clawrium 26.5.4

CLI tool for managing AI assistant fleets

Clawrium - An aquarium for *claws

Fleet management for AI agents on your local network.

Documentation · Issues · Roadmap · Discord

---

How it works

Clawrium uses Ansible under the hood for SSH-based orchestration. You run clm from your control machine, which talks to target hosts over SSH. No agents, no containers, no Kubernetes complexity - just processes running on hosts with a unified management layer.

Why Clawrium

You're running multiple AI agents - coding assistants, internal tools, experiment harnesses - across machines on your network. Without Clawrium, you SSH into each box, manage configs individually, lose track of token spend, and have no unified view of what's running where.

Clawrium gives you kubectl-style fleet control for AI agents:

• One CLI, all hosts. Add machines to your fleet and deploy any agent type to any host.
• Specialized agents. Each agent does one job and does it well. Instead of one overloaded assistant, run a fleet of purpose-built agents - a coding agent, a review agent, a research agent - each with its own context, data, and configuration isolated from the rest.
• Local inference. Use hardware you already have - Mac Minis, NVIDIA DGX Spark, spare servers - as inference providers. Run smaller open models like Gemma, GPT-4o-mini, Kimi, or Llama locally and point multiple agents at them.
• Model experimentation. Swap models across agents to compare performance without touching individual configs.
• Lifecycle management. Upgrades, rollbacks, secrets rotation, backups - handled.
• Token tracking & guardrails. See spend across your fleet. Set limits before someone's experiment burns through your API budget.

What is a "Claw" or an Agent?

A Claw or an Agent is a general-purpose AI assistant that runs on a host in your network. Unlike coding-focused assistants (Copilot, Cursor), Claws are designed for broader tasks:

• OpenClaw - Open-source general assistant
• ZeroClaw - Lightweight assistant for resource-constrained hosts
• IronClaw - High-performance assistant for demanding workloads

Clawrium manages the lifecycle of these agents across your fleet - install, configure, start, stop, upgrade, monitor.

Who this is for

Clawrium is for engineers running AI agents in non-trivial setups - home labs, dev teams, research groups. If you have more than one agent running on more than one machine, this tool exists for you.

It is not a hosted platform. There's no dashboard, no SaaS, no account signup. It's a Python CLI that talks to your machines via Ansible. You own everything.

Quickstart

What You'll Need

Requirement	Why
Python 3.10+	Runtime for clm CLI
uv	Fast Python package installer
SSH access to a remote host	Clawrium manages agents over SSH
API key (Anthropic, OpenAI, etc.)	Agents need inference providers

Install & Run

# Install
uv tool install clawrium

# Or run without installing
uvx --from clawrium clm --help

5-Minute Setup

# Initialize config
clm init
# → Created /home/user/.config/clawrium/config.yaml

# Set up SSH to your host
clm host init 192.168.1.100 --user myuser
# → Checking SSH connectivity...
# → SSH key copied to 192.168.1.100

# Add the host to your fleet
clm host add 192.168.1.100 --alias worker-1
# → Host 'worker-1' added

# Add an inference provider
clm provider add anthropic --type anthropic
# → Enter API key: ********
# → Provider 'anthropic' configured

# Install OpenClaw agent
clm agent install --type openclaw --host worker-1 --name my-assistant
# → Installing openclaw on worker-1...
# → Agent 'my-assistant' installed

# Configure and start
clm agent configure my-assistant
clm agent start my-assistant
# → Agent 'my-assistant' started

# Check fleet status
clm ps
# NAME           TYPE      PROVIDER  HOST      STATUS   UPTIME
# my-assistant   openclaw  openai    worker-1  running  2m

# Chat with your agent
clm chat my-assistant
# → Connected to my-assistant
# → Type your message...

# Or open the local web dashboard
clm gui
# → Clawrium GUI starting on http://127.0.0.1:36000 — press Ctrl+C to stop

You should see: A running agent in clm ps output with status running.

→ Full setup guide: ric03uec.github.io/clawrium

Key Concepts

Concept	What it is
Host	A machine in your network running one or more agents
Agent	An installed AI assistant instance managed by Clawrium
Agent Type	The implementation/runtime class of an agent
Agent Name	The unique identifier for an installed agent instance
Registry	Platform-defined agent types with versions, dependencies, and templates

FAQ

1. What operating systems are supported?

Right now, Clawrium is only tested on Ubuntu hosts and Ubuntu control machines.

Other Linux distributions may work, but they are not currently part of the test matrix.

2. Which agents are supported today?

OpenClaw is officially supported and tested end-to-end.

Hermes (Nous Research) is supported in 🚧 In Development status — install, configure, and a local OpenAI-compatible HTTP API on 127.0.0.1:8642 are wired end-to-end. clm chat and external messaging gateways are not yet supported for hermes. See the Hermes Support Matrix for details.

Additional agent types are planned.

3. Is Claude subscription supported?

No. Clawrium supports API keys only, by design.

4. Which channels are supported?

Discord and Slack are supported for OpenClaw.

Additional channels are planned.

5. Does Clawrium install Docker or Kubernetes?

No. Clawrium does not require Docker or Kubernetes. It manages agent processes over SSH using Ansible.

6. Can I manage multiple hosts with different agent types?

Yes. You can register multiple hosts and run different agent types on each host from the same clm control node.

7. Why doesn't it support x-agent and y-feature?

I'm building Clawrium in my spare time, so I prioritize my own use cases first.

If you want support for a specific agent type or feature, please open an issue and send a PR. See CONTRIBUTING.md for contribution guidelines.

8. Why not Kubernetes?

Two reasons:

1. Most AI agent runtimes don't support it. These run as local processes, not containerized services. They expect a home directory, local config files, and direct access to the host. Wrapping them in containers adds friction with no payoff.

2. K8s is overkill for local fleets. You're managing 3-10 machines on a LAN, not orchestrating microservices across cloud regions. Kubernetes brings etcd, control planes, networking overlays, RBAC, and a learning curve that dwarfs the problem. You don't need a container scheduler - you need to SSH into a box and run a process.

Clawrium uses Ansible under the hood instead. Ansible gives you idempotent host management, secrets handling, and multi-machine orchestration without requiring anything on the target machines beyond SSH. Clawrium sits on top of Ansible and adds the agent-specific layer: lifecycle management, token tracking, model swapping, and fleet-wide visibility.

Tech Stack

Python · Typer · ansible-runner · uv

Contributing

git clone https://github.com/ric03uec/clawrium && cd clawrium
make test       # Run tests
make lint       # Check style
make format     # Auto-format

Issues are the source of truth. See CONTRIBUTING.md for the full workflow.

License

Apache 2.0