--- title: 'Llama Stack' description: 'Llama Stack is a framework from Meta AI for building Agentic applications.' --- import CodeTooltip from '/snippets/add-code-tooltip.mdx' import EnvTooltip from '/snippets/add-env-tooltip.mdx' AgentOps integrates with Llama Stack via its python [client](https://github.com/meta-llama/llama-stack-client-python) to provide observability into applications that leverage it. Llama Stack has comprehensive [documentation](https://llama-stack.readthedocs.io/) available as well as a great [quickstart](https://llama-stack.readthedocs.io/en/latest/getting_started/index.html) guide. You can use this guide to setup the Llama Stack server and client or alternatively use our Docker [compose](https://github.com/AgentOps-AI/agentops/blob/main/examples/llama_stack_client_examples/docker-compose.yml) file. ## Adding AgentOps to Llama Stack applications ```bash pip pip install agentops ``` ```bash poetry poetry add agentops ``` ```bash pip pip install llama-stack-client ``` ```bash poetry poetry add llama-stack-client ``` ```python python import agentops agentops.init() ``` ```python .env AGENTOPS_API_KEY= ``` Read more about environment variables in [Advanced Configuration](/v1/usage/advanced-configuration) Execute your program and visit [app.agentops.ai/drilldown](https://app.agentops.ai/drilldown) to observe your waterfall! 🕵️ After your run, AgentOps prints a clickable url to console linking directly to your session in the Dashboard ## Examples An example notebook is available [here](https://github.com/AgentOps-AI/agentops/blob/main/examples/llama_stack_client_examples/notebook.ipynb) to showcase how to use the Llama Stack client with AgentOps.