python agentcore command is already installed, it shadows the npm one, because both use the same command name.

I can open a PR for this.

Dominant language
MDX
Stars
418
Forks
2.7k
Avg merge
1d 6h
Merged PRs (30d)
351

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from langchain-ai/docs

All issues in langchain-ai/docs

Similar issues

More Cloud issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.