Understand OpenClaw by Building One - 5: Many of Them

1. Every Agent Starts as a Loop 2. Gear up Your Agent 3. Pack the Conversation And Carry On 4. Beyond the CLI 5. Many of Them 6. Agents are Running, Your are Sleeping 7. More Context! More Context! All code snippets and working code bases are available at this repo . Many of Them One agent can't be an expert at everything. Neither should it try. You've built a capable agent. It can read files, search the web, run commands. But ask it to do everything and it struggles. Some tasks need specialized knowledge. Some tasks need focused context. The solution isn't a bigger agent - it's multiple smaller ones. Agent Discovery Agents are defined in AGENT.md files. A loader discovers them at startup: class AgentLoader : def discover_agents ( self ) -> list [ AgentDef ]: """ Scan agents directory and return list of valid AgentDef. """ return discover_definitions ( self . config . agents_path , " AGENT.md " , self . _parse_agent_def ) Routing: Match Tasks to Agents Right task to right agent? We nee