Agent Plugins Marketplace
← All plugins

aws-ai-ml

v0.1.0

Generative AI and ML skills for the main agent: Amazon Bedrock models, agents, knowledge bases, and guardrails, plus AWS AI/ML service selection and SageMaker AI, with the read-only SageMaker AI MCP server.

CodexClaude CodeAgent Plugins2 Skills2 MCP serversstdio

By TalkOps AILicense: Apache-2.00 GitHub starsUpdated last week

Directory evidence

Runtimes
Codex, Claude Code, and Agent Plugins
Parsed components
4 skill or MCP entries
Source updated
Oct 10, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install aws-ai-ml for Codex and Claude Code

Installs for the current user
codex plugin marketplace add talkops-ai/devops-plugins
codex plugin marketplace upgrade talkops-devops-plugins
codex plugin add aws-ai-ml@talkops-devops-plugins

Paste and run these commands in a terminal with Codex. They add and refresh the talkops-devops-plugins catalog, then install this plugin.

Compatibility: the page URL and API slug “aws-ai-ml” remain stable.

  • Codex: aws-ai-ml@agent-plugin-marketplace → aws-ai-ml@talkops-devops-plugins

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/talkops-ai/devops-plugins

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/vertical-plugins/aws-ai-ml/.

Plugin files

plugins/vertical-plugins/aws-ai-ml/
├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
├── plugin.json
├── skills/amazon-bedrock/SKILL.md
├── skills/aws-ai-ml/SKILL.md
└── .mcp.json

Included Skills2

amazon-bedrockskills/amazon-bedrock/SKILL.md

Builds generative AI applications on Amazon Bedrock. Covers model invocation (Converse API, InvokeModel), RAG with Knowledge Bases, Bedrock Agents, Guardrails, and AgentCore (including the Harness managed agent loop). Applies when invoking models, setting up Knowledge Bases, creating agents, applying guardrails, deploying to AgentCore, migrating/porting/converting a Bedrock Agent (including inline agents) to an AgentCore Harness, troubleshooting Bedrock errors (ThrottlingException, AccessDeniedException), or choosing models (Claude, Llama, Nova, Titan). Also for prompt caching, quota and throttling diagnosis, cost tracking, migrating between Claude model generations (4.5 to 4.6 to 4.7), chunking strategies, API selection (Converse vs InvokeModel), guardrail capabilities, and model selection. Also covers AgentCore Payments (x402, microtransactions, Payment Manager, Connector, Instrument, Coinbase CDP, Stripe Privy, paid endpoints, agent payments). NOT for custom model training, Rekognition, or Comprehend.

aws-ai-mlskills/aws-ai-ml/SKILL.md

Selects, deploys, and customizes AI models on Amazon SageMaker. Fine-tuning (SFT, DPO, RLVR, RLAIF), model selection, dataset preparation, evaluation, deployment to SageMaker endpoints or Bedrock, inference optimization and endpoint diagnostics. Covers the full lifecycle from planning through production. Use when fine-tuning models on SageMaker, choosing/selecting which base model to customize or fine-tune from SageMaker Hub, finding a model to deploy without fine-tuning, transforming datasets for training, checking data readiness, evaluating model quality, deploying to endpoints, benchmarking or optimizing inference, setting up IAM roles and S3 buckets for training jobs, or managing a SageMaker Managed MLflow app. Also use to check endpoint health, diagnose failures, debug latency or errors, or view container logs and CloudWatch metrics. Covers Serverless Model Customization, Nova and OSS deployment paths, and PySDK v3. NOT for Ground Truth labeling, Feature Store, or general-purpose AWS infrastructure.

MCP servers2

aws-mcpstdio
command
uvx
args
mcp-proxy-for-aws-cli==1.7.0 https://aws-mcp.us-east-1.api.aws/mcp --skip-auth --metadata INSTALL_SOURCE=agent-toolkit-core
sagemakerstdio
command
uvx
args
awslabs.sagemaker-ai-mcp-server@latest
env.FASTMCP_LOG_LEVEL
ERROR

Plugin manifests3

plugins/vertical-plugins/aws-ai-ml/.codex-plugin/plugin.json
{
  "name": "aws-ai-ml",
  "version": "0.1.0",
  "description": "Generative AI and ML skills for the main agent: Amazon Bedrock models, agents, knowledge bases, and guardrails, plus AWS AI/ML service selection and SageMaker AI, with the read-only SageMaker AI MCP server.",
  "author": {
    "name": "TalkOps AI"
  },
  "homepage": "https://github.com/talkops-ai/devops-plugins",
  "repository": "https://github.com/talkops-ai/devops-plugins",
  "license": "Apache-2.0",
  "keywords": [
    "aws",
    "ai",
    "ml",
    "bedrock",
    "sagemaker",
    "generative-ai"
  ],
  "skills": "./skills/",
  "mcpServers": "./mcp.json",
  "interface": {
    "displayName": "AWS AI and ML",
    "shortDescription": "Generative AI and ML skills for the main agent",
    "longDescription": "Generative AI and ML skills for the main agent: Amazon Bedrock models, agents, knowledge bases, and guardrails, plus AWS AI/ML service selection and SageMaker AI, with the read-only SageMaker AI MCP server.",
    "developerName": "TalkOps AI",
    "category": "Cloud",
    "capabilities": [
      "Read",
      "Write"
    ],
    "websiteURL": "https://github.com/talkops-ai/devops-plugins/tree/main/plugins/vertical-plugins/aws-ai-ml",
    "brandColor": "#FF9900"
  }
}
plugins/vertical-plugins/aws-ai-ml/.claude-plugin/plugin.json
{
  "name": "aws-ai-ml",
  "version": "0.1.0",
  "description": "Generative AI and ML skills for the main agent: Amazon Bedrock models, agents, knowledge bases, and guardrails, plus AWS AI/ML service selection and SageMaker AI, with the read-only SageMaker AI MCP server.",
  "author": {
    "name": "TalkOps AI"
  },
  "homepage": "https://github.com/talkops-ai/devops-plugins",
  "repository": "https://github.com/talkops-ai/devops-plugins",
  "license": "Apache-2.0",
  "keywords": [
    "aws",
    "ai",
    "ml",
    "bedrock",
    "sagemaker",
    "generative-ai"
  ]
}
plugins/vertical-plugins/aws-ai-ml/plugin.json
{
  "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
  "name": "aws-ai-ml",
  "version": "0.1.0",
  "description": "Generative AI and ML skills for the main agent: Amazon Bedrock models, agents, knowledge bases, and guardrails, plus AWS AI/ML service selection and SageMaker AI, with the read-only SageMaker AI MCP server.",
  "author": {
    "name": "TalkOps AI"
  },
  "homepage": "https://github.com/talkops-ai/devops-plugins",
  "repository": "https://github.com/talkops-ai/devops-plugins",
  "license": "Apache-2.0",
  "keywords": [
    "aws",
    "ai",
    "ml",
    "bedrock",
    "sagemaker",
    "generative-ai"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[aws-ai-ml on Agent Plugins Marketplace](https://pluginsmp.com/plugins/aws-ai-ml)