Pinvou Agent
An open-source desktop AI agent workspace for work, design, and coding.
English · 简体中文 · 日本語
Download Preview · Website · QQ Group · Issues · Discussions · Security
Pinvou Agent is more than a chat window. It brings everyday work, visual design, and software development into one desktop workspace — designed for tasks that should end with a result, not just another chat response. Use tools, work with files, and build personal knowledge; bring a dedicated coding agent into a real project over ACP; or turn a prompt into a visual artifact you can continue editing.
Use a local model for a fully private loop, connect any OpenAI-compatible endpoint, and extend the agent with MCP servers, CLI connectors, Skills, and workflows.
🧭 One workspace, three ways to work
💼 Work: give the agent a real task
Combine attachments, personal knowledge, specialist personas, Skills, MCP tools, and workflows to research, analyze, write, and deliver reusable files — not just another block of chat text.
🎨 Design: from a prompt to an editable visual
Create posters and data visualizations in natural language. Open the result in design mode, select elements directly, and adjust copy, fonts, colors, dimensions, and layout — or keep describing changes and let the agent iterate on the current design.
💻 Code: bring a coding agent into a real project
Use Codex, Claude Code, or Kimi through ACP in the same desktop workspace. The coding agent can read and edit a real project or an isolated temporary workspace, run commands, and surface plans, tool steps, permission requests, and file changes. Sessions stay bound to their workspace and can be continued after restarting the app.
✨ Features
🎯 From conversation to deliverables
- Multi-session workspace with title search — messages, tool calls, and artifacts persist with each session
- Attachments for PDF, Office documents, images, and text — drag, drop, or paste them in
- Artifact panel automatically collects every file the agent creates or edits; preview, locate, and open them in one place
- Editable Markdown artifacts — edit directly, or select a passage and ask the agent to revise it
- Plan / YOLO modes — review the plan first for complex work, or execute directly when the task is clear
- Auxiliary chat — ask side questions while a task runs, in a per-task side session whose only tool is a server-enforced read-only view of that task's own history (ADR-0024), isolated from the task's execution context
🧠 Knowledge and memory
- Local knowledge base with file management, full-text and vector retrieval; attach multiple collections to one chat, enable or disable each independently, and retain collection and file provenance in answers
- Memory center captures long-term preferences and context, with explicit candidate review and confirmation
- Persona card pool — create, save, and apply specialist roles for different domains
- Skills, Commands, and workflows turn proven methods into stable, reusable capabilities
🔌 Real tools and connectors
- Unified tool store for local MCP servers, remote MCP servers, CLI tools, and API connectors
- OAuth / SSO authorization where supported — no manual key pasting
- Ready-made connectors for Feishu (Lark), DingTalk, WeCom, Tencent Meeting, Tencent Docs, Tencent ima, Obsidian, plus QCC, PatSnap, Canva, AMap Weather, and more
- Remote control — scan a QR code from your phone to view and steer the running workspace
🖥️ Built for daily operation
- Windows system tray — closing the main window keeps it running in the notification area; click the tray icon to return, or right-click → Exit to quit (details)
- Global bring-to-front shortcut (off by default,
Ctrl/Cmd+Alt+P) — enable it in Settings → General to summon the window with a key while it runs in the background
- Local voice input with on-demand speech model downloads
- Centralized monitoring of GPU, memory, disk, model service, and context usage
- Updates via GitHub Releases — in-app update checks are not enabled yet
- Sessions, settings, knowledge, and runtime extensions all live under
~/.pinvou3/
[!NOTE]
Whether data leaves your machine depends on the model and tools you enable. A local model with local tools stays fully local. Cloud models, remote MCP servers, and third-party connectors send the relevant requests to their respective services.
📸 Screenshots
🤖 Model Access
Pinvou Agent works with local vLLM and any OpenAI-compatible API. Save multiple model configurations in the app, give cloud configurations optional display aliases, and switch between them per session without changing the model identifier sent to the provider. Built-in templates cover local vLLM, DeepSeek, Kimi, Qwen, Doubao, MiniMax, Zhipu (GLM), MiMo, OpenAI, Anthropic, Gemini, and xAI — or fill in any custom compatible endpoint.
Local vLLM example:
This is the beginning of the README. Read the rest at the original. Read the full README ↗
