# Ramalama Labs Docs

## Docs

- [bench](https://docs.ramalama.com/cli/commands/ramalama/bench.md): benchmark specified AI Model
- [chat](https://docs.ramalama.com/cli/commands/ramalama/chat.md): OpenAI chat with the specified REST API URL
- [containers](https://docs.ramalama.com/cli/commands/ramalama/containers.md): list all RamaLama containers
- [convert](https://docs.ramalama.com/cli/commands/ramalama/convert.md): convert AI Models from local storage to OCI Image
- [daemon](https://docs.ramalama.com/cli/commands/ramalama/daemon.md): run a RamaLama REST server
- [info](https://docs.ramalama.com/cli/commands/ramalama/info.md): display RamaLama configuration information
- [inspect](https://docs.ramalama.com/cli/commands/ramalama/inspect.md): inspect the specified AI Model
- [list](https://docs.ramalama.com/cli/commands/ramalama/list.md): list all downloaded AI Models
- [login](https://docs.ramalama.com/cli/commands/ramalama/login.md): login to remote registry
- [logout](https://docs.ramalama.com/cli/commands/ramalama/logout.md): logout from remote registry
- [perplexity](https://docs.ramalama.com/cli/commands/ramalama/perplexity.md): calculate the perplexity value of an AI Model
- [pull](https://docs.ramalama.com/cli/commands/ramalama/pull.md): pull AI Models from Model registries to local storage
- [push](https://docs.ramalama.com/cli/commands/ramalama/push.md): push AI Models from local storage to remote registries
- [rag](https://docs.ramalama.com/cli/commands/ramalama/rag.md): generate and convert Retrieval Augmented Generation (RAG) data from provided documents into an OCI Image
- [ramalama](https://docs.ramalama.com/cli/commands/ramalama/ramalama.md): Simple management tool for working with AI Models
- [rm](https://docs.ramalama.com/cli/commands/ramalama/rm.md): remove AI Models from local storage
- [run](https://docs.ramalama.com/cli/commands/ramalama/run.md): run specified AI Model as a chatbot
- [serve](https://docs.ramalama.com/cli/commands/ramalama/serve.md): serve REST API on specified AI Model
- [stop](https://docs.ramalama.com/cli/commands/ramalama/stop.md): stop named container that is running AI Model
- [version](https://docs.ramalama.com/cli/commands/ramalama/version.md): display version of RamaLama
- [Configuration File](https://docs.ramalama.com/cli/configuration/conf.md): Configuration file reference
- [OCI Spec](https://docs.ramalama.com/cli/configuration/ramalama-oci.md): Configuration file reference
- [Installation](https://docs.ramalama.com/cli/getting-started/installation.md): How to install RamaLama on your system
- [Introduction](https://docs.ramalama.com/cli/introduction.md): RamaLama strives to make working with AI simple, straightforward, and familiar by using OCI containers.
- [cann](https://docs.ramalama.com/cli/platform-guides/cann.md): Platform-specific setup guide
- [cuda](https://docs.ramalama.com/cli/platform-guides/cuda.md): Platform-specific setup guide
- [macos](https://docs.ramalama.com/cli/platform-guides/macos.md): Platform-specific setup guide
- [musa](https://docs.ramalama.com/cli/platform-guides/musa.md): Platform-specific setup guide
- [Creating API Keys](https://docs.ramalama.com/cloud/api-keys/creating.md): Learn how to create and manage API keys for RamaLama Cloud.
- [Using API Keys](https://docs.ramalama.com/cloud/api-keys/using.md): How to authenticate requests with your RamaLama Cloud API key.
- [Introduction](https://docs.ramalama.com/cloud/introduction.md): Get started with RamaLama Cloud and API access.
- [Metrics](https://docs.ramalama.com/cloud/metrics.md): Usage and performance analytics for RamaLama Cloud (coming soon).
- [Supported Models](https://docs.ramalama.com/cloud/supported-models.md): Browse models available through the RamaLama Cloud gateway.
- [bench](https://docs.ramalama.com/oss-docusaurus/docs/commands/ramalama/bench.md): benchmark specified AI Model
- [chat](https://docs.ramalama.com/oss-docusaurus/docs/commands/ramalama/chat.md): OpenAI chat with the specified REST API URL
- [containers](https://docs.ramalama.com/oss-docusaurus/docs/commands/ramalama/containers.md): list all RamaLama containers
- [convert](https://docs.ramalama.com/oss-docusaurus/docs/commands/ramalama/convert.md): convert AI Models from local storage to OCI Image
- [daemon](https://docs.ramalama.com/oss-docusaurus/docs/commands/ramalama/daemon.md): run a RamaLama REST server
- [info](https://docs.ramalama.com/oss-docusaurus/docs/commands/ramalama/info.md): display RamaLama configuration information
- [inspect](https://docs.ramalama.com/oss-docusaurus/docs/commands/ramalama/inspect.md): inspect the specified AI Model
- [list](https://docs.ramalama.com/oss-docusaurus/docs/commands/ramalama/list.md): list all downloaded AI Models
- [login](https://docs.ramalama.com/oss-docusaurus/docs/commands/ramalama/login.md): login to remote registry
- [logout](https://docs.ramalama.com/oss-docusaurus/docs/commands/ramalama/logout.md): logout from remote registry
- [perplexity](https://docs.ramalama.com/oss-docusaurus/docs/commands/ramalama/perplexity.md): calculate the perplexity value of an AI Model
- [pull](https://docs.ramalama.com/oss-docusaurus/docs/commands/ramalama/pull.md): pull AI Models from Model registries to local storage
- [push](https://docs.ramalama.com/oss-docusaurus/docs/commands/ramalama/push.md): push AI Models from local storage to remote registries
- [rag](https://docs.ramalama.com/oss-docusaurus/docs/commands/ramalama/rag.md): generate and convert Retrieval Augmented Generation (RAG) data from provided documents into an OCI Image
- [ramalama](https://docs.ramalama.com/oss-docusaurus/docs/commands/ramalama/ramalama.md): Simple management tool for working with AI Models
- [rm](https://docs.ramalama.com/oss-docusaurus/docs/commands/ramalama/rm.md): remove AI Models from local storage
- [run](https://docs.ramalama.com/oss-docusaurus/docs/commands/ramalama/run.md): run specified AI Model as a chatbot
- [serve](https://docs.ramalama.com/oss-docusaurus/docs/commands/ramalama/serve.md): serve REST API on specified AI Model
- [stop](https://docs.ramalama.com/oss-docusaurus/docs/commands/ramalama/stop.md): stop named container that is running AI Model
- [version](https://docs.ramalama.com/oss-docusaurus/docs/commands/ramalama/version.md): display version of RamaLama
- [Configuration File](https://docs.ramalama.com/oss-docusaurus/docs/configuration/conf.md): Configuration file reference
- [OCI Spec](https://docs.ramalama.com/oss-docusaurus/docs/configuration/ramalama-oci.md): Configuration file reference
- [Installation](https://docs.ramalama.com/oss-docusaurus/docs/getting-started/installation.md): How to install RamaLama on your system
- [Introduction](https://docs.ramalama.com/oss-docusaurus/docs/introduction.md): RamaLama strives to make working with AI simple, straightforward, and familiar by using OCI containers.
- [cann](https://docs.ramalama.com/oss-docusaurus/docs/platform-guides/cann.md): Platform-specific setup guide
- [cuda](https://docs.ramalama.com/oss-docusaurus/docs/platform-guides/cuda.md): Platform-specific setup guide
- [macos](https://docs.ramalama.com/oss-docusaurus/docs/platform-guides/macos.md): Platform-specific setup guide
- [musa](https://docs.ramalama.com/oss-docusaurus/docs/platform-guides/musa.md): Platform-specific setup guide
- [Models (OCI)](https://docs.ramalama.com/registry/artifacts/model.md): Raw model files packaged as OCI artifacts for portability, provenance, and secure distribution.
- [Model Images](https://docs.ramalama.com/registry/artifacts/model-image.md): Turnkey container images that bundle a runtime and a specific model — the fastest path to serving.
- [Runtimes](https://docs.ramalama.com/registry/artifacts/runtime.md): Hardened, distroless inference engines (e.g., llama.cpp, vLLM) for CPU and GPU.
- [Docker Compose](https://docs.ramalama.com/registry/deploying/compose.md): Run RamaLama in Docker Compose with CPU or GPU.
- [Kubernetes](https://docs.ramalama.com/registry/deploying/kubernetes.md): Run RamaLama on Kubernetes with CPU or GPU nodes.
- [Local Environment](https://docs.ramalama.com/registry/deploying/local.md): Configure your machine for running RamaLama locally.
- [CVE Guidance](https://docs.ramalama.com/registry/education/CVE.md): Understanding CVEs and how RamaLama reduces risk.
- [SBOM](https://docs.ramalama.com/registry/education/SBOM.md): Retrieve and use SBOMs for RamaLama images.
- [RamaLama Enterprise](https://docs.ramalama.com/registry/getting_started/about.md): Secure, hardened AI container images for production environments.
- [Discord](https://docs.ramalama.com/registry/getting_started/discord.md)
- [Introduction](https://docs.ramalama.com/registry/getting_started/introduction.md): Simplify compliance and build faster with our catalogue of provably untampered LLMs and hardened containers.
- [RamaLama CLI](https://docs.ramalama.com/registry/getting_started/oss.md): The local first toolkit for deploying and using AI in containers.
- [Cloud](https://docs.ramalama.com/registry/quickstart/cloud.md): Using RamaLama Labs container artifacts in the cloud.
- [Laptop](https://docs.ramalama.com/registry/quickstart/laptop.md): Using RamaLama Labs container artifacts on your local machine.
- [Go](https://docs.ramalama.com/sdk/go.md): Go SDK status and availability.
- [Introduction](https://docs.ramalama.com/sdk/introduction.md): Production-grade, local-first AI SDKs for apps built on RamaLama.
- [Chat](https://docs.ramalama.com/sdk/python/capabilities/chat.md): Send chat completion requests with the RamaLama Python SDK.
- [Speech-to-Text](https://docs.ramalama.com/sdk/python/capabilities/speech-to-text.md): Speech-to-text support in the RamaLama Python SDK.
- [Installation](https://docs.ramalama.com/sdk/python/installation.md): Install the Python SDK and required runtime tools.
- [Introduction](https://docs.ramalama.com/sdk/python/introduction.md): Overview of the RamaLama Python SDK.
- [Quick start](https://docs.ramalama.com/sdk/python/quickstart.md): Run your first local model with the Python SDK.
- [Rust](https://docs.ramalama.com/sdk/rust.md): Rust SDK status and availability.
- [TypeScript](https://docs.ramalama.com/sdk/typescript.md): TypeScript SDK status and availability.