How much does Yuxi cost?

Yuxi is free and MIT-licensed. It is a self-hosted solution, so there is no SaaS subscription fee, but you must provide your own infrastructure and model API keys.

What models does Yuxi support?

Yuxi supports multi-model configurations through a unified config layer. It claims support for 15+ providers, including OpenAI, Claude, and DeepSeek, allowing you to choose the best model for your tasks.

Is Yuxi suitable for managed SaaS users?

No. Yuxi is strictly self-hosted with no SaaS tier. If you need a managed service or lack the infrastructure capacity to run a LangGraph platform, you should skip it.

What integrations does Yuxi offer?

The platform supports MCP tool integration and ships with connectors for Dify and Notion. It also includes built-in skills for image generation and report writing within its agent runtime.

How does Yuxi handle document retrieval?

It uses an agentic RAG pipeline that ingests PDFs, Office docs, and images. It extracts entities into a knowledge graph, allowing the agent to decide when and how to retrieve information.

Yuxi

Open-source AI agent platform that fuses agentic RAG with knowledge graphs on a LangGraph runtime.

Free· Free, MIT-licensed self-hostRAGMulti-model6.8 / 10

Visit website →

In short

Yuxi is a free, MIT-licensed self-hosted AI agent platform using LangGraph to combine agentic RAG with knowledge graphs for enterprise assistants.

Best for

Pick Yuxi if you're building a self-hosted enterprise assistant and want agentic RAG plus a knowledge graph out of the box.

Skip if

Skip it if you need a managed SaaS, prefer a vector-only RAG stack, or don't have infra capacity to run a LangGraph platform.

Yuxi (语析) is an MIT-licensed AI agent platform built on LangGraph that pairs retrieval-augmented generation with knowledge-graph construction. The runtime gives each agent a sandboxed virtual workspace, supports MCP tool integration, sub-agents for orchestration, and async workers for long-running jobs, plus built-in skills for image generation and report writing.

What sets Yuxi apart is the "agentic RAG" pipeline: it ingests PDFs, Office docs and images, extracts entities and relationships into a knowledge graph, and lets the agent decide when and how to retrieve. It targets teams building internal enterprise assistants who want self-hosted control over their data and aren't satisfied with vanilla vector-only RAG. There is no SaaS tier; you run it yourself.

The platform claims 15+ model providers through a unified config layer (OpenAI, Claude, DeepSeek, and others) and ships connectors for Dify and Notion. Expect the usual self-hosted overhead - infra, model keys, evaluation tuning - in exchange for full ownership.

Editor's take

Yuxi is a credible pick for teams who've outgrown naive vector RAG and want knowledge-graph reasoning without writing their own LangGraph harness. It's clearly aimed at self-hosters and the docs lean Chinese-first, so budget some integration time. Promising, but treat it as a framework, not a finished product.

— The AI Tool Bible editorial team

Pros

✅ Open-source under MIT with full self-host control
✅ Combines RAG with knowledge graphs rather than vector-only retrieval
✅ Sandboxed agent runtime with MCP, sub-agents and async workers
✅ Pluggable across 15+ LLM providers via unified config

Cons

⚠️ Self-host only - no managed offering or SLA
⚠️ Smaller community vs. LangChain/Dify; docs lean Chinese-first
⚠️ Knowledge-graph pipeline adds operational complexity over plain RAG

Use cases

agentic-ragknowledge-graphsenterprise-agentsdocument-qamcp-tools

Frequently asked

How much does Yuxi cost?: Yuxi is free and MIT-licensed. It is a self-hosted solution, so there is no SaaS subscription fee, but you must provide your own infrastructure and model API keys.
What models does Yuxi support?: Yuxi supports multi-model configurations through a unified config layer. It claims support for 15+ providers, including OpenAI, Claude, and DeepSeek, allowing you to choose the best model for your tasks.
Is Yuxi suitable for managed SaaS users?: No. Yuxi is strictly self-hosted with no SaaS tier. If you need a managed service or lack the infrastructure capacity to run a LangGraph platform, you should skip it.
What integrations does Yuxi offer?: The platform supports MCP tool integration and ships with connectors for Dify and Notion. It also includes built-in skills for image generation and report writing within its agent runtime.
How does Yuxi handle document retrieval?: It uses an agentic RAG pipeline that ingests PDFs, Office docs, and images. It extracts entities into a knowledge graph, allowing the agent to decide when and how to retrieve information.