CowAgent vs OpenClaw

CowAgent

MIT software with seven releases in 90 days, memory kept as plain files in the owner's workspace and three per-session permission modes. Source and Docker installs default to full-access, no action asks for approval, and an open report of 31 July 2026 says group members could reach the owner's files through the bot.

OpenClaw

Self-hosted under the MIT licence, with state, memory and credentials kept on the owner's machine and no paid tier. A fresh install runs tools on the host with full access, no approval prompt and no sandbox, and the project has published 722 security advisories since January 2026, 14 of them critical.

CowAgent

1. Set agent_permission_mode to workspace-write or read-only before connecting any channel. Source and Docker installs default to full-access
2. Keep the bot out of group chats that include other people. Any member who mentions it reaches the same tools as the owner
3. Set web_password before changing web_host to 0.0.0.0. The password is empty by default
4. Set external_api_token to enable POST /v1/chat/completions, and send conversation_id to keep one session. The model field does not select a model
5. Run it in a container for a hard boundary. The docs and the source both say the permission modes are not isolation

OpenClaw

1. Set a session permission mode of guarded or workspace, or tools.exec.mode, before connecting mail. The default runs host commands without approval
2. Turn on agents.defaults.sandbox for any agent that reads mail, web pages or attachments. Sandboxing is off by default
3. Set tools.message.crossContext.allowAcrossProviders and allowWithinProvider to false to confine sends to the current conversation
4. Route incoming mail to a restricted reader agent, as the IMAP and Gmail guides show, and deny gateway, cron, sessions_spawn and sessions_send for it
5. Run openclaw security audit after setup, and treat the Gateway token as an owner credential. POST /tools/invoke accepts it with full operator access