yuyonghao-123

DAG-based workflow engine supporting sequential, conditional, and parallel tasks with checkpoint persistence and event-driven execution.

通过12个标准化任务自动评估AI Agent在文件操作、数据处理、系统操作、健壮性与代码质量五大维度的综合能力。

Provides API for evaluating RAG quality, logical reasoning, and detecting hallucinations in AI-generated content with batch support.

Analyze code quality issues, detect code smells, and automatically apply refactoring suggestions with preview, apply, and rollback support.

基于 WebSocket 的多智能体 P2P 通信服务器，支持 Agent 注册、低延迟消息转发、RPC 调用、发布/订阅、能力发现及离线消息。

基于 ReAct 框架的双系统 AI 协调器，自动评估任务复杂度，智能切换快速执行和深度推理模式，支持多工具协作。

提供基于 Docker 和 GitHub Actions 的多阶段构建、CI/CD 流水线和健康检查的生产部署套件。

Provides role-based access control, input/output content review, sensitive operation confirmation, and comprehensive audit logging for secure system management.

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...

基于中文向量嵌入和知识图谱，实现语义搜索、实体提取及自动管理的高效记忆系统。

企业级文档检索系统，支持多模型语义嵌入、混合向量+关键词搜索、Cross-Encoder重排序与完整来源引用。

提供基于12项标准化任务的AI Agent能力评估，涵盖文件操作、数据处理、系统操作、健壮性和代码质量，自动评分生成报告。

Supports image understanding, OCR, speech-to-text, and text-to-speech synthesis with multi-voice and multimodal unified processing using OpenAI and Edge TTS.

Provides a complete AI agent observability solution with structured logs, metrics, distributed tracing, alert management, and a real-time monitoring dashboard.

基于 ReAct 框架的双系统 AI 代理协调器，自动评估任务复杂度并在快速执行与深度推理间智能切换，实现高效分层推理。

Autonomous AI decision engine with multi-objective optimization, risk assessment, decision trees, and reinforcement learning for robust decision-making.

基于 WebSocket 的多智能体 P2P 通信服务器，支持低延迟消息转发、RPC 调用、发布/订阅、能力发现及离线消息队列。

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comp...

Provides benchmark testing, A/B testing, performance regression detection, and simulation environment testing for agent evaluation.

读取本地 Word、Excel、PowerPoint、PDF 及多种文本格式文件，支持内容解析和摘要输出。

Secure sandbox for executing Node.js, Python, Go, and Rust code with timeout, CPU, and isolated temporary directory constraints.

Enables agents to self-monitor execution, reflect on tasks, analyze errors, and adjust learning strategies through metacognitive processes.

提供基于文档分块、简单词频嵌入及混合向量+关键词搜索的RAG 2.0检索系统，支持中英文本和来源引用。

Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).

自动监控、分析和优化OpenClaw技能性能，识别瓶颈并自动应用优化方案提升执行效率和稳定性。

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autono...

实现 n8n 与 OpenClaw Agent 的双向集成，支持Webhook触发执行、结果回调、认证验证及可观测性。

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express...

Provides error monitoring, automatic fallback, confidence evaluation, and multi-agent voting to maintain accuracy in multi-step workflows.

在受限 PowerShell 环境中安全执行脚本，支持命令白名单、超时控制、输出限制、文件隔离和执行前安全检查。

Analyzes agent performance and optimizes prompts, parameters, workflows, and strategies for continuous self-improvement.

在受限的 PowerShell 环境中安全执行脚本，支持命令白名单、超时控制、输出限制和文件路径隔离。