> ## Documentation Index > Fetch the complete documentation index at: https://docs.phidata.com/llms.txt > Use this file to discover all available pages before exploring further. # LLM OS The [LLM OS](https://x.com/karpathy/status/1723140519554105733) proposes that LLMs are the CPU/Kernal of an emerging operating system and can solve problems by coordination multiple resources. Andrej Karpathy talks about it [in this tweet](https://twitter.com/karpathy/status/1723140519554105733), [this tweet](https://twitter.com/karpathy/status/1707437820045062561) and [this video](https://youtu.be/zjkBMFhNj_g?t=2535). Here's [a video](https://x.com/ashpreetbedi/status/1790109321939829139) of me building the LLM OS. Using this template, we can run the llm-os locally using docker and in production on AWS. ## Create your codebase Create your codebase using the `llm-os` template ```bash Mac theme={null} phi ws create -t llm-os -n llm-os ``` ```bash Windows theme={null} phi ws create -t llm-os -n llm-os ``` This will create a folder `llm-os` with the following structure: ```bash theme={null} llm-os # root directory of your llm-os ├── ai ├── agents.py # AI Agents ├── app # Streamlit app ├── api # FastApi routes ├── db # database settings ├── Dockerfile # Dockerfile for the application ├── pyproject.toml # python project definition ├── requirements.txt # python dependencies generated using pyproject.toml ├── scripts # helper scripts ├── utils # shared utilities └── workspace # phidata workspace directory ├── dev_resources.py # dev resources running locally ├── prd_resources.py # production resources running on AWS ├── secrets # storing secrets └── settings.py # phidata workspace settings ``` ## Set Credentials We use gpt-4o as the LLM, so export your `OPENAI_API_KEY`. You can get one [from OpenAI](https://platform.openai.com/account/api-keys) if needed. ```bash Mac theme={null} export OPENAI_API_KEY=sk-*** ``` ```bash Windows theme={null} setx OPENAI_API_KEY sk-*** ``` If you'd like to use the research agent, export your `EXA_API_KEY`. You can get one [from here](https://dashboard.exa.ai/api-keys) if needed. ```bash Mac theme={null} export EXA_API_KEY=*** ``` ```bash Windows theme={null} setx EXA_API_KEY *** ``` ## Run LLM OS We'll build a simple front-end for the LLM OS using [streamlit](https://streamlit.io/). Start the `app` group using: ```bash terminal theme={null} phi ws up --group app ``` ```bash shorthand theme={null} phi ws up dev:docker:app ``` **Press Enter** to confirm and give a few minutes for the image to download (only the first time). Verify container status and view logs on the docker dashboard. ### LLM OS * Open [localhost:8501](http://localhost:8501) to view your LLM OS. * Enter a username. * Add blog post to knowledge: [https://blog.samaltman.com/what-i-wish-someone-had-told-me](https://blog.samaltman.com/what-i-wish-someone-had-told-me) and ask: what did sam altman wish he knew? * Test Web search: Whats happening in france? * Test Calculator: What is 10! * Test Finance: What is the price of AAPL? * Test Finance: Write a comparison between nvidia and amd, use all finance tools available and summarize the key points * Test Research: Write a report on Hashicorp IBM acquisition LLM OS ## Optional: Serve your LLM OS as an API Streamlit is great for building micro front-ends but any production application will be built using a front-end framework like [next.js](https://nextjs.org) backed by a RestApi built using [FastApi](https://fastapi.tiangolo.com/). Your LLM OS comes with ready-to-use FastApi endpoints. Update the `workspace/settings.py` file and set `dev_api_enabled=True` ```python workspace/settings.py theme={null} ... ws_settings = WorkspaceSettings( ... # Uncomment the following line dev_api_enabled=True, ... ``` ```bash terminal theme={null} phi ws up --group api ``` ```bash shorthand theme={null} phi ws up dev:docker:api ``` **Press Enter** to confirm * Open [localhost:8000/docs](http://localhost:8000/docs) to view the API Endpoints. * Test the `v1/assitants/chat` endpoint with ```json theme={null} { "message": "Whats 10!", "agent": "LLM_OS" } ``` ### Build an AI Product using the LLM OS Your `llm-os` comes with pre-configured API endpoints that can be used to build your AI product. The general workflow is: * Call the `/assitants/create` endpoint to create a new run for a user. ```json theme={null} { "user_id": "my-app-user-1", "agent": "LLM_OS" } ``` * The response contains a `run_id` that can be used to build a chat interface by calling the `/assitants/chat` endpoint. ```json theme={null} { "message": "whats 10!", "stream": true, "run_id": "372224c0-cd5e-4e87-a29d-65d33d9353a5", "user_id": "my-app-user-1", "agent": "LLM_OS" } ``` These routes are defined the `api/routes` folder and can be customized to your use case. Message us on [discord](https://discord.gg/4MtYHHrgA8) if you need help. ## Delete local resources Play around and stop the workspace using: ```bash terminal theme={null} phi ws down ``` ```bash full options theme={null} phi ws down --env dev --infra docker ``` ```bash shorthand theme={null} phi ws down dev:docker ``` or stop individual Apps using: ```bash app theme={null} phi ws down --group app ``` ```bash api theme={null} phi ws down --group api ``` ```bash database theme={null} phi ws down --group db ``` ## Next Congratulations on running your LLM OS locally. Next Steps: * [Run your LLM OS on AWS](/templates/llm-os/run-aws) * Read how to [update workspace settings](/templates/how-to/workspace-settings) * Read how to [create a git repository for your workspace](/templates/how-to/git-repo) * Read how to [manage the development application](/templates/how-to/development-app) * Read how to [format and validate your code](/templates/how-to/format-and-validate) * Read how to [add python libraries](/templates/how-to/install) * Chat with us on [discord](https://discord.gg/4MtYHHrgA8)