Overview
Modular Platform
A simplified diagram of how the Modular Platform scales your GenAI deployment.
Modular Platform
Modular MAX Code Repo Agent architecture
Modular MAX: Code Repo Agent is an experimental containerized agent that lets you chat with your code repositories through an interactive terminal session. Designed to enhance developer productivity, it supports repository-aware Q&A, automatic documentation generation for Python and Mojo codebases, and general programming assistance. Actively in development, this early release is a great opportunity to explore the future of AI-assisted coding and share feedback to shape its evolution.
Highlights
- Repository-aware Q&A for answering questions about specific codebases
- General programming chat for development assistance
- Automatic documentation generation for Python and Mojo repositories
Details
Unlock automation with AI agent solutions

Features and programs
Financing for AWS Marketplace purchases
Pricing
Vendor refund policy
This agent is experimental and is currently under active development. We would love your feedback as we continue to improve the experience.
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
Deploy the max-code-repo-agent container
- Amazon ECS
- Amazon EKS
- Amazon ECS Anywhere
- Amazon EKS Anywhere
Container image
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
Latest Modular MAX: Code Repo Helper agent container image
Additional details
Usage instructions
Important: This container requires an NVIDIA GPU.
Please visit the MAX GPU requirements page to view compatible NVIDIA GPUs: https://docs.modular.com/max/faq/#gpu-requirementsÂ
Want to deploy this container on an AMD GPU? Contact us here: https://www.modular.com/company/talk-to-usÂ
Run the container on an NVIDIA GPU using the following command:
docker run
--gpus 1
-v ~/.cache/huggingface:/root/.cache/huggingface
--env "HF_HUB_ENABLE_HF_TRANSFER=1"
--env "HF_TOKEN=<secret>"
modular/max-repo-agent:latest
Learn more about the HF_TOKEN environment variable and how to create Hugging Face access tokens: https://huggingface.co/docs/huggingface_hub/en/package_reference/environment_variables#hftoken , https://huggingface.co/docs/hub/en/security-tokensÂ
Start the container. MAX will load the model weights from Hugging Face Hub (Qwen2.5-7B-Instruct-1M). When the model is ready, Docker logs will show: max.serve: Server ready on http://0.0.0.0:8010Â
Open an interactive terminal to the container: docker exec -it <container-name> /bin/bash
You can use the docker ps command to find the container name. You may need SSH access to your GPU instance depending on your setup.
Provide a GitHub URL as a prompt. For best results, include only the URL with no additional context. The agent will suggest next steps and prompt phrasing. The repository should be written in Python or Mojo.
Support
Vendor support
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
