Paseo: One Cockpit for Claude Code, Codex, Copilot and More Coding Agents

Self-hosted multi-agent orchestration (19.5k stars): Claude Code, Codex, Copilot, OpenCode, Pi, Antigravity and Muse Code behind one interface, running on your own machines with your full dev environment; a daemon (WebSocket + MCP) coordinates them, with Electron desktop / Expo iOS & Android / web / CLI clients, voice tasking, phone follow-up and parallel agents. In the same family as Orca, differentiating on self-hosting, multi-provider and mobile voice; monorepo ships plugin/skills ecosystem and an end-to-end encrypted relay.

getpaseo/paseo20kTypeScriptNOASSERTION1 min read

One-liner: a single cockpit for multiple coding agents

Paseo (getpaseo/paseo, 19.5k stars) is a self-hosted platform that orchestrates multiple coding agents from one interface: Claude Code, Codex, Copilot, OpenCode, Pi, Antigravity and Muse Code behind the same entry point, running on your own machines with your full dev environment — your tools, your configs, your skills. Five clients (Electron desktop, Expo iOS/Android, web, CLI) connect to one local daemon (WebSocket API + MCP server); tasks can be dictated by voice, monitored and merged from your phone, and multiple agents run in parallel. Like Orca and its peers, it tackles the fragmentation of "AI coding output grew, but switching interfaces, managing sessions and following up across devices didn't"; Paseo's differentiators are self-hosting, multi-provider and mobile-first voice. The monorepo is cleanly layered: server (daemon orchestration) / app (Expo client) / cli / desktop / relay (end-to-end encrypted transport) / website, with a plugin system and skills directory — an open ecosystem.

AI Coding Coding Agent Agent orchestration Self-Hosted Multi-agent

SOURCE LINKS

https://github.com/getpaseo/paseo https://paseo.sh

Related Projects

nextlevelbuilder/ui-ux-pro-max-skillMIT

UI UX Pro Max: a 132k-star AI coding skill that generates complete design systems from 192 industry reasoning rules

An open-source AI skill that injects design intelligence into coding agents: one request generates a complete design system (style + colors + typography + anti-patterns) from 192 industry reasoning rules, 79 searchable UI styles, 192 color palettes, 74 font pairings, 25 chart types and 22 tech stacks (React, Next.js, Astro, SwiftUI, Flutter, Three.js and more). The v2.0 flagship Design System Generator runs five parallel searches (product type, style, palette, landing pattern, typography) through a BM25-ranked reasoning engine to output pattern, style, colors, typography, effects, anti-patterns and a pre-delivery checklist (4.5:1 contrast, no emoji icons, cursor-pointer, prefers-reduced-motion, four responsive breakpoints). MIT licensed, one-line npm CLI install, works with Claude Code and other coding agents.

AI CodingUI/UXOpen Source

Python132k14k530

pbakaus/impeccableApache-2.0

Impeccable: the design language that makes your AI coding agent better at design

An open-source design skill by Paul Bakaus: 1 skill, 24 commands and 61 deterministic anti-pattern detector rules that kill AI frontend slop (Inter everywhere, purple gradients, cards-in-cards). Installs into 16 harnesses including Claude Code, Cursor, Codex and Gemini CLI; live browser iteration plus a Chrome extension. Pure Markdown rules with a zero-LLM detector engine. Apache-2.0, 75k+ stars.

HarnessAI CodingDesign

JavaScript76k4.5k207

alibaba/open-code-reviewApache-2.0

Alibaba open-sources Open Code Review: battle-tested hybrid code review CLI

Originating from Alibaba's internal official AI review assistant (tens of thousands of devs, millions of defects over two years): hybrid deterministic pipelines + LLM Agent, line-level comments, built-in NPE/thread-safety/XSS/SQL-injection rulesets, plugins for Claude Code/Codex/Cursor and more, CI/CD integration, and a public benchmark of 200 real PRs with 1,505 annotated issues. OpenAI/Anthropic compatible.

Alibabaopen-code-reviewCode Review

Go43k3.1k133

walkinglabs/learn-harness-engineeringMIT

Learn Harness Engineering: a project-based course on making AI coding agents reliable

An open-source, project-based course (14 lectures, 8 projects, 15 languages) on building the instructions/state/verification/scope/lifecycle subsystems that make frontier models reliable inside real repos — includes reverse-engineered harness breakdowns of Pi, Claude Code, Codex and DeepSeek, plus loop- and graph-engineering advanced lectures. MIT licensed, ships a harness-creator skill and a zero-dependency audit script.

HarnessAI CodingAgent

TypeScript19k2.0k83

As an Amazon Associate, we earn from qualifying purchases.