An open-source desktop AI agent that uses tools, works with your files, builds knowledge, and delivers real artifacts.
Website · CodeWhale Engine · Issues · Discussions · Security
Pinvou Agent is more than a chat window. It brings models, tools, personal knowledge, specialist personas, and reusable workflows into one desktop workspace — designed for work that should end with a result, not just another chat response.
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.
- 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
- Code sessions over ACP (e.g. Codex) bring a coding agent into the same workspace
- Local knowledge base with file management, full-text search, and vector retrieval
- 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
- 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 ima, Obsidian, enterprise knowledge bases, and legal / enterprise data services
- Remote control — scan a QR code from your phone to view and steer the running workspace
- Local voice input with on-demand speech model downloads
- Centralized monitoring of GPU, memory, disk, model service, and context usage
- In-app updates on Linux, with OTA delivery on macOS and Windows
- 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.
 |
 |
| Extend the agent with tools and connectors | Preview and deliver generated artifacts |
Pinvou Agent works with local vLLM and any OpenAI-compatible API. Save multiple model configurations in the app and switch between them per session. Built-in templates cover local vLLM, DeepSeek, Kimi, Qwen, Doubao, MiniMax, Zhipu, and MiMo — or fill in any custom compatible endpoint.
Local vLLM example:
export DEEPSEEK_BASE_URL="http://127.0.0.1:8000/v1"
export DEEPSEEK_API_KEY="local-no-auth"
export DEEPSEEK_MODEL="your-model-name"Endpoints, model names, and API keys can also be managed directly in the application settings. For a non-loopback plain HTTP endpoint in a trusted development network, explicitly set DEEPSEEK_ALLOW_INSECURE_HTTP=1.
- Git with submodule support
- Node.js and npm
- A current Rust toolchain
- The Tauri 2 system dependencies for your platform
- An accessible OpenAI-compatible model endpoint
The source tree supports Linux, Windows, and macOS. The initial macOS target is Apple Silicon on macOS 11 or later.
git clone --recursive https://github.com/Pinvou/pinvou-agent.git
cd pinvou-agent/pinvou3-app
npm ci
npm run devIf you cloned without submodules:
git submodule update --init --recursive
React + Vite UI
↕ Tauri commands / events
pinvou3-app (desktop orchestration)
↕ EngineHandle / AgentHarness
CodeWhale (agent engine submodule)
├─ OpenAI-compatible model services
├─ MCP servers and CLI connectors
└─ Skills, Commands, Hooks, and Compaction
CodeWhale provides the agent engine: model calls, streaming, tool execution, sessions, MCP, Skills, hooks, and compaction. pinvou3-app/ owns the desktop UI, runtime configuration, orchestration, and operating-system integration — it never re-implements engine capabilities.
| Extension goal | Where it belongs |
|---|---|
| Add a domain agent or tool bundle | A SKILL.md package |
| Connect an external API | An independent MCP server or connector |
| Guide model behavior | Bundle instructions (instructions.md) |
| Change desktop UI or system integration | pinvou3-app/ |
| Fix a reusable engine issue | The CodeWhale fork, following the fork policy |
pinvou3-app/ Tauri 2 + React/Vite desktop application
CodeWhale/ Agent engine submodule
pinvou3-app/resources/mcp-servers/
Independent local MCP servers
workflows/ Reusable workflows
scripts/ Tests, guards, build, and release helpers
docs/ Architecture and maintenance documentation
Run these commands from the repository root:
(cd pinvou3-app && npm run lint:ui)
(cd pinvou3-app && npm run build:ui)
(cd pinvou3-app && npm test)
(cd pinvou3-app/src-tauri && cargo test --lib -- --test-threads=1)
./scripts/fork-guard.sh --fastContributions are welcome! Please read CONTRIBUTING.md for the contribution workflow and CI gates, and docs/fork-policy.md for CodeWhale maintenance rules. By participating, you agree to our Code of Conduct.
- 🐛 GitHub Issues — reproducible bugs and focused feature requests
- 💡 GitHub Discussions — questions and ideas (community support is best-effort, see SUPPORT.md)
- 🔒 Do not report security vulnerabilities in public issues — use the private channel in SECURITY.md or email
security@pinvou.com
Licensing, third-party attribution, SBOM, and brand-use boundaries are documented in THIRD_PARTY_NOTICES.md, docs/sbom.md, and TRADEMARKS.md.
Pinvou Agent is under active development — the main branch and the latest release notes are the source of truth for current behavior.
MIT License · Made with ❤️ by the Pinvou team and contributors