clawhub install ramalama-cliπ About This Skill
name: ramalama-cli description: Run and interact with AI agents. metadata: openclaw: emoji: "π¦" requires: bins: - ramalama anyBins: - docker - podman install: - id: brew kind: brew formula: ramalama bins: - ramalama label: Install ramalama CLI (brew) - id: uv kind: uv formula: ramalama bins: - ramalama label: Install ramalama CLI (uv)
Ramalama CLI
Use when an alternative AI agent is better suited to a task. For example, working with sensitive data or solving simple tasks with a cheap and local agent, or accessing specialist models with unique capabilities.
Overview
Use this skill to execute ramalama tasks in a consistent, low-risk workflow.
Prefer local discovery (--help, local config files, existing project scripts) before making assumptions about flags or runtime defaults.
Prefer ramalama when tasks need:
hf://, oci://, rlcr://, url://)Preflight
Run these checks before first invocation in a session:
ramalama version
podman info >/dev/null 2>&1 || docker info >/dev/null 2>&1
ramalama run --help
If serving on default port, verify availability:
lsof -i :8080
Decision Matrix
ramalama run "" ramalama run ramalama serve ramalama chat --url "" ramalama rag ramalama bench and ramalama perplexity inspect, pull, push, convert, list, rmUsage
Start with top-level discovery:
ramalama --help
ramalama version
Apply global options before the subcommand when needed:
ramalama [--debug|--quiet] [--dryrun] [--engine podman|docker] [--nocontainer] [--runtime llama.cpp|vllm|mlx] [--store ] ...
Use command-level help before invoking unknown flags:
ramalama --help
Known-Good Recipes
1) One-shot run
ramalama run granite3.3:2b "Summarize this in 3 bullets: "
2) Detached service + API call
ramalama serve -d granite3.3:2b
curl http://localhost:8080/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{"model":"granite3.3:2b","messages":[{"role":"user","content":"Hello"}]}'
3) Direct Hugging Face source
ramalama serve hf://unsloth/gemma-3-270m-it-GGUF
4) RAG package then query
ramalama rag ./docs my-rag
ramalama run --rag my-rag granite3.3:2b "What are the auth requirements?"
5) Benchmark and list benchmark history
ramalama bench granite3.3:2b
ramalama benchmarks list
Reliability Defaults
For agent automation, prefer explicit and deterministic flags:
ramalama --engine podman run -c 4096 --pull missing granite3.3:2b ""
Recommended defaults:
--engine explicitly when environment is mixed-c/--ctx-size on constrained hosts--pull missing for faster repeat runsTroubleshooting
--engine podman
podman machine list and start machine if needed
timed out during startup:podman logs
- reduce context (-c 4096) and retry
-p Notes
serve exposes an OpenAI-compatible endpoint for external clients.list --json, inspect --json) for robust parsing in automation.ramalama chat --url when the model is already served elsewhere.π‘ Examples
Start with top-level discovery:
ramalama --help
ramalama version
Apply global options before the subcommand when needed:
ramalama [--debug|--quiet] [--dryrun] [--engine podman|docker] [--nocontainer] [--runtime llama.cpp|vllm|mlx] [--store ] ...
Use command-level help before invoking unknown flags:
ramalama --help
π Tips & Best Practices
serve exposes an OpenAI-compatible endpoint for external clients.list --json, inspect --json) for robust parsing in automation.ramalama chat --url when the model is already served elsewhere.