Skip to content
Local-First AI Agent Platform

Yunque Agent

An AI that grows — with you.

Production-ready, local-first AI Agent platform. Single binary, 5-layer memory, hybrid RAG, 15+ channels.

Core Capabilities

A single binary, batteries-included AI Agent runtime

5-Layer Memory

Short-term, mid-term, long-term, editable, and knowledge graph — the most comprehensive memory architecture

Hybrid RAG

BM25 sparse + vector dense + RRF fusion + optional Rerank (Jina/Cohere/LLM)

15+ Channels

Telegram, Feishu, Discord, WhatsApp, Slack, Signal, WeCom, DingTalk, LINE, and more

Enterprise Security

Merkle audit chain, PII redaction, guardrails engine, federation protocol with HMAC signing

Single Binary

Zero-dependency Go binary. Deploy anywhere — Docker, K8s, or just download and run

Smart Routing

Auto model selection by complexity (fast/smart/expert), with circuit breaker and cost tracking

Why Yunque

Not just another AI framework — a complete Agent runtime

01

Local-First

Your data stays local. No cloud lock-in, no data leakage risk. Single Go binary, zero external dependencies, deploy in 5 minutes.

02

9 Algorithm Engines

RRF fusion, temporal decay, semantic distillation, causal chain extraction, KV summarizer, multi-hop reasoning — far beyond vector search.

03

Open Source

Plugin system + Skill Market + Workflow Engine — community-driven, build the AI you deserve.

Start Building Your AI Agent

Download, configure, chat — get your first Agent running in 5 minutes

© 2025 云鸢科技(青岛)有限公司 × Dream Lab