Skip to main content
Agentic.ai
JU

Jules

Agenticness13/36·Adaptive Collaborator

An autonomous coding agent for repo tasks and PRs

Jules helps you offload coding chores like bug fixes, test work, and version bumps. It works with GitHub, runs code in a cloud VM, and asks for approval before it turns changes into a PR.

Agenticness = how independently a tool can take action, scored across 9 dimensions. Scored independently by David Kooi, Skylark Creations — see full rubric →

See pricing ↓

Chrome Extension
Code Execution
File Access
Integrations
B2B
Copilot (Human-in-Loop)
Fully Autonomous
Visit Jules

Is this your tool? Claim this listing to manage your content and analytics.

Recent activity

What's happened with Jules lately

  • Score change
    Rubric upgrade v3_0 → v3.1: score 8/32 → 15/368 → 15/36(+7)

    Rubric upgrade: agenticness v3.0 (8 dims, /32) → v3.1 (9 dims, /36). Adds Dim 9 (Operator Sovereignty), splits Dim 6 into 6a/6b lenses, tightens Dim 4 autonomous-retry distinction. Not a product change — score shift reflects new dimension + recalibrated rubric, not a change in the tool. Fanout suppressed.

    See the news that prompted this

News mentions sourced from our news feed; score changes from periodic re-evaluations.

Ask about Jules

Get answers based on Jules's actual documentation

Try asking:

About

What It Is

Jules is an experimental AI coding agent from Google Labs. It’s built for developers who want help with repository work that can be time-consuming but fairly routine: fixing bugs, adding tests, updating dependencies, and making feature changes.

What to Know

Jules is more autonomous than a typical coding assistant, but it is not fully hands-off. The workflow still includes a planning step and user approval before code changes are applied, so it fits best when you want an agent to do the implementation work while you stay in control of the final output.

Key Features
Connects to GitHub repositories and branches
Clones code into a cloud VM for task execution
Generates a task plan before making changes
Edits code and shows a diff for review
Creates pull requests from completed work
Use Cases
Fixing bugs in an existing codebase with a review step before merge
Bumping framework or library versions across a repository
Adding or updating tests for a specific function or module
Agenticness: Adaptive Collaborator

Proposes and executes multi-step plans with your approval.

High evidence
Last evaluated: Jul 5, 2026

Dimension Breakdown

Action Capability
Autonomy
Adaptation
State & Memory
Safety
How agenticness works →

Categories

Coding Agents
Pricing
  • Free: 15 tasks per day and 3 concurrent tasks; powered by Gemini 2.5 Pro.
  • Pro: 100 tasks per day and 15 concurrent tasks; higher access to the latest models, starting with Gemini 3 Pro.
  • Ultra: 300 tasks per day and 60 concurrent tasks; priority access to the latest models, starting with Gemini 3 Pro.
Details
jules.google
AddedMarch 26, 2026
RefreshedJuly 5, 2026
Agenticness
Adaptive Collaborator
Quick Facts
DeploymentCloud-hosted
AutonomySemi-autonomous
Model supportSingle model
Open sourceNo
Team supportSmall team
Pricing modelSubscription
Interfacegui, cli, api
Sources
WebGoogle Docs: Online Document & PDF Editor | Google Workspace
Last updated July 5, 2026
Similar tools

Related Tools

Kilo Code
Agenticness15/36·Adaptive Collaborator

Coding Agents

Kilo Code is the v5.x community fork of Roo Code (which was archived May 15, 2026). Open-source VS Code extension for agentic coding — Apache 2.0 licensed, BYOK across many providers, runs locally as an IDE extension.

OpenHands
Agenticness18/36·Adaptive Collaborator

Coding Agents

OpenHands (formerly OpenDevin) is a fully autonomous open-source AI coding agent. MIT-licensed core, plans + executes Python actions via CodeAct, uses browser + terminal + files. ~72% on SWE-bench Verified with Sonnet 4.5 via the OpenHands Software Agent SDK (arXiv:2511.03690).

Augment Code
Agenticness17/36·Adaptive Collaborator

Coding Agents

Augment Code is an enterprise-focused AI coding agent built around a 200K-token Context Engine. Closed-source SaaS with strong SWE-bench Verified results (70.6% self-reported) and the highest accuracy on the only public benchmark for AI-assisted code review.

AICode
Agenticness17/36·Adaptive Collaborator

Coding Agents

AICode is a VS Code extension for enterprise teams working in large legacy codebases. It maps dependencies and architecture, audits specifications before coding, and keeps changes reviewable inside your infrastructure.

Enterprise
Chrome Extension
B2B
+4
Stay in the loop

Get the weekly agentic AI briefing

New tools, top picks, and trends — delivered every Thursday.

I use AI for: