No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by coasty-ai · Claude Skill · ★ 136
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is open-cowork safe to install? View the security audit →
open-cowork Hand off computer tasks to an AI coworker — watch it work, approve from anywhere. An open-source, cross-platform agentic coworker on the Coasty Computer Use API. It sees a screen and acts on it — your own desktop, a cloud VM, or a browser — streams every step live, pauses for your approval, and keeps spend visible and capped. Quickstart · <a href
| Stars | 136 |
| Forks | 34 |
| Language | TypeScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 66.0369322257512/100 |
| Open Issues | 7 |
| Last Updated | 2026-08-02 |
| Created | 2026-06-11 |
| Platforms | browser, claude-code, gemini, node |
| Est. Tokens | ~16k |
These tools work well together with open-cowork for enhanced workflows:
Looking for a open-cowork alternative? If you're comparing open-cowork with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Auto-Use Computer Use — drives your OS, browser, scours the web, writes your code. One agent, end to end.
Browser-automation agent for Chrome — natural-language tasks executed through native tool calling, scoped Skil
Python API client for AI providers that intends to replace LangChain and LangGraph for most common use cases.
Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpee
Custom node for ComfyUI/Stable Diffustion
AI controls your OS. OS AI Computer Use, OS and API agnostic. For now on OpenAI and Anthropic API. Desktop app
Explore other popular claude skill tools:
open-cowork is Open-source alternative to Claude Co-Work built by Claude. with BYOK. It is categorized as a Claude Skill with 136 GitHub stars.
open-cowork is primarily written in TypeScript. It covers topics such as anthropic, anthropic-api, anthropic-claude.
You can find installation instructions and usage details in the open-cowork GitHub repository at github.com/coasty-ai/open-cowork. The project has 136 stars and 34 forks, indicating an active community.
open-cowork is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to open-cowork on Agent Skills Hub include Auto-Use, pie-ai-agent, simplemind. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: