#3434th of 87 in Coding agents and assistants

pi-desktop

Desktop app that runs coding agents in persistent sessions with plugins

Documentation ↗ Repository on GitHub ↗

Stars: 6.9k
License: LGPL-3.0
Last commit: Oct 2026
Last release: Oct 2026
Language: TypeScript

Stars, last 29 weeks+6,833

46 on 25 Mar 20266,879 on 14 Oct 2026

From GitHub's daily star counts.

Checked 15 Oct 2026 on GitHub.

Overview

PI-Desktop is a desktop app for macOS, Windows and Linux that organizes agent work as projects and sessions, with Agent, Plan and Goal modes, Subagents and parallel Worker Sessions. It is built on the pi agent runtime and supports OpenAI, Anthropic, OpenAI-compatible APIs, Ollama and LM Studio. Plugins can add panels, widgets, tools, skills, themes and MCP servers. The README labels the 0.20.x line Early Preview.

Who it is for: Developers wanting a local desktop workspace for multiple coding agents

Strengths

Sessions persist across app launches, with branching, search and recovery of interrupted work
Model chosen per session: OpenAI, Anthropic, compatible gateways, Ollama, LM Studio
Imports local sessions from Claude Code, Codex, OpenCode and Pi
Local-first: no telemetry, no account, credentials kept in the OS Keychain

Weaknesses

README labels the 0.20.x line as Early Preview
Desktop app only; no Docker image or server deployment
Agent engine depends on the pi runtime packages
LGPL-3.0 license may constrain some embedding or redistribution uses

What it needs

no GPU
Needs pi-ai, pi-agent-core, pi-coding-agent, Node.js >=22.19 (build), pnpm >=10 (build), Rust toolchain (build)
Models: OpenAI, Anthropic, OpenAI-compatible APIs, Ollama, LM Studio

Also in Coding agents and assistants

See all 87

Also in Coding agents and assistants
Rank	Project	Score
1	claw-codeRust CLI coding agent harness using Anthropic and OpenAI-compatible APIs194.9k starsMIT	83 out of 100
2	ArchonYAML workflow engine that runs AI coding agents through fixed dev steps23.7k starsMIT	82 out of 100
3	oh-my-openagentTerminal coding agent with multi-model orchestration and git-backed memory70.1k starscustom license	80 out of 100
#4	Open SWELangChain coding agent that plans, implements and reviews pull requests11k starsMIT	80 out of 100
#5	opencodeTerminal coding agent with build and plan modes, plus a desktop app213.8k starsMIT	79 out of 100

How to choose

Check which models it can use: your own keys, local models, or only the vendor's.
See what it may do without asking (edit files, run shell, push) and how you approve.
Prefer agents that work in a branch or worktree you can throw away.

Health

Releases: 72 in the last 12 monthsLast one 2 days ago
Top contributor: 78% of commits2,690 of 3,440 in the last 12 months
Security advisories: NoneOn GitHub, in the last 12 months
OpenSSF Scorecard: Not checked

Read from GitHub, deps.dev and OpenSSF on 15 Oct 2026. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check.

License in plain words

LGPL-3.0 Custom terms

Use it at work: Check
Change it and rebrand it: Check
Sell it or host it for others: Check

Your part: GitHub could not match these terms to a standard license. Read the license before you use it at work, rebrand it or host it for others.

A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)

#34 of 87 in Coding agents and assistants on Archestack, as of 15 Oct 2026.

In your README

The badge updates twice a day.

[![Archestack](https://archestack.com/badge/vastsa/pi-desktop.svg)](https://archestack.com/best-of-vibe-coding/projects/pi-desktop/)

How badges work

On your site or blog

A card with the rank, score and signals, in light or dark to match the reader.

<iframe src="https://archestack.com/embed/best-of-vibe-coding/pi-desktop/" title="pi-desktop on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>

Preview the card

Best of Vibe Coding on GitHub

Each review comes from the project's README and facts we check on GitHub. The fix form opens with pi-desktop filled in.