wenda logo

wenda

Free

6.1k

FreeFree tier
Inputs: textOutputs: text
Type
Open Source

About wenda

Wenda (闻达) is an open-source LLM calling platform designed for efficient content generation in specific environments. It addresses the computational resource limitations of individuals and small-to-medium enterprises, while ensuring knowledge security and privacy. The platform integrates a knowledge base supporting local offline vector libraries, local search engines, and online search engines. It supports a wide range of large language models including chatGLM-6B/chatGLM2-6B, chatRWKV, Llama, MOSS, Baichuan, Aquila-7B, InternLM, and online APIs such as OpenAI API and chatGLM-130b API. Additional features include Auto scripts (JavaScript plugins for custom workflows), conversation history management, intranet deployment, multi-user concurrent access, streaming output, quantization, and LoRA support.

Key Features

Knowledge base integration: local offline vector libraries, local search engines, online search engines
Multiple large language models: chatGLM-6B/chatGLM2-6B, chatRWKV, Llama, MOSS, Baichuan, Aquila-7B, InternLM, OpenAI API, chatGLM-130b API
Auto scripts: JavaScript plugins for custom dialog flows, external API access, online LoRA switching
Conversation history management
Multi-user concurrent use
Intranet deployment
Streaming output
CPU/GPU support with quantization
LoRA model support
Runs on hardware with 6GB VRAM

Pros & Cons

Pros
  • Free and open-source
  • Supports a wide range of LLMs (both offline and online APIs)
  • Integrated knowledge base for retrieval-augmented generation
  • Extensible with JavaScript Auto scripts
  • Privacy-focused: can be deployed on intranet, no data leakage
  • Works on low-resource hardware (e.g., 6GB VRAM)
Cons
  • Documentation primarily in Chinese, may be less accessible for non-Chinese speakers
  • Some models (Llama, MOSS, Baichuan without LoRA) are not recommended for Chinese users
  • Requires manual setup and configuration (Python environment, model downloads)
  • Limited community support outside Chinese ecosystem

Best For

Efficient content generation for specific environmentsPersonal and small-to-medium enterprise AI applications with limited computational resourcesKnowledge-secure and private AI deploymentsOffline or intranet-based LLM usage

FAQ

What is Wenda?
Wenda (闻达) is an open-source LLM calling platform that aims to provide efficient content generation while considering resource limitations and privacy concerns for individuals and small businesses.
Which models does Wenda support?
It supports offline models like chatGLM-6B/chatGLM2-6B, chatRWKV, Llama, MOSS, Baichuan, Aquila-7B, InternLM, and online APIs including OpenAI API and chatGLM-130b API.
Does Wenda require a GPU?
No, it supports both CPU and GPU. It can run on hardware with as little as 6GB VRAM with quantization.
Can I add custom functionality?
Yes, Wenda has Auto scripts using JavaScript that allow you to create custom dialog flows, access external APIs, and switch LoRA models on the fly.
Is Wenda free?
Yes, Wenda is free and open-source.