PI-Desktop

Most coding agents live inside a terminal, an editor extension, or a hosted service.

PI-Desktop gives the agent workflow a workspace of its own.

Projects, sessions, files, reviews, previews, models, permissions, extensions, and long-running work live together — without tying your workflow to a single editor, model vendor, or hosted runtime.

Same agent. Different approval boundaries.

Agent — let it inspect the tree, patch files, run commands, test, and keep going.

Plan — review the approach before execution. The agent researches first, produces an immutable implementation plan, and waits for approval.

Goal — lock the objective and acceptance criteria. The agent decides how to get there.

Privileged tools still go through the permission layer in every mode.

Explore all screenshots →

PI-Desktop is designed around persistent projects and long-running sessions rather than disposable chat threads.

• Manage multiple projects and sessions
• Pin, archive, branch, and search conversations
• Queue prompts while an agent is already running
• Reference files with @
• Use slash commands
• Review diffs and command output
• Keep streaming responses checkpointed so interrupted work can recover whenever possible

Large tasks do not have to live in one context window.

Delegate independent work to background Subagents for:

• codebase exploration
• multi-file implementation
• research and investigation
• test analysis
• adversarial review

Each Subagent runs in its own context and reports its result back to the parent agent.

PI-Desktop has multiple extension layers, from lightweight reusable instructions to full desktop integrations.

Plugins can extend PI-Desktop with:

Install plugins locally or through the marketplace using the .piplug package workflow.

Build your first plugin →

Give agents reusable instructions and workflows. Skills can be installed globally or activated for individual projects.

Connect external tools and services through Model Context Protocol servers without baking them into the desktop application.

PI-Desktop can also be controlled by an external MCP Agent. Start the app with PI_DESKTOP_MCP_CONTROL=1, then read the loopback endpoint and bearer token from mcp-control.json in the Electron user-data directory.

The control endpoint supports project, session, and Agent workflows plus a reviewed desktop operation catalog. It is disabled by default, binds to loopback only, and grants the calling local Agent the same authority as the desktop for those operations. confirm: true is not a user prompt.

Extensions written for the pi CLI can run inside PI-Desktop's agent unchanged.

A plugin can list them under contributes.agentExtensions, or Plugins → Import pi extension can wrap an existing extension file or directory in a plugin.

They can register tools, slash commands, and hooks on every turn, tool call, and provider request. They run with the same access as the agent's own tools, gated by the agent.extension permission.

PI-Desktop does not hardcode your agent workflow to one model vendor.

Use:

• OpenAI and Anthropic
• OpenAI-compatible APIs
• hosted model gateways
• local gateways such as Ollama and LM Studio
• multiple models under the same provider
• provider OAuth accounts where supported

Per-model configuration can include context windows, output limits, reasoning controls, temperature, and other model-specific behavior.

The model is a replaceable part of the workflow — not the workflow itself.

PI-Desktop is local-first, not "nothing ever touches the network."

There is no required PI-Desktop account and no mandatory PI-hosted relay between your machine and your model provider.

If you use a remote model provider, the context required for that model request is sent to that provider according to its own privacy policy.

1. Download PI-Desktop
   Get the latest build from GitHub Releases.

2. Connect a model
   Open Settings → Model configuration, choose a provider or compatible API, and add your credentials.

3. Open a project
   Add any local repository or project directory from the sidebar.

4. Choose Agent, Plan, or Goal
   Start immediately, approve an implementation plan first, or define the outcome and let the agent choose the path.

5. Review the result
   Inspect edits in the Review panel, check command output, preview the application, and continue without leaving PI-Desktop.

Download the latest release →

Packaged builds can check GitHub Releases for updates and surface new versions inside the application.

Windows NSIS and Linux AppImage can download and install updates in-app. macOS, Linux deb/rpm, and the Windows portable executable open the releases page.

ldd --version

electron PI-Desktop-<version>-linux-x64.asar

xattr -r -d com.apple.quarantine /Applications/PI-Desktop.app

Windows releases of PI-Desktop are digitally signed with free code signing provided by SignPath.io, using a certificate from the SignPath Foundation.

Already using another coding agent?

PI-Desktop can import local sessions from:

• Claude Code
• Codex
• OpenCode
• Pi

Open Settings → Import to bring existing work into the desktop workspace.

PI-Desktop separates the user interface, privileged host capabilities, and the agent loop.

flowchart TB
 UI["React Renderer<br/>Chat · Projects · Reviews · Settings"]
 Electron["Electron Main<br/>Desktop orchestration"]
 Rust["Rust Host Core<br/>Permissions · Filesystem · SQLite · Secrets"]
 Agent["pi Agent Sidecar<br/>Agent loop · Models · Streaming"]
 Provider["Model Provider<br/>Cloud or Local"]
 UI --> Electron
 Electron --> Rust
 Electron --> Agent
 Agent <--> Rust
 Agent --> Provider

The renderer has no Node integration.

The Rust Host Core owns privileged workspace operations, permissions, persistence, and secrets. The pi Agent Sidecar owns model interaction and the agent loop. Electron coordinates the desktop lifecycle while keeping those responsibilities separated.

Read the architecture specification →

PI-Desktop builds on the excellent work of the pi-mono ecosystem.

The agent runtime uses pi-ai and pi-agent-core.

Pi provides the agent engine. PI-Desktop turns it into a persistent desktop workspace.

The desktop application also uses technologies including Electron, React, TypeScript, Rust, SQLite, Vite, Tailwind CSS, Shiki, Mermaid, KaTeX, TypeBox, and i18next.

PI-Desktop is an early preview under active development.

The current 0.14.x line includes the desktop shell, streaming agent runtime, Agent / Plan / Goal workflows, permission-aware workspace tools, projects and sessions, session imports, local MCP control, MCP / Skills / Subagents, background delegation, multi-provider model configuration, plugins and marketplace support, context checkpoints, notifications, release notes, and cross-platform packaging.

Current priorities include:

• macOS tagged-release qualification
• installer upgrade and rollback qualification
• continued runtime and session-recovery hardening
• stronger plugin sandboxing and publisher verification
• broader UI-driven end-to-end coverage

Follow development through the project board and milestones.

git clone https://github.com/vastsa/PI-Desktop.git
cd PI-Desktop
pnpm install
cargo build -p host-core
pnpm build:js
pnpm dev

pnpm typecheck
pnpm lint
pnpm test

pnpm docs:dev
pnpm docs:check

Useful references:

• Documentation
• Specification index
• Architecture
• Product scope
• Plugin development
• E2E test plan
• Release runbook
• Repository agent guide

Issues, bug reports, feature proposals, documentation improvements, plugins, Skills, MCP integrations, and pull requests are welcome.

For larger changes, opening an issue first makes it easier to align the implementation with the existing architecture and product contracts.

When working in the repository, start with AGENTS.md and the specification index.

Report an issue · View open issues · Build a plugin

Not by a lone genius, but by a token-powered construction crew.

This project was created with the models below.

• Linux.Do — Share, discuss, and follow development with the community.

PI-Desktop is licensed under the GNU Lesser General Public License v3.0.

See LICENSE for details.