Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
View plugin → 
MemTensor
WeKnora
FeaturedOpen-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
Plugin facts
GitHub stars 21061
LicenseNOASSERTION
Primary languageGo
Last push2026-08-31T12:32:13Z
MaintainerTencent
Added to this directory2026-08-21
Screenshots
About this plugin
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
Install this DSH plugin
Copy the command below and run it in your DeepSeek Harness terminal.
dsh plugin add github:Tencent/WeKnora Plugins run with the permissions of your dsh process and may execute code at install time. Review the source repository and its license before installing. Pin the commit hash for reproducible installs. Plugin safety →
More about this plugin
WeKnora is an open-source, LLM-powered knowledge framework built for enterprise-grade document understanding, semantic retrieval, and autonomous reasoning.
Related guides
Learn how to choose, install, and use memory plugins.
About this plugin: WeKnora
What is WeKnora?
WeKnora is a memory plugin maintained by Tencent. Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
How do I install WeKnora?
Run dsh plugin add github:Tencent/WeKnora in your DeepSeek Harness terminal. The dsh CLI resolves the plugin from GitHub and installs it into your active profile. For reproducible installs, pin a commit hash: dsh plugin add github:Tencent/WeKnora#commit.
Is WeKnora free?
WeKnora is a community open-source project released under the NOASSERTION license. You can inspect its source and install it for free.
Related plugins
ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.
View plugin → 
agentscope-ai
memsearch
2537A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
View plugin → 
zilliztech