YaoApp / yao
āØ Yao is a single-binary runtime to build and run autonomous agents ā no Python, no Node.js, just define the role.
AI Architecture Analysis
This repository is indexed by RepoMind. By analyzing YaoApp/yao in our AI interface, you can instantly generate complete architecture diagrams, visualize control flows, and perform automated security audits across the entire codebase.
Our Agentic Context Augmented Generation (Agentic CAG) engine loads full source files into context on-demand, avoiding the fragmentation of traditional RAG systems. Ask questions about the architecture, dependencies, or specific features to see it in action.
Embed this Badge
Showcase RepoMind's analysis directly in your repository's README.
Repository Overview (README excerpt)
Crawler viewYao ā Build Autonomous Agents. Just Define the Role. Yao is an open-source engine for autonomous agents ā event-driven, proactive, and self-scheduling. **Quick Links:** **š Homepage:** https://yaoapps.com **š Quick Start:** https://yaoapps.com/docs/documentation/en-us/getting-started **š Documentation:** https://yaoapps.com/docs **āØ Why Yao?** https://yaoapps.com/docs/why-yao **š¤ Yao Agents:** https://github.com/YaoAgents/awesome ( Preview ) --- What Makes Yao Different? | Traditional AI Assistants | Yao Autonomous Agents | | ----------------------------- | ------------------------------------- | | Entry point: Chatbox | Entry point: Email, Events, Schedules | | Passive: You ask, they answer | Proactive: They work autonomously | | Role: Tool | Role: Team member | > The entry point is not a chatbox ā it's email, events, and scheduled tasks. --- Features Autonomous Agent Framework Build agents that work like real team members: ā¢ **Three Trigger Modes** ā Clock (scheduled), Human (email/message), Event (webhook/database) ā¢ **Six-Phase Execution** ā Inspiration ā Goals ā Tasks ā Run ā Deliver ā Learn ā¢ **Multi-Agent Orchestration** ā Agents delegate, collaborate, and compose dynamically ā¢ **Continuous Learning** ā Agents accumulate experience in private knowledge bases Native MCP Support Integrate tools without writing adapters: ā¢ **Process Transport** ā Map Yao processes directly to MCP tools ā¢ **External Servers** ā Connect via SSE or STDIO ā¢ **Schema Mapping** ā Declarative input/output schemas Built-in GraphRAG ā¢ **Vector Search** ā Embeddings with OpenAI/FastEmbed ā¢ **Knowledge Graph** ā Entity-relationship retrieval ā¢ **Hybrid Search** ā Combine vector similarity with graph traversal Full-Stack Runtime Everything in a single executable: ā¢ **All-in-One** ā Data, API, Agent, UI in one engine ā¢ **TypeScript Support** ā Built-in V8 engine ā¢ **Single Binary** ā No Node.js, Python, or containers required ā¢ **Edge-Ready** ā Runs on ARM64/x64 devices