Practical overview
When it fits
Use Wanwu when an organization needs a self-hosted environment that combines agent development with RAG, workflow orchestration, model management, MCP integration, or interface-level automation.
Who it is for
- Enterprise teams developing AI agents and internal automation.
- Forward Deployed Engineers delivering AI applications into customer systems.
- Developers needing workflow, knowledge-base, MCP, or GUI-agent capabilities in one platform.
Documented uses
- Build agent applications for enterprise use cases.
- Create RAG and knowledge-base assistants from documents and URLs.
- Orchestrate business processes with visual workflows.
- Develop agents that interact with applications through their user interfaces.
- Manage models and deploy multiple agent projects in a multi-tenant environment.
Requirements & limits
The repository is public, marked active in the supplied record, and licensed under Apache-2.0. The documentation describes self-hosted deployment across Linux, Docker, and server environments.
- Whether the team can operate a self-hosted Go and Docker-oriented environment.
- Whether visual workflow orchestration is useful for the target business process.
- Whether document retrieval, GraphRAG, or ontology-based reasoning is required.
- Whether agents need MCP, API, code, or GUI-level integrations.
- Whether multi-tenant operation and model management matter for the deployment.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Set up the Wanwu development platform
Prepare a self-hosted Wanwu environment for enterprise agent development.
Before you start
- A Linux, Docker, self-hosted, or server environment.
- Go 1.24.0 or newer, as listed in the repository README.
- Access to the public Wanwu repository.
Steps
Obtain the Wanwu source from the public repository.
Prepare the documented Go and deployment environment.
Use one of Wanwu's documented deployment paths, including the visual platform route.
Create agents, workflows, or question-and-answer applications through the platform interface.
Expected outcome
A Wanwu environment prepared for building agent applications, workflows, or RAG-based experiences.
Guide limitations
- The available documentation identifies deployment paths but does not provide enough verified command-level setup detail here to describe a complete installation sequence.
Compare options for Retrieval-augmented applications
These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.
| Project | Documented purpose | Platform | Access and requirements |
|---|---|---|---|
| Wanwu Agent Platform | Build agent applications for enterprise use cases. | Docker, Linux, Self-hosted, Server | The repository is public, marked active in the supplied record, and licensed under Apache-2.0. The documentation describes self-hosted deployment across Linux, Docker, and server environments. |
| Hydra — hassenhamdi | Ingest Markdown documents into a searchable knowledge base. | CLI, Self-hosted, Server | The repository is public and identifies an MIT license. Local setup requires Python 3.10+, a Gemini API key and Docker with Docker Compose for Milvus. |
| Agentnexus | Configure agents from stored models, tools, prompts, memory, and knowledge sources. | Docker, Self-hosted, Server | The project is documented as open source, and its README states that it uses the MIT License. |
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 1 October 2026
- Original website title
- UnicomAI/wanwu · Official homepage title · retained in its source language