P
🤖AutomatisationIntermediate5 steps

NanoClaw: the lightweight containerized OpenClaw

NanoClaw is the minimalist, containerized version of OpenClaw. Same open-source philosophy, same ClawHub ecosystem, but with a smaller footprint and a Docker-first approach. Where OpenClaw targets developers wanting a full ecosystem, NanoClaw is for those who want a ready-to-go AI agent in seconds: `docker run` and you're set. Ideal for edge computing, Raspberry Pi or Kubernetes setups. NanoClaw shares the same MIT license and skill standard as its big brother, making it easy to move to full OpenClaw when your needs grow.

dockeropen-sourceedgelightweightopenclawagent-iacontainers

For who

DevOps developers, IoT tinkerers, and teams looking for an embedded, portable AI agent easy to deploy via Docker.

Input

Type: text
Format: json

Requetes HTTP vers l'API NanoClaw avec prompt, skills selectionnes et contexte optionnel.

steps (5)

1

Run the container

info

Execute `docker run -d --name nanoclaw ghcr.io/openclaw/nanoclaw:latest` to start the container in the background.

2

Provide an LLM key

info

Pass your API key (Anthropic, OpenAI or local Ollama) via the `-e LLM_API_KEY=...` env var.

3

Mount a skills volume

info

Mount a local volume to persist installed ClawHub skills across container restarts.

4

Expose the API

info

Open port 3000 to interact with NanoClaw over HTTP or WebSocket from your scripts and applications.

5

Orchestrate if needed

info

Deploy multiple NanoClaw instances via Docker Compose or Kubernetes for horizontal scaling.

Output

Type: text
Format: json

Reponses JSON de l'agent : actions, resultats, logs structures.

Example

Input

POST /api/v1/tasks with `{"prompt": "Fetch Paris weather and send it to my Discord webhook"}`

Output

NanoClaw installs the weather skill and calls the configured Discord webhook. Returns a JSON {status: success, duration_ms: 842}.

Customization

ParameterDescriptionDefault
Image DockerTag de l'image a utiliser (latest, stable, ou version epinglee).latest
Persistance des skillsVolume Docker pour garder les skills entre redemarrages./data/skills
Mode LLMLocal via Ollama ou API distante (Anthropic/OpenAI).Anthropic

Technical Notes

Image ~150 MB. Runs with 1 GB RAM. MIT license. Compatible with ClawHub skills and agentskills.io.