Jules

Jules is an autonomous cloud-based coding agent developed by Google Labs and the AIDA team. Designed to execute routine and repetitive development workflows asynchronously, Jules handles tasks such as bug fixing, framework migrations, test generation, and dependency updates without requiring continuous developer intervention. Day-to-day interactions occur across multiple interfaces, including a command-line interface (CLI), web UI, direct GitHub issue labeling, and a programmatic API. When assigned a task, Jules provisions an isolated Cloud Virtual Machine, clones the target repository and branch, formulates an execution plan using Google's Gemini models (Gemini 2.5 Pro on entry tiers and Gemini 3 Pro on higher tiers), applies file modifications, executes test suites to verify correctness, and produces a pull request with a complete diff for review. Unlike local CLI coding agents that manipulate files and execute shell commands directly on the user's host machine, Jules offloads execution to managed cloud VMs. This sandboxed architecture allows teams to run multi-agent workflows in parallel—ranging from 3 to 60 concurrent tasks—without risking local environment corruption or consuming local hardware resources. Jules is offered in tiered plans (Base, Pro, and Ultra) that govern daily task quotas (15 to 300 tasks per day), model access (Gemini 2.5 Pro vs. Gemini 3 Pro), and task concurrency limits.

Tags: ai agent, cli, code assistant, coding agent, developer tools

Visit Jules

Key features

  • Cloud VM Execution — Clones and executes code within isolated Google Cloud virtual machines, validating build and test status without touching the local host environment. - Gemini 2.5 and Gemini 3 Pro Integration — Leverages Google's Gemini 2.5 Pro and Gemini 3 Pro models for multi-file codebase reasoning and code generation. - Native GitHub Integration — Clones branches, verifies changes against the repository test suite, and automatically opens pull requests. - Issue-Driven Automation — Dispatches coding tasks asynchronously by tagging GitHub issues with the jules label. - Multi-Interface Access — Supports task orchestration via a dedicated CLI tool, web console, or the Jules REST API. - High-Concurrency Execution — Scales from 3 concurrent tasks on standard tiers up to 60 concurrent tasks on Ultra plans for parallel development.

Use cases

Use Case: Major Framework and Dependency Upgrades A developer requests a major framework upgrade, such as migrating a Next.js application to a new major version. Jules analyzes the repository in a cloud VM, updates dependency configurations, adapts imports and directory structures to comply with breaking changes, runs the build to verify, and submits a PR.

Use Case: Automated Test Coverage Expansion A team assigns Jules to generate test coverage for uncovered endpoints by tagging relevant GitHub issues with jules. Jules inspects existing test harnesses, writes unit and integration tests, confirms they pass inside the virtual machine, and surfaces the diff for developer review.

Use Case: Parallel Bug Remediation A developer working through a backlog dispatches multiple issue fixes simultaneously via the CLI. Jules executes the fixes across isolated cloud containers in parallel, preventing workspace collisions on the local machine and reducing turnaround time.

Who it is for

Jules is built for individual developers, open-source maintainers, and engineering teams seeking an asynchronous, cloud-sandboxed agent to handle boilerplate maintenance, migrations, and bug fixes without blocking local environments. It is not suitable for offline development workflows, air-gapped environments, or teams requiring alternative foundation model providers like Anthropic Claude or local Ollama instances.

Install guide

Installation Jules provides a CLI utility to interact with the service directly from the terminal. Install the CLI using the standard package distribution method (or refer to the official documentation at https://jules.google/docs/cli/reference): bash # Standard npm installation method npm install -g @google/jules-cli

First Run Authenticate your terminal session with your Google account and link your GitHub organization or repository permissions: bash # Authenticate the CLI jules auth login # Verify configuration and linked repositories jules config list

Example Session Dispatch a task to Jules to refactor a module or upgrade a dependency directly from your repository directory: bash # Trigger Jules on the current branch jules run "Upgrade Next.js to v15, convert pages to the app router, and ensure all tests pass" # Inspect active task status jules tasks list # Review the diff and generated PR jules pr view

Part of CLI Coding Agents

Categories: AI Coding Agents, Code Assistants, Developer Tools

Related CLI agents

  • OpenHands — OpenHands (formerly OpenDevin) is an open-source autonomous AI software development agent and orchestration platform. It provides an extensible runtime environment…
  • Plandex — Plandex is an open-source terminal-based AI coding agent designed to handle complex, multi-file engineering tasks in large codebases. Created by…
  • Amp — Amp (developed by AmpCode) is an autonomous coding agent platform and remote development harness designed to execute software engineering tasks…
  • Kiro — Kiro is an agentic engineering platform and CLI coding agent built and operated by AWS. It extends beyond standard code-completion…
  • OpenCode — OpenCode is an open-source AI coding agent developed by Anomaly that operates across terminal environments, desktop applications, and IDE extensions.…
  • Ona — Ona (formerly Gitpod's agentic platform, now part of OpenAI) is an enterprise-grade cloud agent orchestration platform that manages and runs…
  • AI Tools
  • Categories
  • Industries
  • CLI Coding Agents
  • MCP Servers
  • MCP Categories