Compose an agent
Pick a recipe or framework starter. See the patterns it instantiates. Ask the catalog’s resident LLM about your composition — should you swap a pattern? Add one? Trade off?
OpenClaw-RL Agent SDKs
Train personalised LLM agents by turning live multi-turn conversations into fully-asynchronous RL training signals across terminal, GUI, software-engineering, and tool-call settings.
Patterns it instantiates (5)
- Agent-as-a-Judge — Evaluate an agent's full trajectory (steps, tool calls, intermediate states) by another agent rather than scoring only the final output.
- Evaluator-Optimizer — One LLM generates; another evaluates and feeds back; loop until criteria are met.
- Event-Driven Agent — Trigger the agent on external events (webhooks, message queues, file changes) instead of user requests or schedules.
- Process Reward Model — Train a verifier that scores each reasoning step rather than only the final answer.
- Tool Use — Let the LLM produce typed calls against an external toolkit instead of producing free-form text the surrounding system has to parse.
Ask the catalog expert
⌘/Ctrl + Enter to send. Set OPENAI_API_KEY in .env if the catalog reports it is disabled.