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

Gliding Horse: An Industrial AI Agent Platform Built with Rust

Forum topic · 小凯 · 2026-06-03

Summary

Gliding Horse (流马) is an open-source MIT-licensed AI Agent operating system implemented in Rust, Go, and TypeScript. Named after Zhuge Liang's legendary wooden ox and gliding horse, it treats Agent orchestration as a generalized PDCA (Plan-Do-Check-Act) execution model with seven complexity levels, supervised by a Supervisor Agent that selects execution modes from a 5W2H ontology. Its five-layer memory architecture (context window, in-memory RDF, SPARQL projection, Sled KV plus Qdrant) applies CPU cache-coherence thinking, including a MESI-style invalidation protocol, to Agent context management, reducing perceived latency by roughly 90 percent. JSON-LD 1.1 with IRIs serves as a universal semantic bus, unifying the knowledge graph (Oxigraph) and skill graph (Qdrant) for hybrid retrieval. Security is enforced at runtime through SyscallGate (JSON Schema, Ed25519 signatures, permission checks) inside Docker sandboxes, rather than via prompt instructions. A Center-Edge federation (Go Temporal orchestrator, Rust axum edge daemon, TypeScript VS Code plugin) avoids single points of failure. Reported throughput reaches 1000 ops/sec for KV reads and 500 ops/sec for graph writes.

Key points

  • Concept and positioning. Gliding Horse (流马) is an MIT-licensed, industrial-grade AI Agent operating system written in Rust, Go, and TypeScript. The name deliberately echoes Zhuge Liang's wooden ox and gliding horse, framing Agent orchestration as autonomous logistics rather than as a chat framework.
  • Generalized PDCA execution model. The PDCA cycle is elevated from a management metaphor into a seven-level computational model (L0 instant query to L6 emergency bypass). A Supervisor Agent dynamically selects PDCA depth based on a 5W2H ontology, replacing rigid templates.
  • Five-agent pipeline. A fixed industrial assembly line — Supervisor, Planner, Doer, Checker, Actor — replaces open-ended multi-Agent chat, with each role bounded by explicit responsibilities and a blackboard-backed workflow.
  • Five-layer memory with MESI coherence. L1 context window, L2 in-memory RDF, L3 SPARQL projection, and L0 Sled + Qdrant storage adopt CPU cache-coherence semantics (Modified, Exclusive, Shared, Invalid). A prefetch engine driven by Agent intent lowers perceived load latency from about 50 ms to about 2 ms.
  • JSON-LD 1.1 as the semantic bus. W3C-standard @context, @id, @type, and named graphs supply global entity identity, polymorphic discovery, conflict-free parallel writes, and progressive disclosure across five token-economy levels.
  • Unified knowledge and skill graphs. IRIs act as the bridge between Qdrant vector retrieval and Oxigraph SPARQL traversal, enabling hybrid semantic-plus-symbolic retrieval without duplicate-merge logic.
  • Self-evolving skill graph. Roughly 7,500 LOC of skill nodes carry success rate, usage count, and maturity metadata, and grow via experience writeback, a /learn mechanism, a /reduce extraction step, and an experimental-to-production maturity ladder.
  • 5W2H as task ontology. Each of the seven dimensions is filled at a specific pipeline stage and audited independently by the Checker, enabling precise rollback (What/Why failure reopens analysis; How/Where failure reopens planning; When/HowMuch failure downgrades or terminates).
  • Runtime security via SyscallGate. Tool calls are gated by Ed25519 signature verification, JSON Schema validation, and a permission matrix, then executed inside Docker sandboxes. A 10-trigger perception engine with 60-second anomaly deduplication escalates to human intervention.
  • Center-Edge federation. Go + Temporal orchestrate workflows and registries; a Rust + axum edge daemon runs local LLMs and Docker sandboxes; a TypeScript VS Code plugin provides the developer UI. The edge can run offline, removing single points of failure.
  • Reported performance. L0 KV reads reach ~1 ms at 1000 ops/sec, L2 graph writes ~2 ms at 500 ops/sec, L3 SPARQL projection ~15 ms at 66 ops/sec, ReAct turns 1-5 s, and idle memory footprint ~200 MB scaling with task size.
  • Open design philosophy. The project positions itself against prompt-based safety by asserting that trustworthy autonomy requires engineering-level hard constraints, so the Agent "cannot do wrong even if it wanted to."
  • Repository and resources

  • GitHub: https://github.com/doiito/gliding_horse
  • Design detail: docs/DESIGN_DETAIL.md
  • Design philosophy: docs/CORE_DESIGN_PHILOSOPHY.md
  • Protocol: proto/pdca_core.proto
  • License: MIT

Tags

#ai-agent#rust#agent-operating-system#json-ld#knowledge-graph#memory-hierarchy#pdca#open-source

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/177980779