OpenClaw
The AI assistant that runs on your own computer, in your chats.
At a glance
Price not confirmed · Source review 2026-11-04- Price & billing
Open-source project with no paid tier, hosted service or token, according to the README; running it needs the user's own model provider access, whose prices are not stated in the text read, so no charge fact is recorded.
- Free allowance
Not separately confirmed. Check the current plan before relying on a free allowance.
- Best suited to
users who want an assistant in the chats they already use, since one Gateway covers Discord, iMessage, Slack, Teams, Telegram, WhatsApp and many more channels.; privacy-minded users who want data on their own hardware, since state, memory and credentials live locally and the tool phones home only for a daily version check by default.; builders who want swappable models, since models and agent harnesses such as Claude, Codex and local models are plugins that can be swapped.
Fit is editorial guidance, not a measured result.- Platforms
Access: not separately verified. Operating systems not separately verified.
Published-source facts and editorial guidance. No product test is implied. Confirm current conditions before purchase.
No product screenshot is claimed for this listing. Use the official website ↗ to inspect the current interface.
What to know before choosing
Good fit
users who want an assistant in the chats they already use, since one Gateway covers Discord, iMessage, Slack, Teams, Telegram, WhatsApp and many more channels.; privacy-minded users who want data on their own hardware, since state, memory and credentials live locally and the tool phones home only for a daily version check by default.; builders who want swappable models, since models and agent harnesses such as Claude, Codex and local models are plugins that can be swapped.
Limits and trade-offs
users who want a hosted, managed assistant with no install, since OpenClaw runs on the user's own computer through a local Gateway.; users who want to treat inbound messages as trusted by default, since the README warns to treat inbound messages as untrusted input.
Plans and free allowances
Open-source project with no paid tier, hosted service or token, according to the README; running it needs the user's own model provider access, whose prices are not stated in the text read, so no charge fact is recorded.
Evidence
Official repository ↗ (reviewed 2026-11-04), Official homepage ↗ (reviewed 2026-11-04)
Official published documentation reviewed; not a product test
Dates: Last reviewed 2026-11-04. Last reviewed is the latest source or editorial review date; it is not a content-change date.
A closer look at OpenClaw
OpenClaw is an open-source AI assistant that runs on the user's own computer and meets users in the channels they already use: Discord, iMessage, Slack, Teams, Telegram, WhatsApp and more than 20 others, plus native apps for macOS, iOS, Android, Windows and Linux. One local Gateway runs it as a personal or shared claw, state, memory and credentials stay on local hardware, models and harnesses are swappable plugins, and the README states it has no paid tier, hosted service or token.
Editorial guidance based on published documentation. The workflow below is a suggested starting point, not a measured product result.
When to choose OpenClaw
- users who want an assistant in the chats they already use, since one Gateway covers Discord, iMessage, Slack, Teams, Telegram, WhatsApp and many more channels.
- privacy-minded users who want data on their own hardware, since state, memory and credentials live locally and the tool phones home only for a daily version check by default.
- builders who want swappable models, since models and agent harnesses such as Claude, Codex and local models are plugins that can be swapped.
When to choose something else
- users who want a hosted, managed assistant with no install, since OpenClaw runs on the user's own computer through a local Gateway.
- users who want to treat inbound messages as trusted by default, since the README warns to treat inbound messages as untrusted input.
A practical starting workflow
- Install with the installer script for macOS, Linux or Windows, or install the published package with npm.
- Complete the onboarding wizard, which verifies model access, creates the workspace and configures the Gateway.
- Check the gateway status, open the dashboard Control UI, send a test message, then connect channels such as WhatsApp, Telegram or Slack.
Check before committing
- Testimonials on the homepage are social quotes, not product documentation; the README is the documented source used for workflow and install claims here.
- Security guidance in the README treats inbound messages as untrusted input, and DM-capable channels pair unknown senders only with care, so channel setup needs attention.
- Model and provider behaviour depends on the models and harnesses the user configures, which OpenClaw itself does not fix.
Common questions
What is OpenClaw?
An open-source AI assistant that runs on the user's own computer and meets users in Discord, iMessage, Slack, Teams, Telegram, WhatsApp and more than 20 other channels, plus native apps for macOS, iOS, Android, Windows and Linux.
Does OpenClaw have a paid tier?
No paid tier, hosted service or token, according to the README; state, memory and credentials live on the user's own hardware.
How do I install OpenClaw?
Install with the installer script for macOS, Linux and Windows, or install the published package with npm, then run onboarding and open the Control UI dashboard.
Compare approaches for this task
Sources and checks
Last source review is not a date of product testing. No rating or test result is implied by inclusion. Check the current plan and terms before buying.