OpenClaw
Open-source, self-hosted personal AI assistant operating via messaging apps and a local gateway, with support for tools, sessions, memory, and automation.
OpenClaw
Open-source, self-hosted personal AI assistant operating via messaging apps and a local gateway, with support for tools, sessions, memory, and automation.
System classification
3A type of AI system whose primary interface is text-based or conversational interaction. Such a system answers questions, explains concepts, helps solve problems, and assists users through dialogue-based interaction.
Dla systemów, których podstawowym sposobem interakcji jest rozmowa w formie czatu.
AI system type focused on workflow automation, multi-step integration, process execution, and reducing manual user effort in operational or business tasks.
Dla systemów, których ważnym elementem jest automatyzacja workflow. Niezalecany dla systemów, które tylko odpowiadają na pytania bez warstwy procesowej.
A type of AI system capable of not only responding but also acting: planning steps, using tools, making decisions, and executing tasks in a more autonomous manner.
Dla systemów o realnej warstwie agentowej, z planowaniem, narzędziami lub wykonaniem działań. Niezalecany dla prostych chatbotów bez działania narzędziowego.
Modalities
9AI capabilities and tools
9Interaction modes
Integrations & connectors
9Kliknij ikonę, aby zobaczyć szczegóły integracji.
Applications
4Product features
6System tools
9Related AI tech and concepts
Similar and related systems
OpenClaw operates locally — user data remains on the device. The project has identified issues with prompt injection and unauthorized data access via malicious skills. Active hardening of security code is ongoing, and machine-checkable security models have been published.
The Cisco AI security team found that third-party skills can perform data exfiltration and prompt injection without user awareness. One maintainer warned that the project poses risks to users unfamiliar with the command line. Prompt injection vulnerabilities have not been assigned separate CVEs, as this is a known industry-wide issue with LLMs. The skill registry (ClawHub) has limited vetting. In March 2026, the Chinese government restricted OpenClaw use in state agencies on security grounds.