Skip to content

AgentGoogle

Jules

Async coding agent that clones your repo and ships PRs.

Categories
AgentIDE
Pricing
FREEMIUM
Source
Proprietary
Hosting
Cloud
Platforms
WebCLIAPI
Models
Single model (proprietary)
Verified
Jun 7, 2026

Jules is Google's asynchronous coding agent. It clones your GitHub repository into a secure Google Cloud VM, understands the full project context, then writes tests, fixes bugs, and makes multi-file changes in the background before opening a pull request. A Jules Tools CLI and a Jules API extend it into your own workflows.

Capabilities 3

What it actually does — grouped by capability family.

  • Autonomous coding agent (primary capability)
  • Test generation (primary capability)
  • Terminal / CLI agent (secondary capability)

Pros & cons

  • Fully async, runs in the background
  • Opens PRs with multi-file changes
  • Audio changelog of its work
  • Jules Tools CLI + API to extend it
  • Cloud-only, no local execution
  • Gemini-only model backing
  • Async loop slower than in-editor agents
  • Newer than Copilot/Cursor agents

Tags

Alternatives to Jules (4)

View all Agent →
  • View Devin details
    AgentPAID

    Devin

    Cognition AI

    Autonomous software engineer agent. Plans, codes, ships from a prompt.

    Cognition's hosted SWE agent. Operates inside its own sandbox with a browser, terminal, and editor — plans the work, writes the code, and submits a PR. Aimed at long-horizon tickets rather than tab-completions.

    Autonomous, async whole-ticket work
    Closed model and harness
    • autonomous
    • swe-agent
    • browser
    • sandbox
    Open
  • View OpenAI Codex CLI details
    IDEFREEMIUMOpen core

    OpenAI Codex CLI

    OpenAI

    OpenAI's open-source coding agent for the terminal.

    A lightweight, open-source coding agent that runs locally in your terminal, reading your repository, editing files, and running commands in a conversational loop you review in real time. Built in Rust for speed, it supports Model Context Protocol tools, subagents for parallel tasks, and switching between GPT models. Sign in with a ChatGPT plan (Plus, Pro, Business, Edu, or Enterprise) or use an OpenAI API key.

    Runs locally in your terminal
    Best with OpenAI/GPT models
    • cli
    • coding-agent
    • terminal
    • open-source
    Open
  • View Claude Code details
    IDEFREEMIUM

    Claude Code

    Anthropic

    Anthropic's official CLI / IDE / web agent.

    Anthropic's agentic coding tool. It reads the spec, drafts the diff, runs the tests, and opens the PR — across the CLI, IDE extensions, the desktop app, and the web.

    Strong autonomous multi-step coding
    Anthropic models only
    • agentic
    • cli
    • ide
    • mcp
    • +1
    Open
  • View Factory details
    AgentPAID

    Factory

    Factory

    Agent-native software development with autonomous 'Droids'.

    An agent-native platform for software development built around 'Droids' — autonomous coding agents that plan, edit, and run tasks across a codebase. Works from a CLI/SDK and runs agents both in the cloud and locally in the background. Model-agnostic across frontier and open-weight models.

    Droids plan, edit, and run tasks autonomously
    Paid-only, no free tier
    • coding-agents
    • software-development
    • cli
    • autonomous
    Open
Open Jules