# UnicomAI/wanwu

China Unicom's Yuanjing Wanwu Agent Platform is an enterprise-grade, multi-tenant AI agent development platform. It helps users build applications such as intelligent agents, workflows, and rag, and also supports model management. The platform features a developer-friendly license, and we welcome all developers to build upon the platform.

Repository: https://github.com/UnicomAI/wanwu
Canonical: https://ross.abutalabs.com/products/wanwu
Language: Go
License: Apache-2.0
License Family: permissive
Topics: ai, llm, mcp, rag, wanwu, workflow, agentic-ai, agentic-framework, ai-agent, ai-agent-development-framework, ai-agents-framework, development, genai, open-ai, golang, agent
Last push: 2026-07-31T09:26:31+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 95, release rhythm 94, longevity 32
- inputs: {"age_days": 453, "days_push": 33, "days_rel": 40, "gap_med": 7, "n_releases_24m": 46}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2448, forks 134 (observed 2026-08-28T04:06:52.811535+00:00)

## What it is
Yuanjing Wanwu is China Unicom's enterprise-grade, multi-tenant AI agent development platform built in Go. It provides all-in-one tooling for building intelligent agents, workflows, RAG knowledge bases, and model management under an Apache-2.0 license.

## Use cases
- build an enterprise AI agent platform
- create a chatbot grounded on company documents
- set up a RAG knowledge base over internal PDFs and policies
- orchestrate multi-step AI workflows visually
- manage and serve multiple LLMs in one place
- deploy a multi-tenant agent platform for teams
- connect agents to external tools via MCP

## When to choose
- you need a self-hosted, commercial-friendly (Apache-2.0) agent platform
- you want RAG, workflows, and model management bundled in one system
- you need multi-tenant support for enterprise deployment
- you prefer a Go-based backend with Docker deployment

## When to avoid
- you only need a lightweight agent library inside an existing Python app
- you want a fully managed SaaS without self-hosting
- your stack is tightly coupled to LangChain-style Python ecosystems

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, rag, llm-inference, workflow-automation, mcp, chatbot, web-framework
- domain: artificial-intelligence, large-language-models, self-hosted, developer-tools
- platform: self-hosted, go
- tags: agent-platform, multi-tenant, enterprise-ai, knowledge-base, fde-toolchain, model-management, ai-agents, retrieval-augmented-generation, docker, linux, web-server

## Member repositories
- UnicomAI/wanwu (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:52.811535+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:30:27.658670+00:00, confidence not recorded.
  - readme: https://github.com/UnicomAI/wanwu (fetched 2026-08-28T04:06:52.811535+00:00, sha 4d0663fbcf14)
- Data as of 2026-08-30T08:39:29.467469+00:00.