English | 简体中文 | UpdateLog | Help Docs
ChatWiki is a workflow automation platform focused on the WeChat ecosystem, dedicated to making every official account a super AI agent. It fully integrates the open capabilities of the official account platform, allowing you to build WeChat ecosystem applications through drag-and-drop, enabling features like one-click rewriting of official account articles and AI-curated comment replies.
-
Industry First: Automatic reply to private messages for unverified official accounts, supporting text, voice, images, mini-program cards, video messages, etc.
-
WeChat Workflows: Integrates trigger scenarios such as user private messages, comments, follows, unfollows, menu clicks, etc. Supports various processing steps like replying to private messages, tagging fans, generating draft articles, publishing articles, and more.
-
Knowledge Base Synchronization: Supports scraping articles and materials from official accounts to build a knowledge base with one click.
-
Workflow Orchestration: Conversational workflows, plugin workflows, including basic workflow nodes, bidirectional MCP, Agent mode, and user interaction.
-
Document Knowledge Base: Supports URL reading, batch document import, API integration, AI-based segmentation, QA segmentation, parent-child segmentation. Supports knowledge graphs, hybrid vector search, and visual exploration of knowledge graphs.
-
QA Knowledge Base: Automatically extracts QA knowledge from uploaded documents, supports automatic clustering of unknown questions, and summarizes common FAQs from human conversations.
-
Human Handoff: Handles general user inquiries via bot, while also supporting human staff. Issues that the bot cannot resolve can be escalated to human客服, with multi-agent collaborative assignment.
-
Model Support: Supports over 20 mainstream global models, including DeepSeek R1, doubao pro, qwen max, OpenAI, Claude, etc.
-
Multiple Deployment Options: Offers desktop client, supports publishing as a WebApp, and embedding into websites, official accounts/service accounts, wecome staff, WeChat store staff, etc.
-
MCP & API Integration: Allows integration of external MCP services or publishing workflows as MCP services. Complete OpenAPI interface for easy integration with existing business systems.
-
Multi-account Permission Management: Three-tier permission system (admin, editor, viewer) ensures data isolation. IP whitelist and permanent login logs.
- 🌍 Free Trial URL: chatwiki.com
- 🖼️ Screenshots:
ChatWiki Community Edition is deployed using Docker and can be installed in just a few simple steps:
# Install Docker
sudo curl -sSL https://get.docker.com/ | CHANNEL=stable sh
# Clone the project
git clone https://github.com/zhimaAi/chatwiki.git
cd chatwiki/docker
# Start the service
docker compose up -d
# Start using it, access via IP:port (ensure the specified port ${CHAT_SERVICE_PORT}, default 18080, is open)
# Default username: admin
# Default password: chatwiki.com@123
For any issues or suggestions during installation and deployment, please contact us or refer to the help documentation for assistance. You can also check the guides below.
-
Frontend: vue.js
-
Backend: golang + python
-
Database: PostgreSQL16 + pgvector + zhparser
Feel free to contact us for help or to provide suggestions to improve ChatWiki. You can reach us through:
- Help: Check the help documentation
- Email: Send an email to jarvis@2bai.com.cn to contact us.
- WeChat: Scan the QR code below to join the ChatWiki tech community group. Please add the note "chatwiki" when adding.
For the complete changelog, please click 👉️👉️UpdateLog.md
2026/10/10
1.Agent bot: Persona supports inserting variables
2.[STD] Added support for creating multiple Agents: 3 for the Enterprise Edition and 10 for the Flagship Edition
3.[STD] Fixed a known issue where applications could not be selected in the Xiaohongshu trigger
4.[STD] Custom models: Added Tencent Hunyuan as a new model provider
5.[STD] Added a workflow call limit for free-version accounts that have not consumed credits for three days
6.Fixed a known authentication issue in bot API key management
7.LLM calls: Fall back to text for multimodal input types unsupported by the model
2026/09/18
1.[STD] Cloud version human handoff settings: User intent-based handoff now supports custom recognition criteria
2.[STD] Added credit usage statistics to the cloud version
3.[STD] Fixed an issue where the trigger count in human handoff keyword statistics did not change based on the selected
time range
4.[STD] Cloud version VIP system: Added the Flagship Edition
5.System security optimization: Plugin download URLs are now retrieved from the server
6.[STD] Limited the number of workflow calls in the free cloud version
7.Workflow HTTP request node: Adjusted the timeout duration
8.[STD] Fixed incorrect model names being stored for custom model statistics
9.Knowledge base retrieval test: The browser now remembers entered content, and the page has been optimized
2026/09/04
1.[STD]Q&A knowledge base recycle bin: Added one-click emptying
2.External Service: Updated the page design for PC and H5 based on Alibaba Cloud
3.Increased the sensitive word limit to 20,000
4.Fixed an issue where Context was not passed in some embedding scenarios
This project follows the ChatWiki Open Source License. The ChatWiki Open Source License is based on the Apache License 2.0, but with additional restrictions:
- ChatWiki is free for individual users, including non-commercial or commercial activities conducted by individuals.
- Any company, organization, institution, or team that uses ChatWiki for commercial purposes must contact us to obtain a commercial license.
- When using ChatWiki's frontend components, you may not remove or modify the "ChatWiki" logo, trademark, or copyright notice contained therein.
The full license text can be found in the LICENSE file. For commercial licensing, please contact us.