AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
MCP verified MIT Self-run

Pinvou Agent

mcp-pinvou-pinvou-agent · by Pinvou

Open-source desktop AI agent for tools, files, knowledge, workflows, and real deliverables.

No reviews yet
0 installs
15 views
0.0% view→install

Install

$ agentstack add mcp-pinvou-pinvou-agent

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/mcp-pinvou-pinvou-agent)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
17d ago

Declared compatibility

Claude CodeClaude DesktopCursorWindsurf

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Pinvou Agent? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Pinvou Agent

[English](README.md) | [简体中文](README.zh-CN.md)

An open-source desktop AI agent that can use tools, work with files, build knowledge, and deliver real artifacts.

Website · CodeWhale engine · [Security](SECURITY.md) · [MIT License](LICENSE)

Pinvou Agent brings models, tools, personal knowledge, specialist personas, and reusable workflows into one desktop workspace. It is designed for work that should end with a result—not just another chat response.

Use a local model for a private loop, connect any OpenAI-compatible endpoint, or extend the agent through MCP servers, CLI connectors, Skills, and workflows.

What you can do

  • Turn conversations into deliverables — create and edit Markdown, documents, spreadsheets, code, and other files, then preview every generated artifact in one place.
  • Work with your own context — import PDF, Office, image, and text attachments; search local knowledge; and manage long-term memory explicitly.
  • Let the agent use tools — connect MCP servers, local CLI tools, and external APIs from a unified tool store.
  • Reuse reliable methods — package domain behavior as Skills, Commands, specialist personas, or multi-step workflows.
  • Choose how the agent acts — use Plan mode for review-first work or YOLO mode for direct execution.
  • Run locally or in the cloud — use local vLLM or any compatible model provider without locking the application to one vendor.

A workspace built for outcomes

Extend the agent with tools and connectors Preview and deliver generated artifacts

Core capabilities

| Area | Included | |---|---| | Agent runtime | Streaming responses, tool loops, sessions, hooks, compaction, Skills, and MCP | | Desktop workspace | Multi-session chat, attachment handling, artifact preview, and file editing | | Knowledge | Local files, full-text and vector retrieval, memory review, and knowledge management | | Automation | Scheduled tasks, reusable workflows, specialist personas, and structured deliverables | | Model access | Local vLLM, built-in provider templates, and custom OpenAI-compatible endpoints | | Extensibility | MCP servers, CLI connectors, APIs, Skills, Commands, and workflow packages |

> [!NOTE] > Whether data leaves your machine depends on the model and tools you enable. A local model with local tools can stay local. Cloud models, remote MCP servers, and third-party connectors send the relevant requests to their respective services.

Quick start

Prerequisites

  • 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 14 or later.

Run from source

git clone --recursive https://github.com/Pinvou/pinvou-agent.git
cd pinvou-agent/pinvou3-app
npm ci
npm run dev

If you cloned without submodules:

git submodule update --init --recursive

Connect a local model

Pinvou Agent supports local vLLM and custom OpenAI-compatible APIs. You can manage endpoints, models, and API keys from the application settings.

export DEEPSEEK_BASE_URL="http://127.0.0.1:8000/v1"
export DEEPSEEK_API_KEY="local-no-auth"
export DEEPSEEK_MODEL="your-model-name"

For a non-loopback plain HTTP endpoint in a trusted development network, explicitly set DEEPSEEK_ALLOW_INSECURE_HTTP=1.

Architecture

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.

| 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 | | Change desktop UI or system integration | pinvou3-app/ | | Fix a reusable engine issue | The CodeWhale fork, following the fork policy |

Repository layout

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

Development checks

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 --fast

See [CONTRIBUTING.md](CONTRIBUTING.md) for the current contribution workflow and [docs/fork-policy.md](docs/fork-policy.md) for CodeWhale maintenance rules.

Community and security

Pinvou Agent is licensed under the [MIT License](LICENSE). Please use GitHub Issues for reproducible bugs and focused feature requests, and GitHub Discussions for questions and ideas. Community support is best-effort; see [SUPPORT.md](SUPPORT.md).

Do not report security vulnerabilities in public issues. Use the private reporting channel in [SECURITY.md](SECURITY.md), or email security@pinvou.com.

Contributions follow our [Code of Conduct](CODEOFCONDUCT.md). Licensing, third-party attribution, SBOM, and brand-use boundaries are documented in [THIRDPARTYNOTICES.md](THIRDPARTYNOTICES.md), [docs/sbom.md](docs/sbom.md), and [TRADEMARKS.md](TRADEMARKS.md).


Pinvou Agent is under active development. The main branch and the latest release notes are the source of truth for current behavior.

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.