Jules
Google asynchronous coding agent that works on your GitHub repo by itself
Visit website →About
Jules is Google's asynchronous coding agent: you connect a GitHub repository, describe a task such as a bug fix, a dependency upgrade or new tests, and it clones the project into a cloud virtual machine, plans the change, runs it and comes back with a pull request and an audio summary. It is built for work you hand off.
Google documents usage limits but not language. The free tier allows 15 tasks a day with three running at once; Google AI Pro raises that to 100 a day and 15 concurrent, and AI Ultra to 300 and 60. Paid tiers are limited to individual Gmail accounts for now. Nothing in the documentation mentions Arabic prompts or right-to-left text, and because output arrives as a pull request rather than in a terminal, the display problems that affect command-line agents matter less here.
Pricing in October 2026: free tier; higher limits through Google AI Pro and AI Ultra subscriptions.
AI-assisted draft, human-reviewed before publishing — see how we choose & review tools.
Why we picked it
Jules sidesteps the one Arabic problem every terminal agent shares, because its output is a pull request rather than text in a console. That makes it a practical option for Arabic-speaking developers even though Google documents nothing about the language, and the catalog had no entry for it.
Featured in our guides
Related tools
- 1 Rystic Realistic local API simulators for testing AI agents Freemium
- 2 Superfik Open-source canvas to watch AI coding agents work — each on its own card Free
- 3 Momentic AI QA engineer that catches bugs before they ship Freemium
- 4 Stroq Finds leaked secrets in AI coding agent sessions Free
- 5 Verdict Local model verifying CLI outcomes for AI agents. Exit code 0 ≠ proof Free
- 6 Backenly Autonomous backend your coding agent builds over MCP and keeps running Freemium