ramalama
RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers.
File Explorer
Download Latest Version (.zip)- version
- bug_report.yaml
- feature_request.yaml
- install-ollama.sh
- approve-command.yml
- build-macos-installer.yml
- ci.yml
- docsite-publish.yml
- install_ramalama.yml
- pypi.yml
- stale.yml
- CODEOWNERS
- renovate.json5
- asahi-pull-request.yaml
- asahi-push.yaml
- cann-pull-request.yaml
- cann-push.yaml
- cuda-pull-request.yaml
- cuda-push.yaml
- cuda-tools-pull-request.yaml
- cuda-tools-push.yaml
- e2e-pull-request.yaml
- e2e-push.yaml
- e2e-tests.yaml
- init-snapshot.yaml
- test-vm-cmd.yaml
- intel-gpu-pull-request.yaml
- intel-gpu-push.yaml
- intel-gpu-tools-pull-request.yaml
- intel-gpu-tools-push.yaml
- llama-stack-pull-request.yaml
- llama-stack-push.yaml
- openvino-pull-request.yaml
- openvino-push.yaml
- pi-agent-pull-request.yaml
- pi-agent-push.yaml
- pull-request-pipeline.yaml
- push-pipeline.yaml
- ramalama-pull-request.yaml
- ramalama-push.yaml
- ramalama-cli-pull-request.yaml
- ramalama-cli-push.yaml
- ramalama-rag-pull-request.yaml
- ramalama-rag-push.yaml
- ramalama-tools-pull-request.yaml
- ramalama-tools-push.yaml
- ramalama-release-tag.yaml
- create-release-snapshot.yaml
- push-release-snapshot.yaml
- create-override-snapshot.sh
- create-override-snapshot.yaml
- push-snapshot.yaml
- remoting-pull-request.yaml
- remoting-push.yaml
- rocm-pull-request.yaml
- rocm-push.yaml
- rocm-tools-pull-request.yaml
- rocm-tools-push.yaml
- stable-diffusion-pull-request.yaml
- stable-diffusion-push.yaml
- test-cmd.yaml
- wait-for-image.yaml
- ramalama
- ramalama
- ramalama.fish
- _ramalama
- Containerfile
- Containerfile
- Containerfile.rag
- Containerfile.tools
- Makefile
- requirements-rag.in
- requirements-rag.txt
- requirements-tools-cpu-aarch64.txt
- requirements-tools-cpu.txt
- requirements-tools-cu129-aarch64.txt
- requirements-tools-cu129.txt
- requirements-tools-rocm7.1.txt
- requirements-tools-xpu.txt
- requirements-tools.in
- Containerfile
- Containerfile
- Containerfile
- containers.conf
- entrypoint.sh
- Containerfile
- populate.py
- server.py
- Containerfile
- entrypoint.sh
- oneAPI.repo
- Containerfile
- entrypoint.sh
- Containerfile
- Containerfile
- Containerfile
- Containerfile
- Containerfile
- Containerfile
- Containerfile
- Containerfile
- build-cli.sh
- build-vllm.sh
- build_llama.sh
- build_rag.sh
- build_stable_diffusion.sh
- build_tools.sh
- doc2rag
- lib.sh
- rag_framework
- Containerfile
- entrypoint.sh
- camera-demo.html
- ramalama.sh
- README.md
- ramalama-ls.1
- ramalama-nvidia.7
- ramalama-ps.1
- api-key.md
- api.md
- authfile.md
- backend.md
- cache-reuse.md
- color.md
- ctx-size.md
- device.md
- engine-args.md
- env.md
- format.md
- goose-image.md
- help.md
- host.md
- image.md
- interactive.md
- keep-groups.md
- keepalive.md
- logfile.md
- max-tokens.md
- mcp.md
- model-draft.md
- model-transports.md
- models-max.md
- name.md
- ncmoe.md
- network.md
- ngl.md
- oci-runtime.md
- opencode-image.md
- pi-image.md
- port.md
- privileged.md
- prompt.md
- pull.md
- rag-pair.md
- runtime-args.md
- seed.md
- selinux.md
- serve-examples-body.md
- spec-draft-n-max.md
- spec-draft-n-min.md
- spec-draft-p-min.md
- spec-type.md
- stack-image.md
- summarize-after.md
- temp.md
- thinking.md
- threads.md
- tls-verify.md
- url.md
- webui.md
- workdir.md
- wsl2-docker-cuda.md
- wsl2-podman-cuda.md
- .gitignore
- MACOS_INSTALL.md
- Makefile
- ramalama-bench.1.md
- ramalama-bench.1.md.in
- ramalama-benchmarks.1.md
- ramalama-cann.7.md
- ramalama-chat.1.md
- ramalama-containers.1.md
- ramalama-convert.1.md
- ramalama-cuda.7.md
- ramalama-daemon.1.md
- ramalama-info.1.md
- ramalama-inspect.1.md
- ramalama-list.1.md
- ramalama-login.1.md
- ramalama-logout.1.md
- ramalama-macos.7.md
- ramalama-models.1.md
- ramalama-musa.7.md
- ramalama-oci.5.md
- ramalama-perplexity.1.md
- ramalama-perplexity.1.md.in
- ramalama-pull.1.md
- ramalama-push.1.md
- ramalama-rag.1.md
- ramalama-rm.1.md
- ramalama-run.1.md
- ramalama-run.1.md.in
- ramalama-sandbox-goose.1.md
- ramalama-sandbox-goose.1.md.in
- ramalama-sandbox-opencode.1.md
- ramalama-sandbox-opencode.1.md.in
- ramalama-sandbox-pi.1.md
- ramalama-sandbox-pi.1.md.in
- ramalama-sandbox.1.md
- ramalama-serve.1.md
- ramalama-serve.1.md.in
- ramalama-stop.1.md
- ramalama-version.1.md
- ramalama-version.1.md.in
- ramalama.1.md
- ramalama.conf
- ramalama.conf.5.md
- README.md
- _category_.json
- _category_.json
- _category_.json
- _category_.json
- installation.mdx
- _category_.json
- cuda.mdx
- introduction.mdx
- index.tsx
- styles.module.css
- custom.css
- index.module.css
- index.tsx
- markdown-page.md
- favicon.png
- logo.svg
- ramalama-favicon.svg
- ramalama-logo-full-horiz.svg
- .nojekyll
- .gitignore
- convert_manpages.py
- docusaurus.config.ts
- Makefile
- package-lock.json
- package.json
- sidebars.ts
- tsconfig.json
- man-page-checker
- markdown-preprocess
- rm.sh
- tree_status.sh
- xref-helpmsgs-manpages
- ramalama.icns
- ramalama-logo-full-horiz-dark.png
- ramalama-logo-full-horiz.png
- ramalama-logo-full-vertical-added-bg.png
- ramalama-logo-full-vertical-dark.png
- ramalama-logo-full-vertical.png
- ramalama-logo-no-text.png
- ramalama-logo-full-horiz-dark.svg
- ramalama-logo-full-horiz.svg
- ramalama-logo-full-vertical-added-bg.svg
- ramalama-logo-full-vertical-dark.svg
- ramalama-logo-full-vertical.svg
- ramalama-logo-no-text.svg
- ramalama-logo.png
- no-rpm.fmf
- rpm.fmf
- errors.py
- manager.py
- schemas.py
- utilities.py
- __init__.py
- api_providers.py
- base.py
- openai.py
- errors.py
- model.py
- serve.py
- base.py
- daemon.py
- proxy.py
- ramalama.py
- model_runner.py
- daemon.py
- logging.py
- __init__.py
- base.py
- image.py
- pdf.py
- txt.py
- __init__.py
- file_manager.py
- mcp_agent.py
- mcp_client.py
- __init__.py
- base_info.py
- error.py
- gguf_info.py
- gguf_parser.py
- safetensor_info.py
- safetensor_parser.py
- constants.py
- global_store.py
- go2jinja.py
- reffile.py
- snapshot_file.py
- store.py
- template_conversion.py
- __init__.py
- cli.py
- handler.py
- __init__.py
- common.py
- llama_cpp.py
- llama_cpp_commands.py
- mlx.py
- vllm.py
- __init__.py
- __init__.py
- interface.py
- loader.py
- registry.py
- __init__.py
- oci.py
- oci_artifact.py
- resolver.py
- spec.py
- strategies.py
- strategy.py
- __init__.py
- api.py
- base.py
- huggingface.py
- modelscope.py
- ollama.py
- rlcr.py
- transport_factory.py
- url.py
- __init__.py
- amdkfd.py
- annotations.py
- arg_types.py
- chat.py
- chat_utils.py
- cli.py
- cli_arg_normalization.py
- common.py
- compat.py
- compose.py
- config.py
- config_types.py
- console.py
- endian.py
- engine.py
- file.py
- hf_style_repo_base.py
- host_utils.py
- http_client.py
- kube.py
- layered_config.py
- log_levels.py
- logger.py
- model_server.py
- oci_tools.py
- ollama_repo_utils.py
- path_utils.py
- prompt_utils.py
- proxy_support.py
- py.typed
- quadlet.py
- rag.py
- sandbox.py
- shortnames.py
- stack.py
- toml_parser.py
- tools.py
- version.py
- ramalama.spec
- conclusion.html
- distribution.xml.template
- ramalama-pkg.plist
- readme.html
- welcome.html
- build_macos_pkg.sh
- newver.sh
- release-image.sh
- release.sh
- replace-shas.sh
- shortnames.conf
- conftest.py
- README.md
- test_artifact.py
- test_basic.py
- test_bench.py
- test_cli_max_tokens.py
- test_convert.py
- test_help.py
- test_info.py
- test_inspect.py
- test_list.py
- test_mlx.py
- test_pull.py
- test_rag.py
- test_rm.py
- test_run.py
- test_sandbox.py
- test_serve.py
- utils.py
- no-rpm.fmf
- vllm.yaml
- basic.yaml
- with_chat_template.yaml
- with_custom_name.yaml
- with_env_vars.yaml
- with_mmproj.yaml
- with_model_draft.yaml
- with_nvidia_gpu.yaml
- with_port.yaml
- with_port_mapping.yaml
- with_rag_oci.yaml
- with_rag_path.yaml
- sample.csv
- sample.json
- sample.md
- sample.sh
- sample.toml
- sample.txt
- sample.yaml
- basic_hostpath.yaml
- draft_model_hostpath.yaml
- with_chat_template.yaml
- with_custom_name.yaml
- with_env.yaml
- with_mmproj.yaml
- with_port.yaml
- with_port_mapping.yaml
- with_rag.yaml
- ollama-gguf
- ollama-type-car
- ollama-type-car-gguf
- url-simple
- tinyllama.container
- tinyllama.image
- tinyllama.volume
- tinyllama.container
- tinyllama.container
- tinyllama.image
- tinyllama.volume
- tinyllama.container
- tinyllama.image
- tinyllama.volume
- tinyllama.container
- tinyllama.image
- tinyllama.volume
- modelfromstore.container
- modelfromstore_add_to_unit.container
- modelfromstore_ct.container
- modelfromstore_mmproj.container
- gpt-oss-120b.container
- oci-model.container
- oci-model.image
- oci-model.volume
- oci-model-port.container
- oci-model-port.image
- oci-model-port.volume
- oci-model-rag.container
- oci-model-rag.image
- oci-model-rag.volume
- rag-latest-rag.image
- rag-latest-rag.volume
- tinyllama.container
- tinyllama.image
- tinyllama.volume
- __init__.py
- test_openai_provider.py
- conftest.py
- test_api_providers.py
- test_api_transport.py
- test_artifact_strategies_impl.py
- test_artifact_strategy.py
- test_benchmarks_manager.py
- test_chat.py
- test_chat_provider_base.py
- test_cli.py
- test_cli_arg_normalization.py
- test_cli_args.py
- test_common.py
- test_compat.py
- test_compose.py
- test_config.py
- test_config_documentation.py
- test_engine.py
- test_file_loader.py
- test_file_loader_integration.py
- test_file_loader_with_data.py
- test_host_utils.py
- test_http_client.py
- test_huggingface.py
- test_inference_engine_plugins.py
- test_kube.py
- test_layered_config.py
- test_list_cli.py
- test_loader.py
- test_max_tokens.py
- test_model_server.py
- test_model_store.py
- test_oci.py
- test_oci_spec.py
- test_oci_tools.py
- test_ollama.py
- test_proxy_support.py
- test_quadlet.py
- test_rag_unit.py
- test_rlcr.py
- test_router_mode.py
- test_sandbox_cmd.py
- test_shortnames.py
- test_template_conversion.py
- test_toml_parser.py
- test_transport_base.py
- test_transport_factory.py
- test_url.py
- __init__.py
- ci.sh
- conftest.py
- report.md
- .codespelldict
- .gitignore
- .packit-copr-rpm.sh
- .packit.yaml
- .pre-commit-config.yaml
- CLAUDE.md
- CODE-OF-CONDUCT.md
- container_build.sh
- CONTRIBUTING.md
- CONTRIBUTOR_LADDER.md
- flake.lock
- flake.nix
- install-uv.sh
- install.sh
- LICENSE
- MAINTAINERS.md
- Makefile
- MANIFEST.in
- pyproject.toml
- pytest.ini
- ramalama.spec
- README.md
- Roadmap.md
- SECURITY.md
- setup.py
# Installation Guide
1. Get the code
git clone https://github.com/containers/ramalama
Downloads the entire project code from GitHub to your computer.
cd ramalama
Moves into the project folder you just downloaded.
2. Official Install Script
Easy RecommendedPrerequisites
- Python 3 Python is required to use pip.
pip install ramalama
Installs the package published on PyPI directly — no need to clone the source.
curl -fsSL https://ramalama.ai/install.sh | bash
Downloads and runs the official install script in one line — this handles the full setup automatically.
After installing, open a new terminal and run the program's version command (e.g. --version) to confirm it worked.
Pulled directly from this repo's README.
3. Node.js
EasyPrerequisites
cd docsite
This project's files live in a subfolder, so move into it first.
npm install
Downloads and installs the libraries listed in package.json.
npm start
Starts the development/run server.
After running the command, open the address shown in the terminal (usually something like http://localhost:3000) in your browser.
4. Python
EasyPrerequisites
pip install ramalama
Installs the package published on PyPI directly — no need to clone the source.
pip uninstall ramalama
Type this command into your terminal and run it.
If it runs without errors and prints output in the terminal, it worked.
Pulled directly from this repo's README.
5. Make
MediumPrerequisites
- Git Needed to download the project code from GitHub.
- Make Usually pre-installed on Linux/macOS. On Windows, install separately (e.g. via MSYS2 or WSL).
make
Compiles the code based on the generated build configuration to produce an executable.
If it finishes without errors, it worked. Try running the generated executable directly.
// repository documentation
Was this content helpful?
(0 ratings)