Tencent’s WeChat team has expanded its open-source knowledge framework WeKnora with a new v0.8.0 release that adds cross-session long-term memory and rounds out its Skills and code execution stack. WeKnora was originally built to turn enterprise documents into retrieval-augmented generation, or RAG, knowledge bases that support search and question answering. Over time, the framework added Agent, Model Context Protocol, or MCP, and Skills support. In the latest update, WeKnora can store user profile details, preferences, facts and tasks, then call that information back in later conversations. The system does not activate automatically extracted memories by default; users must confirm them first. Skills are now packaged as standalone workspace resources and can be installed from ClawHub, SkillHub, GitHub, GitLab or zip files. During task execution, the agent can also enter Docker, E2B or Cube sandboxes to run commands, read and write files, and send generated files back to the chat window. Admins can restrict which networks those sandboxes may access.
Tencent’s WeChat team has continued to expand WeKnora, its open-source knowledge framework, with the latest v0.8.0 update adding cross-session long-term memory while also filling out its Skills system and code execution environment.
WeKnora was initially focused on turning enterprise documents into RAG knowledge bases for retrieval and question answering. It later added Agent, MCP and Skills support. With the new release, the framework can now remember user profile information, preferences, facts and tasks, then reuse them in later chats.
Automatically extracted memories do not take effect right away. They still require user confirmation before activation.
On the tools side, Skills have been turned into standalone workspace resources. They can be installed from ClawHub, SkillHub, GitHub, GitLab or zip files. When an Agent executes a task, it can also enter Docker, E2B or Cube sandboxes to run commands, read and write files, and send generated files directly back to the chat window. Administrators can limit which networks those sandboxes are allowed to access.
WeKnora remains centered on enterprise knowledge use cases, but it is no longer limited to pulling answers from documents. The framework is now moving toward putting knowledge, memory, tools and execution into a single Agent system.
This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan. Disclaimer:
The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.
Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.
