explaingit

why1101-why/qiyanchatagent

Analysis updated 2026-05-18

21VueAudience · generalComplexity · 2/5Setup · easy

TLDR

A local-first Windows desktop app combining AI chat, note taking, PDF document Q&A, and a conversation practice simulator.

Mindmap

mindmap
  root((Qiyan))
    What it does
      Local-first AI workbench
      AI chat
      Inspiration notes
      ChatPDF
    Tech stack
      Vue
      Electron
      Node.js
    Use cases
      Bring your own key chat
      Notes with AI help
      PDF document Q&A
    Audience
      Individual Windows users
      Privacy conscious users
    Security
      DPAPI encrypted keys
      Local storage only

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Chat with an AI model of your choice while keeping your API keys and history stored locally.

USE CASE 2

Take and organize notes with AI assisted summarizing, polishing, and translation.

USE CASE 3

Ask questions about a PDF document and get answers with page references.

USE CASE 4

Practice conversation and soothing techniques using the built-in simulator.

What is it built with?

VueElectronNode.js

How does it compare?

why1101-why/qiyanchatagentduhbbx/skylerxbianen/lychee-os-demo
Stars212122
LanguageVueVueVue
Setup difficultyeasyeasyhard
Complexity2/52/54/5
Audiencegeneraldeveloperpm founder

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · easy Time to first run · 30min

Requires your own API key from a provider like OpenAI, Anthropic, or a local Ollama setup.

License terms are not stated in the explanation.

In plain English

Qiyan is a Windows desktop app that keeps your AI conversations, notes, and documents stored locally on your own machine rather than in the cloud. It bundles four main tools in one workbench: an AI chat, an inspiration notes section, a simulator for practicing how to soothe someone during a conversation, and a ChatPDF feature for asking questions about documents. For AI chat, you bring your own API key and can connect to OpenAI, DeepSeek, Anthropic, Gemini, Ollama, or any custom OpenAI-compatible endpoint. You can save several different model configurations at once, each with its own provider, parameters, and encrypted key, and switch between them freely. As of the latest update, chat also supports adding images and audio through a file button, clipboard paste, or drag and drop, with a preview before sending, though limits apply: up to six attachments per message, 8 MB per image, 20 MB per audio file, and 24 MB total per message. The inspiration notes tool supports folders, tags, full text search, Markdown preview, and export, with everything saved automatically on your computer. AI can help reorganize, summarize, polish, continue, translate, or extract to-do items from your notes, always showing a preview first so you choose whether to replace, insert, append, or copy the result. ChatPDF parses PDF files locally on your machine, displays every page of the document, and lets you search using both keywords and vector based matching, ask follow up questions, and see which page an answer came from. For security, your API keys are encrypted using Windows' built in DPAPI system through Electron's safeStorage feature, and are not included when you export a backup. The app is built with npm and Electron, and produces a Windows installer through its build scripts.

Copy-paste prompts

Prompt 1
Help me configure my own OpenAI-compatible API key to use with this Qiyan desktop app.
Prompt 2
Show me how to set up a separate model configuration for the ChatPDF embedding model in this app.
Prompt 3
Explain how attachments like images and audio work in the AI chat feature of this project.
Prompt 4
Walk me through building the Windows installer for this Electron app using npm.

Frequently asked questions

What is qiyanchatagent?

A local-first Windows desktop app combining AI chat, note taking, PDF document Q&A, and a conversation practice simulator.

What language is qiyanchatagent written in?

Mainly Vue. The stack also includes Vue, Electron, Node.js.

What license does qiyanchatagent use?

License terms are not stated in the explanation.

How hard is qiyanchatagent to set up?

Setup difficulty is rated easy, with roughly 30min to a first successful run.

Who is qiyanchatagent for?

Mainly general.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.