
PI-Desktop
Local-first AI coding agent desktop: Electron + Rust host core + pi Agent Harness + user-installable plugins
The Lens
By Erik Loyd, SaaS CEO and former COO/CFO of an AWS Premier Partner.
Updated Oct 2026
PI-Desktop is a desktop app for AI coding agents: open a local repo, connect a model, and the agent reads code, edits files, runs commands and shows you the diff. Under the hood it runs pi, Mario Zechner's open source coding agent, wrapped in persistent sessions, a plan mode, subagents and a plugin system. It's free under LGPL-3.0, with no account.
Setup is a download for macOS, Windows or Linux. You bring the model: OpenAI, Anthropic, any OpenAI-compatible endpoint, or local models through Ollama or LM Studio. Requests go straight to your provider, keys sit in the OS keychain, and the app has no telemetry. It can also import your Claude Code, Codex and OpenCode sessions.
There's no paid tier; your only bill is the model. Solo: free, and a good GUI if terminal agents aren't your thing. Small teams: free, each person brings their own keys. Larger teams: no documented admin, SSO or central billing, so that's still Cursor or Copilot territory.
The catch: it's an early preview shipping three releases in a single day, so expect breakage. The author also publishes an optional plugin listing free community API relays. Don't send your code through an anonymous relay.
Free vs Self-Hosted vs Paid
fully freeFree: Everything. LGPL-3.0 desktop app with Agent, Plan and Goal modes, subagents, the Session Orchestrator for parallel worker sessions, MCP servers and a plugin marketplace. No PI-Desktop account, no relay, no PI-Desktop telemetry; API credentials are stored in the OS keychain.
Self-hosted: Nothing to host; it runs on your machine. Packages for macOS (Apple Silicon and Intel), Windows x64 and Linux x64/ARM64 (.AppImage, .deb, .rpm); Linux needs glibc 2.35+ (Ubuntu 22.04+, Debian 12+, Fedora 36+). Building from source needs Node.js 22.19+, pnpm 10+ and a stable Rust toolchain.
Paid: No paid tier. You pay your model provider (OpenAI, Anthropic or any OpenAI-compatible API) at their rates, or nothing if you run local models through Ollama or LM Studio.
Free with no paid tier. The real cost is your model API bill, or zero if you run local models through Ollama or LM Studio.
What to do by team size
- Solo
- free; download the app and add a model key or a local Ollama model
- Small team
- free; every developer configures their own provider keys
- Medium team
- free, but no shared admin, policy or billing controls are documented
- Large team
- look at Cursor or Copilot business plans for SSO, policy and central billing
Get tools like this every Wednesday
One featured tool, three on the radar. No fluff.
A low score is not a verdict on quality. Young and niche tools start low by design. How we calculate scores
License: GNU Lesser General Public License v3.0
Can link without copyleft infecting your code.
Commercial use: ✓ Yes
About
- Owner
- Lan (User)
- Stars
- 7,165
- Forks
- 694
Explore Further
More tools in the directory
everything-claude-code
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
286.7k ★hermes-agent
The agent that grows with you
256.3k ★dify
Production-ready platform for agentic workflow development.
159.3k ★