feder-cr/invisible_dots

Open-source, self-hosted alternative to OpenAI Dots, Grok Bot. Built to be undetectable by anti-bot systems.

View on GitHub ↗Jump to charts ↓Open shareable report →

Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 28 minutes ago
Added to GitGenius on October 7th, 2026
Created on August 4th, 2024
Open Issues & Pull Requests: 0 (+0)
GitHub issues: Enabled
Number of forks: 4,712
Total Stargazers: 31,944 (+1)
Total Subscribers: 190 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 15.4 hours
Mean response time: 17.3 days
90th percentile: 28.7 days
Tracked items: 418

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 0
New in 7 days: 0
Closed in 7 days: 2
Avg open age: N/A days
Stale 30+ days: 0
Stale 90+ days: 0

Recent activity

Opened in 7 days: 0
Closed in 7 days: 2
Comments in 7 days: 2
Events in 7 days: 4

Top labels

  • bug (216)
  • enhancement (118)
  • stale (83)
  • help wanted (30)
  • documentation (28)
  • question (12)
  • good first issue (11)
  • planned (6)

Most active issues this week

Sign in to see which issues are moving.
Sign in

Detailed Description

invisible_dots is a self-hosted AI agent platform that gives each agent its own virtual machine with persistent desktop, shell, files, and browser.

The tool solves the problem of running autonomous AI agents that need to interact with graphical interfaces and maintain state across tasks. It provides each agent with a QEMU virtual machine running on your local PC, allowing the agent to use a browser that does not appear automated, access a desktop environment, execute shell commands, and retain files and login sessions between interactions. You communicate with agents through a web UI, command line, HTTP API, or Telegram, and the tool supports any language model available on OpenRouter using your own API key.

The project suits developers and organizations that need agents to perform extended tasks requiring human judgment and computer interaction, such as web scraping, form filling, file management, or scheduled monitoring tasks. It is designed for self-hosted deployment on Linux and Windows systems with hardware virtualization support. The tool positions itself as an open-source alternative to commercial offerings like OpenAI Dots, Meta Muse, and Claude Cowork, emphasizing local-first operation and the ability to control what each agent can access.

Development activity shows consistent test coverage with an automated test suite, indicating ongoing quality assurance. The project maintains documentation covering quickstart procedures, architecture details, security considerations, and privacy implications, suggesting attention to helping users understand both capabilities and limitations. The codebase is written in TypeScript and Go, with setup automation provided for both Windows and Linux platforms.