nezha  by hanshuaikang

Agent-first desktop app for parallel AI coding

Created 2 months ago
1,442 stars

Top 27.8% on SourcePulse

GitHubView on GitHub
Project Summary

Nezha is a desktop application designed for parallel AI coding by running multiple AI agents (Claude Code, Codex) concurrently across projects. It targets developers seeking to streamline AI-assisted development workflows, offering a unified interface for task management, real-time terminal access, Git operations, and code editing, thereby minimizing context switching and boosting productivity.

How It Works

Adopting an "Agent-First" philosophy, Nezha integrates AI coding agents directly into a desktop environment. Its core innovation is enabling these agents to operate in parallel across multiple projects, facilitated by a unified workspace. This workspace combines a real-time terminal, intelligent session management, code browsing, and native Git integration, allowing developers to delegate tasks, review code, and submit changes seamlessly without leaving the application or context-switching.

Quick Start & Requirements

  • Installation: Requires Claude Code / Codex to be pre-installed. On macOS, unsigned app warnings can be resolved by running xattr -rd com.apple.quarantine /Applications/nezha.app.
  • Prerequisites: Claude Code / Codex, macOS.
  • Footprint: Installation package is 7MB.
  • Links: No direct quick-start or demo links provided.

Highlighted Details

  • Centralized Multi-Tasking: Manage multiple projects and AI coding tasks concurrently within a single interface.
  • Intelligent Session Management: Auto-detects AI sessions, alerts users for manual input, and provides visualized session history for task resumption.
  • Native Git Integration: Supports branch management, code commits with AI-assisted message generation, and Git diff views.
  • Lightweight Code Editor: Features syntax highlighting for major languages and a file tree browser.
  • Usage Analytics: Tracks weekly token consumption and tool invocations for cost and efficiency monitoring.

Maintenance & Community

No specific details on contributors, sponsorships, or community channels (e.g., Discord, Slack) are available in the provided README.

Licensing & Compatibility

The README does not specify a software license, and therefore, commercial use compatibility is undetermined.

Limitations & Caveats

  • Platform Support: Windows and Linux support are listed as planned features, indicating the current version is likely macOS-only.
  • AI Agent Dependency: Requires external installation and configuration of Claude Code / Codex.
Health Check
Last Commit

1 day ago

Responsiveness

Inactive

Pull Requests (30d)
70
Issues (30d)
26
Star History
281 stars in the last 30 days

Explore Similar Projects

Feedback? Help us improve.