Claude Skill
PeiranLi0930/Plugin-GBT
Plugin-GBT is an open-source OpenClaw plugin that makes AI agents smarter and more token-efficient, reducing costs while boosting reasoning performance.
Overview
Repository
Install this Skill
npm installRegistry
Summary
Plugin-GBT is an open-source OpenClaw plugin that enhances AI agents with smarter reasoning and token efficiency, reducing costs while maintaining high performance.
[!NEW!] OpenClaw 插件助力智能体更聪明且节省代币!
Key features
- Token-efficient agent optimization
- Enhanced reasoning capabilities
- Open-source and customizable
- Easy integration with existing agents
Use cases
- Reducing API costs in AI applications
- Improving agent response quality
- Building cost-sensitive AI assistants
- Optimizing token usage in chatbots
README excerpt
# GBT (Gated Behavior Tree) Plugin GBT turns OpenClaw's throwaway execution logs into a reusable experience tree. That changes the economics of agent work. Without GBT, every similar task forces the agent to plan again, reason again, debug again, and spend expensive tokens again. With GBT, successful runs and failed runs are distilled into reusable operational memory. The next time a similar task appears, OpenClaw can stop wasting tokens on rediscovering the same path and instead execute against a learned tree of concrete experience. And when a covered task fails, GBT does not just shrug and move on. It queues that failed trajectory, waits for idle time, asks for approval, silently replays the task inside OpenClaw, localizes the broken step, repairs it, verifies the repaired run against the real environment, and only then writes the repaired experience back into the tree. This is not a prompt wrapper. It is a persistent experience system for OpenClaw. ## Research Origin This plugin is built on the core ideas from the paper: **Traversal-as-Policy: Log-Distilled Gated Behavior Trees as Externalized, Verifiable Policies for Safe, Robust, and Efficient Agents** Peiran Li, Jiashuo Sun, Fangzhou Lin, Shuo Xing, Tianfu Fu, Suofei Feng, Chaoqun Ni, Zhengzhong Tu https://arxiv.org/abs/2603.05517 The plugin version in this repository focuses on turning agent logs into reusable experience trees, routing covered tasks onto cheaper single-step executors, and replaying failed trajectories to repair them into reusable experience. As noted below, this current release does **not** implement the paper's safety-gate mechanism. ## What GBT Actually Does - Distills completed OpenClaw runs into reusable, non-task-specific macro nodes. - Stores both success and failure paths in
Topics
No topics yet.