# wenda-LLM/wenda

闻达：一个LLM调用平台。目标为针对特定环境的高效内容生成，同时考虑个人和中小企业的计算资源局限性，以及知识安全和私密性问题

Repository: https://github.com/wenda-LLM/wenda
Canonical: https://ross.abutalabs.com/products/wenda
Language: JavaScript
License: AGPL-3.0
License Family: copyleft
Topics: chatglm-6b, chatrwkv, rwkv
Last push: 2025-01-23T12:55:35+00:00

## Health v2 (maintenance only)
Score: 31/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 3, release rhythm 35, longevity 89
- inputs: {"age_days": 1257, "days_push": 587, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6159, forks 784 (observed 2026-08-28T04:09:36.728647+00:00)

## What it is
Wenda is a self-hosted LLM invocation platform designed for efficient content generation in constrained environments, integrating local/offline models (ChatGLM, RWKV, Llama, Baichuan) and online APIs. It combines knowledge base retrieval (local vector store or search engines), multi-user support, and extensible JavaScript Auto scripts for custom workflows.

## Use cases
- run a local chatgpt-like assistant on my own hardware
- build a private knowledge base chatbot over my documents
- query local LLMs with retrieval-augmented generation
- deploy an intranet LLM service for a small team
- chat with chatglm-6b or rwkv offline
- extend an llm chat app with custom automation scripts

## When to choose
- you need a private, offline LLM deployment with limited compute
- you want RAG over local documents or intranet search engines
- you need multi-user access and conversation history in a self-hosted setup

## When to avoid
- you only want a hosted API with no local model management
- you need production-grade enterprise LLM orchestration with vendor support
- you primarily work with non-Chinese models and ecosystems

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, rag, chatbot, search-engine, plugin-system, http-server
- domain: large-language-models, chatbots, self-hosted, artificial-intelligence
- platform: python, self-hosted, cross-platform
- tags: llm-platform, knowledge-base, local-llm, chatglm, rwkv, offline-deployment, auto-scripts, privacy, retrieval-augmented-generation, web-server, docker

## Member repositories
- wenda-LLM/wenda (main) score 31

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:36.728647+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:47:29.390932+00:00, confidence not recorded.
  - readme: https://github.com/wenda-LLM/wenda (fetched 2026-08-28T04:09:36.728647+00:00, sha 831967969294)
- Data as of 2026-08-30T08:39:29.467469+00:00.