An agent framework that connects LLMs to the real world. Give AI a persistent identity, memory, and the ability to actually do things.
A long-running daemon that orchestrates everything. It maintains connections to messaging platforms, routes messages to agents, and manages sessions.
Connect to Telegram, WhatsApp, Discord, Signal, Matrix, and more. Same agent, consistent personality across all platforms.
Maintains context within sessions. When context grows too large, it's compacted (summarized) to fit within the model's window.
Unlike stateless chatbots, OpenClaw agents have a workspace - a folder of Markdown files that define who they are and what they remember.
The LLM has no persistent memory on its own. These files are the memory. If the agent wants to remember something, it writes to disk. Next session, it reads the file and "remembers."
Follow a message from arrival to response. Click through each step to see how OpenClaw processes requests.
Hooks let you run code when things happen in OpenClaw. They're TypeScript functions triggered by events.
command:new
User issues /new (new session)
command:reset
User issues /reset
command:stop
User issues /stop
gateway:startup
Gateway starts
agent:bootstrap
Before workspace files are injected (can mutate them)
It can intercept and modify workspace files before they're injected into the system prompt. Inject different personas based on time of day, who's messaging, or any other condition.
For cyber security and enterprise contexts, this architecture enables powerful capabilities.
SOC procedures, past incidents, known configurations - always available to the agent.
Same agent across Slack, Teams, email triggers - unified experience.
Hooks can trigger on session events, integrate with SIEM/SOAR.
Command logging, session transcripts - full accountability.
Sandboxing, exec policies, tool allowlists - enterprise-grade security.
Tailor communication style per channel or audience.