AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Browser Automation/
open-cuak
open-cuak logo

open-cuak

★ 392·Apache-2.0·Updated 2025-06-28

Open-CUAK (Open Computer Use Agent Kit) is an open-source platform from Aident AI for running and managing automation agents at scale, starting with browsers. It drives a dedicated remote browser with vision-based automation, works with any vision-compatible model such as Claude, Gemini or open-source VLMs, and runs locally for full privacy as a free alternative to OpenAI Operator.

open-cuak sits in the Browser Automation category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Run Operator-like browser automation locally for full privacy. A representative use case is Automating web tasks such as form filling, search and booking across real sites. The listed license is Apache-2.0. GitHub stars are currently 392. Relevant tags include agent, automation.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool.

#agent#automation#remote-browser#rpa#vlm#llm#computer-use#browser-automation
$ Install
$ brew install Aident-AI/homebrew-tap/open-cuak && open-cuak start
↗ Visit site★ GitHub
01

Features

01Run Operator-like browser automation locally for full privacy
02Vision-based automation that works like a human across sites
03Dedicated remote browser plus a browser extension to turn any browser into an operator companion
04Model-agnostic: use any vision-compatible model (Claude, Gemini, LLaVA, etc.)
05Cookie management and bot-detection bypass for smoother logins and automation
02

Why choose it

+Run Operator-like browser automation locally for full privacy
+Vision-based automation that works like a human across sites
+Automating web tasks such as form filling, search and booking across real sites
+Supports 4 platforms or runtime environments.
03

Trade-offs

!The final decision should still be made through side-by-side comparison with similar tools.
04

Maintenance check

StaleChecked: 2026-10-20
Last commit
2025-06-28
Commits, last 90 days
0
Releases, last 90 days
0
Latest release
v0.0.1-alpha (2025-02-26)
Open issues
11
Recent issues with at least one comment
17/23
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #54 support custom hostname3 comments · 2025-03-18
  • #31 Improve Project Setup Guide & Add Visualized Architecture in README2 comments · 2025-02-19
  • #56 doesn't start on Linux/Fedora1 comments · 2025-03-22
  • #55 Save workflow not working1 comments · 2025-03-19
  • #45 any chance for support OmniParser-v2.0 ?1 comments · 2025-03-03

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

Claude
Vision model
Verified via docs
Gemini
Vision model
Verified via docs
Chrome
Extension
Verified via docs
Docker
Local deploy
Verified via docs
06

Quick start

1
$ brew install Aident-AI/homebrew-tap/open-cuak
2
$ open-cuak start
07

Use cases

↳Automating web tasks such as form filling, search and booking across real sites
↳Running many browser automation agents in parallel for RPA workloads
↳Self-hosting a private, Operator-style agent instead of a cloud service
08

Alternatives

⚡Top VS:
VSGhostDesk★155→VSsafari-mcp★223→VScdpilot★32→VSUni-CLI★235→
GhostDesk logo
GhostDesk★ 155
Give any AI agent a full desktop — it sees the screen, clicks, types, and runs apps like a human. Automate anything with a UI: browsers, legacy software, internal tools. No API needed. One Docker command.
VSCompare→
safari-mcp logo
safari-mcp★ 223
Native Safari browser automation for AI agents. 80 tools via AppleScript — zero overhead, keeps logins, runs silently in background. Drop-in alternative to Chrome DevTools MCP with 40-60% less CPU/heat on Apple Silicon.
VSCompare→
cdpilot logo
cdpilot★ 32
Zero-dependency browser automation CLI. 70+ commands, 10 test assertions, smart commands (click/fill by text — no LLM needed). MCP server for AI agents with 500x fewer tokens. Extract, observe, script runner. 50KB, pure CDP.
VSCompare→
Uni-CLI logo
Uni-CLI★ 235
Command-grade software access for AI agents. 235+ websites, desktop apps, MCP servers, and external CLIs as one searchable, self-repairing CLI catalog. YAML adapters, structured error envelopes, ~80 tokens per call.
VSCompare→
hanzi-browse logo
hanzi-browse★ 178
let any ai agent use the local browser
VSCompare→
open-computer-use logo
open-computer-use★ 126
MCP server that gives any LLM its own computer — managed Docker workspaces with live browser, terminal, code execution, document skills, and autonomous sub-agents. Self-hosted, open-source, pluggable into any model.
VSCompare→
open-computer-use logo
open-computer-use★ 126
MCP server that gives any LLM its own computer — managed Docker workspaces with live browser, terminal, code execution, document skills, and autonomous sub-agents. Self-hosted, open-source, pluggable into any model.
VSCompare→
camofox-mcp logo
camofox-mcp★ 119
Anti-detection browser MCP server for AI agents — navigate, interact, and automate the web without getting blocked
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
Aident-AI /
open-cuak
↗

Reliable Automation Agents at Scale

392Apache-2.0
Last commit1y ago
StatusNo updates in 1y+
CategoryBrowser Automation
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.