AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Multi-Agent/
wanwu
wanwu logo

wanwu

Active·★ 2.4k·Apache-2.0·Updated 2026-10-23
★ Essential★ Trending

Wanwu is an enterprise-oriented, one-stop AI agent development platform, developed under UnicomAI and released under the Apache 2.0 license. The README groups its capabilities into modules: a model hub for unified access to hundreds of proprietary and open-source models (GPT, Claude, Llama and others, via OpenAI-style APIs, with inference backends such as vLLM and TGI for self-hosting), MCP integration with 100+ preselected industry interfaces, web search with multi-source data, and a visual workflow studio. It also has a feature comparison table, typical application scenarios and a section on adaptation to domestic Chinese databases (TiDB and OceanBase).

To run it, copy `.env.bak` to `.env`, set `WANWU_ARCH` (amd64 or arm64) and `WANWU_EXTERNAL_IP`, set a random `WANWU_BFF_JWT_SIGNING_KEY`, create the `wanwu-net` Docker network and start Docker Compose; images are pulled from Docker Hub on first run, and the web UI is on port 8081 with a default admin login. The workflow module lives in a separate repository (wanwu-workflow for v0.2.0 and later). The README is available in English, Simplified and Traditional Chinese. Much of it is feature description in marketing language, so evaluate by trying the Docker install.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-25.

License
Apache-2.0
Latest release
v0.6.5 · 2026-09-18
Last commit
2026-10-23
Contributors
61
Forks
145
Open issues and PRs
47
First published
2025-06-06

Source: GitHub, npm and PyPI public APIs.

#AI Agent#LLM#RAG#Workflow Automation#Enterprise AI
$ Install
$ docker compose --env-file .env --env-file .env.image.amd64 up -d
↗ Visit site★ GitHub
01

Features

01Unified LLM access and lifecycle management with multi-inference backend support
02Seamless integration with external tools via standardized MCP interfaces
03Low-code visual workflow orchestration for complex business processes
04High-precision RAG with multi-modal retrieval and advanced segmentation
05AI Agent development framework supporting function call, tool expansion, and private knowledge bases
02

Why choose it

+Covers the whole stack in one platform: model hub, MCP, web search, workflows and application building
+Permissive Apache 2.0 license, with self-hosting options for models
+Docker Compose deployment for amd64 and arm64
+Adaptation to TiDB and OceanBase for teams that need domestic databases
03

Trade-offs

!Heavy to run: a multi-service Docker stack with its own network, keys and database
!The README is mostly feature descriptions in marketing language, with few concrete examples or measurements
!The workflow module is a separate repository that changed at v0.2.0, so version pairing matters
!Default admin credentials exist; change them before exposing the platform
04

Maintenance check

ActiveChecked: 2026-10-27
Last commit
2026-10-23
Commits, last 90 days
100+
Releases, last 90 days
2
Latest release
v0.6.5 (2026-09-18)
Open issues
48
Recent issues with at least one comment
16/30
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 32, 15, 23, 21, 24, 11, 9, 1, 1, 6, 1, 0

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #74 请启用 Private Vulnerability Reporting 以方便安全漏洞的私下报告2 comments · 2026-07-08
  • #71 web端如何启用openclaw2 comments · 2026-07-01
  • #48 【严重BUG】发现智能体在调试环节,多次测试后,会失去已配置的工具信息,刷新与删掉重加都不行2 comments · 2026-04-01
  • #97 有没有部署要求低的版本1 comments · 2026-09-04
  • #64 快速启动方法--拉取镜像失败2 comments · 2026-06-03

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

OpenAI API Compatible Models
Native Support
Verified via docs
Claude
Supported
Verified via docs
Unicom Yuanjing
Native Support
Verified via docs
Ollama
Supported
Verified via docs
Tongyi Qianwen
Supported
Verified via docs
Volcano Engine
Supported
Verified via docs
06

Quick start

1
$ docker compose --env-file .env --env-file .env.image.amd64 up -d
07

Use cases

↳Intelligent Customer Service
↳Enterprise Knowledge Management
↳Business Process Automation
08

Alternatives

⚡Top VS:
VSdeer-flow★84.5k→VSii-agent★3.4k→VSragflow★93.0k→VSaiflowy★791→
deer-flow logo
deer-flow★ 84.5k
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
VSCompare→
ii-agent logo
ii-agent★ 3.4k
II-Agent: a new open-source framework to build and deploy intelligent agents
VSCompare→
ragflow logo
ragflow★ 93.0k
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
VSCompare→
aiflowy logo
aiflowy★ 791
AIFlowy is an enterprise-grade AI application development platform based on Java, comparable to products like Dify and Coze.
VSCompare→
agents logo
agents★ 1.5k
Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistants and multi-agent AI workflows.
VSCompare→
AIlice logo
AIlice★ 1.4k
AIlice is a fully autonomous, general-purpose AI agent.
VSCompare→
Pydantic AI logo
Pydantic AI★ 20.9k
GenAI Agent Framework, the Pydantic way. A Python agent framework designed for production with type safety at its core.
VSCompare→
PocketFlow logo
PocketFlow★ 11.3k
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
UnicomAI /
wanwu
↗

Enterprise AI agent development platform, Apache-2.0

2.4k145Apache-2.0
Last commit5d ago
StatusActive
CategoryMulti-Agent
Contributors61
Latest releasev0.6.5
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.