RunLocalAI
orchestrator
Open source
free (self-hosted)
4/5

OpenClaw

Personal AI agent with a local-first gateway architecture. Connects your local LLMs (Ollama, llama.cpp) to the messaging surfaces you already use — WhatsApp, Telegram, Slack, Discord, iMessage, and 20+ more. The runaway hit of early 2026 (renamed twice, now under non-profit foundation stewardship).

By Fredoline Eruo·Last verified May 6, 2026

Overview

Personal AI agent with a local-first gateway architecture. Connects your local LLMs (Ollama, llama.cpp) to the messaging surfaces you already use — WhatsApp, Telegram, Slack, Discord, iMessage, and 20+ more. The runaway hit of early 2026 (renamed twice, now under non-profit foundation stewardship).

Pros

  • Multi-provider fallback
  • Self-hostable
  • Cost routing

Cons

  • Setup overhead

Compatibility

Operating systems
macOS
Linux
Windows
GPU backends
n/a (proxies)
LicenseOpen source · free (self-hosted)

Get OpenClaw

Official site
https://openclaw.dev

Frequently asked

Is OpenClaw free?

OpenClaw has a paid tier (free (self-hosted)). Check the pricing page for current terms.

What operating systems does OpenClaw support?

OpenClaw supports macOS, Linux, Windows.

Which GPUs work with OpenClaw?

OpenClaw supports n/a (proxies). CPU-only inference is also possible but slow.

Reviewed by RunLocalAI Editorial. See our editorial policy for how we evaluate tools.