Full computer-use for AI agents. Self-learning workflows. Native macOS. No screenshots required.
- ✓Open-source license (MIT)
- ✓Recently active
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
git clone https://github.com/ghostwright/ghost-os && cp ghost-os/*.md ~/.claude/agents/Subagents overview
What people ask about ghost-os
What is ghostwright/ghost-os?
+
ghostwright/ghost-os is subagents for the Claude AI ecosystem. Full computer-use for AI agents. Self-learning workflows. Native macOS. No screenshots required. It has 1.6k GitHub stars and was last updated 4mo ago.
How do I install ghost-os?
+
You can install ghost-os by cloning the repository (https://github.com/ghostwright/ghost-os) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is ghostwright/ghost-os safe to use?
+
Our security agent has analyzed ghostwright/ghost-os and assigned a Trust Score of 92/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains ghostwright/ghost-os?
+
ghostwright/ghost-os is maintained by ghostwright. The last recorded GitHub activity is from 4mo ago, with 9 open issues.
Are there alternatives to ghost-os?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy ghost-os to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/ghostwright-ghost-os)<a href="https://claudewave.com/repo/ghostwright-ghost-os"><img src="https://claudewave.com/api/badge/ghostwright-ghost-os" alt="Featured on ClaudeWave: ghostwright/ghost-os" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The agent engineering platform.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.