otty / apps

All apps/RamaLama

RamaLama

ramalama

A tool for managing and serving AI models using containers.

Runs as ramalama|macOS, Linux, Windows|ramalama.ai

Open form in Otty otty.toml

Sync rules

What travels, what stays, what never leaves

RamaLama in your home directory Every rule on this page, by file

· ramalama.conf.d/ Sync

· shortnames.conf Sync

· ramalama.conf Never synced

Only what the catalog names. A directory that syncs brings everything inside it except what is listed as excluded here.

apps/ramalama/otty.tomlThe file this page is generated from

id = "ramalama"

name = "RamaLama"

homepage = "https://ramalama.ai/"

description = "A tool for managing and serving AI models using containers."

executables = ["ramalama"]

[dotfiles]

# https://ramalama.ai/docs/commands/ramalama/ documents the user config at

# $XDG_CONFIG_HOME/ramalama/ramalama.conf and drop-ins in ramalama.conf.d/;

# the same page documents shortnames.conf in the user config directory.

paths = [

"[configHome]/ramalama/ramalama.conf.d/",

"[configHome]/ramalama/shortnames.conf",

]

# The same documentation permits api_key in ramalama.conf. Keep that whole

# file encrypted while syncing the non-secret shortname and drop-in files.

secret = ["[configHome]/ramalama/ramalama.conf"]

side_effect = false

[commands]

format = 1

label = "Run or serve an AI model"

description = "Chat with a model or serve it over HTTP in a container. Image, device, RAG, speculative-decoding and TLS options are left out."

quality = "ai-draft"

parser = { end_of_options = "--", interleave = "permute", long_equals = true, short_attached = false, short_bundles = false }

[[commands.subcommand]]

path = ["run"]

label = "Run a model"

description = "Chat with a model interactively."

[[commands.subcommand.source]]

id = "man"

kind = "manual"

url = "https://github.com/containers/ramalama/blob/main/docs/ramalama-run.1.md"

revision = "main 2026-10-27"

evidence = '''

ramalama run [options] model [arg ...]

--ctx-size, -c size of the prompt context

--max-tokens=integer Maximum number of tokens to generate. Set to 0 for unlimited output (default: 0).

--name, -n Name of the container to run the Model in.

--temp="0.8" Temperature of the response from the AI Model.

--threads, -t Maximum number of cpu threads to use.

'''

[[commands.subcommand.field]]

id = "model"

label = "Model"

type = "string"

position = 0

min = 1

sources = ["man"]

[[commands.subcommand.field]]

id = "backend"

label = "GPU backend"

type = "enum"

option = ["--backend"]

choices = [{ value = "auto", label = "Auto" }, { value = "vulkan", label = "Vulkan" }, { value = "rocm", label = "ROCm" }, { value = "cuda", label = "CUDA" }, { value = "sycl", label = "SYCL" }, { value = "openvino", label = "OpenVINO" }, { value = "cann", label = "CANN" }, { value = "musa", label = "MUSA" }]

sources = ["man"]

[[commands.subcommand.field]]

id = "name"

label = "Container name"

type = "string"

option = ["--name", "-n"]

sources = ["man"]

[[commands.subcommand.field]]

id = "ctx_size"

label = "Context size"

type = "integer"

option = ["--ctx-size", "-c"]

sources = ["man"]

[[commands.subcommand.field]]

id = "temp"

label = "Temperature"

type = "number"

option = ["--temp"]

sources = ["man"]

[[commands.subcommand.field]]

id = "threads"

label = "CPU threads"

type = "integer"

option = ["--threads", "-t"]

sources = ["man"]

[[commands.subcommand.field]]

id = "max_tokens"

label = "Max tokens"

type = "integer"

option = ["--max-tokens"]

sources = ["man"]

[[commands.subcommand.task]]

id = "run"

label = "Run a model"

fields = ["model", "backend", "max_tokens"]

required = ["model"]

[[commands.subcommand.group]]

id = "basic"

label = "Basic"

fields = ["model", "backend", "max_tokens"]

[[commands.subcommand.group]]

id = "advanced"

label = "Advanced"

fields = ["name", "ctx_size", "temp", "threads"]

[[commands.subcommand]]

path = ["serve"]

label = "Serve a model"

description = "Serve a model on a local port."

[[commands.subcommand.source]]

id = "man"

kind = "manual"

url = "https://github.com/containers/ramalama/blob/main/docs/ramalama-serve.1.md"

revision = "main 2026-10-27"

evidence = '''

ramalama serve [options] [model ...]

--ctx-size, -c

--detach, -d

--name, -n

--port, -p

--temp="0.8"

--threads, -t

ramalama serve -d -p 8080 --name mymodel ollama://smollm:135m

'''

[[commands.subcommand.field]]

id = "model"

label = "Model"

type = "string"

position = 0

min = 1

sources = ["man"]

[[commands.subcommand.field]]

id = "backend"

label = "GPU backend"

type = "enum"

option = ["--backend"]

sources = ["man"]

[[commands.subcommand.field]]

id = "name"

label = "Container name"

type = "string"

option = ["--name", "-n"]

sources = ["man"]

[[commands.subcommand.field]]

id = "ctx_size"

label = "Context size"

type = "integer"

option = ["--ctx-size", "-c"]

sources = ["man"]

[[commands.subcommand.field]]

id = "temp"

label = "Temperature"

type = "number"

option = ["--temp"]

sources = ["man"]

[[commands.subcommand.field]]

id = "threads"

label = "CPU threads"

type = "integer"

option = ["--threads", "-t"]

sources = ["man"]

[[commands.subcommand.field]]

id = "port"

label = "Port"

type = "integer"

option = ["--port", "-p"]

sources = ["man"]

[[commands.subcommand.field]]

id = "detach"

label = "Run in background"

type = "boolean"

option = ["--detach", "-d"]

sources = ["man"]

[[commands.subcommand.task]]

id = "serve"

label = "Serve a model"

fields = ["model", "backend", "port", "detach"]

required = ["model"]

[[commands.subcommand.group]]

id = "basic"

label = "Basic"

fields = ["model", "backend", "port", "detach"]

[[commands.subcommand.group]]

id = "advanced"

label = "Advanced"

fields = ["name", "ctx_size", "temp", "threads"]

Use it with your dotfile manager

Same data, in the shape your tool already reads

Opens Otty and adds this tool to what it syncs

Opens otty://sync/add/ramalama. Otty ships with this catalog, so the link only has to name the tool — nothing is downloaded.

Every one of these keeps the credential file out.