Yanshi Manual
Looking for the interactive overview, visual routing gallery, and 15-template matrix? Visit the Yanshi Product Home.
Yanshi is a multimodal content-production runtime written in Rust. Sources go in — an idea, a URL, uploaded files, a recording — and finished deliverables come out: reports, mind maps, audio overviews, slides, flashcards, quizzes, infographics, data tables, video overviews and domain engineering diagrams. Every deliverable runs through the same five stages (Sources → Planner → Generators → Renderers → Artifacts), described in RFC: Content Studio Runtime. It is not a coding-agent framework.
The runtime underneath offers two complementary execution styles that share one foundation:
- Deterministic DAG workflows — a
Flowof nodes with explicit inputs and outputs, dependency-ready concurrent scheduling, conditional execution, map/while loops, retry, timeout, and checkpointed recovery. Usually written as YAML and run withyanshi workflow run. - Agent-native loops —
ReActAgent, Plan-Execute, and multi-agent supervisors that plan, call tools, reflect, and keep memory, with structured step/event traces and hard runtime limits.
The two compose in both directions: AgentNode embeds an agent as a step of a
DAG, and WorkflowTool exposes a whole DAG as a tool an agent can call. Around
them sit Skills (declarative capability packages), MCP tools, RAG, memory,
tracing, the Harness governance shell (hooks, approvals, audit), and an HTTP
gateway with a Web UI.
How this manual is organized
| Part | Read it when you want to… |
|---|---|
| Content Studio Catalogue & Desktop | run the 15 built-in slide, video, paper, repo, and report generators or install Yanshi Studio desktop |
| Getting Started | configure providers and run a first workflow without API keys |
| Workflows | write, debug, and make DAG workflows resilient |
| Agents | run agent loops, multi-agent setups, and Harness sessions |
| Skills, Tools and Plugins | package capabilities and control what tools may do |
| MCP | consume or serve Model Context Protocol tools |
| Models, Multimodal and RAG | pick a provider/model and use image, audio, or retrieval |
| Observability | capture, replay, and inspect traces |
| Operations | deploy the gateway, workers, and database |
| Extending Yanshi | write custom runtimes, nodes, or strategies |
| Reference | check stability tiers, compatibility, and release notes |
| Design and Internals | understand the crate architecture, the Content Studio RFC, the evaluations and the other RFCs behind it |
API documentation for individual crates is generated by cargo doc; links
into source files from this manual open the file on GitHub.
The source of every page lives in the repository’s docs/ directory — use the
edit icon at the top of a page to propose a change.