WeKnora
A local knowledge base tool open-sourced by Tencent's WeChat team. It supports RAG question answering, task execution, MCP, skills, and client features, can generate Wiki pages with knowledge links, and can be invoked as a component by AI tools such as Claude Code.
Timeline (last 90 days)
WeKnora supports knowledge Q&A, task execution, MCP, skills, clients and other features, and can generate Wiki pages with knowledge links, and can be called as a component by AI tools such as Claude Code.
WeKnora officially recommends containerized deployment, but the standard method has relatively high memory requirements (about 4-8GB).
The official WeKnora documentation lists three deployment forms: production environment (containerized/K8s), learning environment (binary), and desktop application (not yet released).
The WeKnora learning environment uses a file-based database and in-memory storage, requires no additional dependencies, and is ready to use after unzipping.
The default listen address configured for the WeKnora learning environment is localhost:8215.
WeKnora's data encryption key corresponds one-to-one with the data directory, and changing the .env file or clearing the data may cause decryption to fail.
The current binary version of WeKnora has no logout button, but you can switch accounts by clearing cookies through the browser developer tools.
All Facts (8)
WeKnora项目采用Go语言开发
90%UnverifiedWeKnora supports knowledge Q&A, task execution, MCP, skills, clients and other features, and can generate Wiki pages with knowledge links, and can be called as a component by AI tools such as Claude Code.
50%UnverifiedWeKnora officially recommends containerized deployment, but the standard method has relatively high memory requirements (about 4-8GB).
50%UnverifiedThe official WeKnora documentation lists three deployment forms: production environment (containerized/K8s), learning environment (binary), and desktop application (not yet released).
50%UnverifiedThe WeKnora learning environment uses a file-based database and in-memory storage, requires no additional dependencies, and is ready to use after unzipping.
50%UnverifiedThe default listen address configured for the WeKnora learning environment is localhost:8215.
50%UnverifiedWeKnora's data encryption key corresponds one-to-one with the data directory, and changing the .env file or clearing the data may cause decryption to fail.
50%UnverifiedThe current binary version of WeKnora has no logout button, but you can switch accounts by clearing cookies through the browser developer tools.
50%