English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Gliding Horse Agent OS: An Open-Source Learning Platform for AI Agent Development

Forum topic · doiito · 2026-06-05

Summary

Gliding Horse is a fully open-source AI agent operating system developed by doiito, available on GitHub with complete design documentation. It orchestrates multiple AI agents through a PDCA (Plan-Do-Check-Act) cycle, acting as an infrastructure layer—a harness—that organizes agents into collaborative, auditable, self-evolving systems. The name references Zhuge Liang's legendary wooden ox and gliding horse transport devices from the Three Kingdoms era. The core orchestration layer is written in Rust, featuring a PDCA loop, 5W2H ontology, and an event bus for agent lifecycle management. Memory is implemented as a five-layer hierarchy with Sled+Qdrant (L0), Oxigraph (L2), and MESI consistency. Interoperability relies on JSON-LD 1.1 with named graphs; knowledge and skill graphs use RDF and SPARQL 1.1, with the skill graph spanning roughly 7,500 lines and designed for self-evolution. A perception engine provides 10 trigger types, anomaly deduplication, and 5W2H constraint checks. Production gateways include gRPC, OpenAI-compatible HTTP, and MCP. The project doubles as a learning platform for agent development and invites community discussion.

Welcome to fellow learners interested in AI agent development! I am the developer of Gliding Horse, and anyone interested is welcome to join the discussion and learn together.

Repository: https://github.com/doiito/gliding_horse

The project is fully open source, including detailed design documentation.

What is Gliding Horse?

Gliding Horse is an AI agent operating system that coordinates multiple AI agents through a PDCA (Plan-Do-Check-Act) cycle. It serves as an infrastructure layer—a harness for AI agents—organizing them into collaborative, auditable, and self-evolving systems, much like Zhuge Liang revolutionized logistics on treacherous mountain roads with his wooden oxen and gliding horses (muniu liuma).

> "We don't just build agents; we build the infrastructure to harness collective intelligence."

Core Technology Stack

| Layer | Technology | Responsibility | |---|---|---| | Core Orchestration (Rust) | PDCA loop · 5W2H ontology · Event bus | Agent orchestration and lifecycle management | | Memory System | L0: Sled+Qdrant · L2: Oxigraph · MESI consistency | Five-layer hierarchical memory | | Data Bus | JSON-LD 1.1 · @id/@type/@context · Named graphs | Universal interoperability layer | | Knowledge Graph | Oxigraph RDF · SPARQL 1.1 · Code AST | Unified storage across subsystems | | Skill Graph | RDF · 7,500 lines · Self-evolving | Dynamic cognitive network | | Perception Engine | 10 trigger types · Anomaly deduplication · 5W2H constraint checks | Proactive monitoring | | Gateway | gRPC · HTTP (OpenAI-compatible) · MCP | Production-grade interfaces |

The Story: From Ancient Wisdom to Modern Intelligence

During the Three Kingdoms period (220–280 AD), the legendary strategist Zhuge Liang, Chancellor of Shu Han, faced a daunting challenge: how to transport supplies efficiently for his northern expeditions across Sichuan's rugged mountain terrain. Traditional wheeled carts struggled on narrow, steep paths, while human porters had limited carrying capacity and quickly exhausted themselves.

His solution—the wooden ox and gliding horse—was an automated transport device that could traverse complex terrain with minimal human guidance. These mechanical marvels were not merely tools; they represented a paradigm shift: autonomous systems extending human capability.

Bridging Past and Present: The Agent Harness

Just as the gliding horse served as an intelligent harness for transporting supplies across impassable terrain, Gliding Horse Agent OS acts as an intelligent harnessing layer for AI agents:

| Ancient Innovation | Modern Implementation | |---|---| | Autonomous transport | Self-driven agent workflows | | Terrain adaptation | Dynamic complexity handling (7 levels) | | Load distribution | Parallel agent execution | | Minimal guidance | Proactive anomaly detection | | Mechanical reliability | Rust memory safety |

> "The skilled warrior adapts to circumstances and turns them to advantage, like pouring water into water." > — Zhuge Liang

This ancient wisdom guides the design philosophy: flexible orchestration that adapts to task complexity, rather than a rigid framework that forces tasks into predetermined molds.

Tags

#ai-agents#agent-os#rust#pdca#knowledge-graph#json-ld#open-source#mcp

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177980861