Google Jules
Also known as: Jules
Google's asynchronous coding agent, now winding down: read only since 11 November 2026 and shut on 31 December 2026, with its work folding into Antigravity. Jules took a GitHub issue, planned it for approval, worked in an isolated cloud VM with browser verification and opened a pull request, driven from a REST API, CLI and scheduled tasks.
Jules is Google's asynchronous coding agent, built in Google Labs and powered by the Gemini family of models, and Google is winding it down. Sessions could run until 11 November 2026, Jules is read only after that, and the service shuts on 31 December 2026, with Google folding what it learned into Antigravity. Until then the Jules Tools CLI exports account settings, environment variables, scheduled tasks, repositories, memories, setup scripts and session history, while code and pull requests already on GitHub stay where they are.
Instead of sitting beside a developer and suggesting code, Jules took a complete task, usually a GitHub issue, and worked on it alone while the developer did something else, handing back a pull request for review. Given a task, it cloned the repository into a secure, isolated Google Cloud virtual machine, read the project, and wrote a step by step plan the developer could review, edit or reject before any code was written.
It then changed files across the project, ran the existing test suite and iterated when tests failed. The VM had network access, so Jules could install dependencies and run real builds. When the work was done it pushed to a branch and opened a pull request with commit messages and a plain summary, and if CI failed on that pull request, Jules read the error, applied a fix and pushed again.
Each task ran in its own cloud machine, so many could run at once in the background. Jules used stronger Gemini models for planning and lighter ones for simpler subtasks, with Gemini 3.1 Pro as the default for Pro users from March 2026, and worked in Python, TypeScript, JavaScript, Go, Rust and Java. It worked through GitHub, could be driven from a command line tool and a public API wired into CI pipelines, Slack, Linear and Jira, ran scheduled tasks, and remembered preferences for each repository.
Google kept Jules private by default, isolating code in short lived VMs and stating it does not train on private code. There was no organization administration, single sign on or compliance attestation, and paid plans came through Google AI subscriptions for individual Google accounts. Jules suited well scoped work such as bug fixes, dependency upgrades, test writing and batched refactors, where a clear brief and good test coverage let an agent run unattended.
From our cloud coding agents video
Devin, Factory, Jules, OpenHands: What Each Cloud Coding Agent Does Best
Our video on the 11 cloud coding agents in the index names what each one does best. For Google Jules, that is the plan, drafted for your approval before any code.
The player starts at Google Jules's part, 3:27 in. Recorded in October 2026; the profile here is live and updates as research is verified.
From our comparison video
Google Jules vs OpenAI Codex (2026): Which Should You Choose?
Our 5 minute video puts Google Jules side by side with OpenAI Codex. It covers what each one does and how each is priced, then when to choose which.
Recorded in October 2026. The profile here is live and updates as research is verified.
Vendor details
Canonical URL
https://jules.google
Category
Coding agent
Company status
first party product
Use cases & customers
Target customers
Deployment options
Integrations
Deep GitHub integration covering issue labels, branches, pull requests and reading and responding to PR comments. MCP server support launched February 2026 with a vendor vetted set covering Linear, Stitch, Neon, Tinybird, Context7 and Supabase, configured by API key. A Render integration detects failed builds and pushes fixes. A REST API at jules.googleapis.com/v1alpha exposes Sources, Sessions and Activities and wires Jules into Slack, Linear, Jira and CI pipelines including GitHub Actions, alongside a Jules Tools CLI on npm and a Gemini CLI extension.
In practice
You have a stack of well-scoped GitHub issues and no time to work them. You assign them to Jules, which clones each repo into its own cloud VM, implements the fix, runs the tests, and opens a pull request for review.
You want to fire off several coding tasks at once and keep working. Jules runs each in a separate cloud machine in parallel, so the work proceeds in the background instead of tying up your editor.
You worry an agent will run off in the wrong direction. Jules writes a step-by-step plan first and lets you edit or reject it before any code is written, so you steer the approach instead of just reviewing the output.
Sources & related URLs
Related / legacy domains
Agentic Index coverage score
9.0 / 14 capabilities · 64%
| Integrations & Tool Calling | Full |
|---|---|
|
Deep GitHub integration covers issue labels, branches, pull requests and reading and responding to PR comments, MCP servers connect Linear, Stitch, Neon, Tinybird, Context7 and Supabase by API key in Settings, a Render integration detects failed builds and pushes fixes, and the REST API wires Jules into Slack, Linear, Jira and CI pipelines including GitHub Actions. GitHub is the only source control host. The agent runs shell commands, installs dependencies and executes builds inside its VM with repository level environment variables. Sourcejules.google/docs/changelog 2026-02-02 and 2025-10-03, docs/integrations/renderread 2026-10-28 |
|
| Workflow Orchestration | Full |
|
A task runs as a multi step plan the agent produces before writing code, with an Interactive Plan mode where it asks clarifying questions and refines the approach collaboratively, a Critic agent performing adversarial review of every proposed change during generation, a Planning Critic reviewing auto approved plans and reported to cut task failure rates by 9.5 percent, a CI Fixer loop that detects failures, fixes, commits and resubmits, and up to five parallel sessions on one prompt via the CLI --parallel flag, within the plan's concurrency limit of 3, 15 or 60 tasks. Sourcejules.google/docs/changelog 2026-01-26-1, 2026-02-19 and 2025-11-10, docs/cli/reference and docs/usage-limitsread 2026-10-28 |
|
| Knowledge Grounding & RAG | Partial |
|
Each task clones the repository into its VM and reads it directly, with AGENTS.md conventions read from the repository root, a file selector to scope context, image upload and web search for current documentation. Suggested Tasks scan up to five repositories for TODO comments. Context is assembled per task, and the docs describe no persistent index, graph or embeddings layer over the customer's code. Sourcejules.google/docs, docs/guides/suggested-tasks and docs/environmentread 2026-10-28 |
|
| Human Oversight & Guardrails | Full |
|
The agent writes a step by step plan the user approves, edits or rejects before any code is written, with an Interactive Plan mode asking clarifying questions first, and the user can chat with it at any point. If the user leaves, the plan auto approves on a timer, and the API's requirePlanApproval option is off by default, so a Planning Critic reviews plans that are auto approved. Work lands on a branch and the user chooses when to publish or open a pull request, a Critic agent adversarially reviews each proposed change during generation, tasks can be paused, resumed or deleted mid run, and commit authorship is configurable so changes are attributed to Jules, co-authored, or the user. Sourcejules.google/docs/guides/review-plan, docs/api/reference and docs/changelog 2026-01-26-1 and 2026-02-19; jules.google/docs/changelog/2025-08-082read 2026-10-28 |
|
| Security, Identity & Governance | Not documented |
|
Jules isolates each task in a cloud VM, reaches repositories only as granted through the GitHub app, stores integration API keys encrypted, does not train on private repositories and tells users they are responsible for the code they run. There is no access surface (SSO, roles, organization administration) and no attestation or trust page, and paid plans are sold to individual Google accounts only. Sourcejules.google/docs/faq and docs/usage-limitsread 2026-10-28 |
|
| Observability & Auditability | Full |
|
Each session carries a collection of activities representing the steps the agent took. Google calls them immutable, following an event source pattern and usable to reconstruct the session, and they are retrievable through the REST API with a createTime range cursor. The web app shows a real time activity feed, per task logs and task history per repository, the full changeset is downloadable in git patch format, and the critic agent's step by step evaluation is visible in the UI as it runs. No organization audit log is documented. Sourcejules.google/docs/changelog 2026-01-26-4 and 2025-09-03, docs/guides/coderead 2026-10-28 |
|
| Memory & State Persistence | Partial |
|
Repository Memory saves the user's preferences, nudges and corrections during a task and references them on later tasks in that repository, toggled on or off per repository under Knowledge. The changelog is the only page that describes it. Memory has no stated lifetime and no documented way to review or delete entries, and environment snapshots and variables are setup state, not memory. Sourcejules.google/docs/changelog 2025-09-30read 2026-10-28 |
|
| Deployment & Data Residency | Not documented |
|
Every task runs in a fresh, short lived Ubuntu VM in Google's cloud with internet access, whose toolchain the customer shapes with a setup script, snapshots and environment variables. That configures the environment, not where it runs. There is no region choice, customer VPC, on premises or tenant option, so a customer with a different residency requirement has no other answer. Sourcejules.google/docs/environment and docs/faqread 2026-10-28 |
|
| Prebuilt Agents, Templates & Packs | Partial |
|
Sample prompts ship as one click starting points, three scheduled task templates (Performance, Design and Security) start recurring tasks, suggested tasks let the agent propose work it has found in the repository, and MCP integrations are offered from a vendor curated list of vetted servers. There is no library of prebuilt agents, installable skills or marketplace, and the community prompt list lives in a GitHub repository. Sourcejules.google/docs/guides/scheduled-tasks, docs and docs/changelog 2025-09-02 and 2026-02-02; jules.google/docs/changelog/2025-09-02read 2026-10-28 |
|
| Triggers & Channel Coverage | Full |
|
Tasks start from a jules label on a GitHub issue, the web app, the Jules Tools CLI, a REST API for CI/CD and chat integrations, scheduled recurring tasks (daily, weekly or monthly) with pause and resume, proactive suggested tasks where Jules scans a repository for TODO comments and surfaces work, pull request comments which the agent reads and acts on, and automatic triggers on CI failures in GitHub Actions and failed Render builds. No inbound webhook is documented. Sourcejules.google/docs/guides/scheduled-tasks, docs/guides/running-tasks and docs/changelog 2025-12-10, 2026-01-26 and 2026-02-19; jules.google/docs/changelog/2025-12-101read 2026-10-28 |
|
| Model Flexibility & Routing | Not documented |
|
Every model Jules runs is Google's Gemini. The changelog makes Gemini 3 Flash the base model on all tiers and Gemini 3.1 Pro the default for Pro subscribers, which is a tier choice within one maker, while the homepage and usage page still name Gemini 2.5 Pro and Gemini 3 Pro. There is no user model choice, no other maker and no bring your own model path. Sourcejules.google/docs/changelog 2026-03-09 and 2026-01-30, docs/usage-limitsread 2026-10-28 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
A REST API at jules.googleapis.com/v1alpha, in alpha, authenticates with an X-Goog-Api-Key header (up to three keys) and exposes Sources, Sessions (create, list, approve plan, send message, auto create PR, repoless sessions) and Activities with git patch output. A Jules Tools CLI installs via npm as @google/jules with jules remote new, list and pull, parallel execution and local patch application, a Gemini CLI extension exposes Jules as a slash command, and MCP server support connects a vetted set of servers by API key. Sourcejules.google/docs/api/reference, docs/api/reference/authentication, docs/cli/reference and docs/changelog 2026-02-02; jules.google/docs/changelog/2026-02-02read 2026-10-28 |
|
| Testing, Debugging & Optimization | Partial |
|
The agent runs the project's existing test suite and iterates when tests fail, writes tests on its own, and the CI Fixer detects a failed GitHub Actions check, works through a fix and resubmits the pull request in a loop. A Critic agent adversarially reviews proposed changes and a Planning Critic reviews plans, both internal quality mechanisms, and Run to Validate checks environment setup scripts. These verify the customer's code and the agent's own output. There is no harness for customers to evaluate or regression test agent behavior. Sourcejules.google/docs/changelog 2026-02-19 and 2026-01-26-1, docs/environmentread 2026-10-28 |
|
| Browser & Computer Use | Full |
|
The default Jules base image includes Playwright and ChromeDriver for front end testing, and the agent renders a running web application and returns a screenshot of the front end alongside its code changes when asked to verify its work, with images shown in the diff viewer. With Gemini 3 Pro, visual verification of web app outcomes is more precise, and Jules can also search the web for documentation and code examples during a task. Sourcejules.google/docs/changelog 2025-08-07 and 2025-11-19, docs/environmentread 2026-10-28 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Product updates
Sessions in Jules can continue until November 11, 2026, after which Jules turns read only, and the product winds down for good on December 31, 2026 as Google unifies its agentic coding work. Users can now export their settings, environment variables, scheduled tasks, connected repositories, memories, setup scripts and full session history, including plans, activity logs and code patches, to a local folder through the Jules Tools CLI. Code, branches and pull requests already live in GitHub and stay there.
Bears on: Agent capability
View sourcePricing
Free; Jules in Pro with Google AI Pro at $19.99 a month
Daily task quotas set by a Google AI subscription
What is public
Jules is free for 15 tasks a day with 3 running at once. Jules in Pro comes with Google AI Pro at $19.99 a month in the US, with 100 tasks a day, 15 concurrent and higher access to the latest model, and Jules in Ultra with Google AI Ultra from $99.99, with 300 tasks a day, 60 concurrent and priority access. Google AI Plus, from $7.99 a month, includes Jules with limited usage, and the Ultra 5x and Ultra 20x tiers include it without task numbers. The paid price buys the wider Google AI subscription, so Jules has no separate cost.
Billing mechanics
Limits are per user, not pooled across a team or family, and daily caps run on a rolling 24 hours: once hit, no new tasks start until the reset, with no per task overage billing.
Variable cost rationale
The subscription is flat and the caps are hard, so spend does not grow with use.
Additional watchouts
Paid tiers were available only to individual Google Accounts ending in @gmail.com. Jules took its last new sessions on 11 November 2026 and shuts down on 31 December 2026.
Sales call required
No, self serve available
Key ambiguities
Google stopped new Jules sessions on 11 November 2026 and shuts the service on 31 December 2026, so no plan buys new Jules work.
Cancellation / refund
Billing runs through the Google One AI plans subscription under standard Google subscription terms.
Missing data
Google does not state business or enterprise pricing for Jules or a way to pool seats.
Related vendors
- Cognition — Maker of Devin, an autonomous AI software engineer
- 10Web — Agentic website platform whose AI agents build, host and manage…
- AgentUI — Managed AI app builder for operations teams that generates and hosts…
- Aider — Open source, model agnostic terminal coding agent that edits your…
- Amp — Amp is a coding agent from Amp Frontier Corporation that runs each…
- Anthropic Claude Code — Claude Code is Anthropic's agentic coding tool
Alternatives to Google Jules
Other products that do the work Google Jules does, and what each one is.
- Anthropic Claude CodeGoogle Jules vs Anthropic Claude Code →
- CapyAgent platform for engineering teamsGoogle Jules vs Capy →
- OpenAI CodexGoogle Jules vs OpenAI Codex →Video
- CognitionMaker of DevinGoogle Jules vs Cognition →
- OpenHandsGoogle Jules vs OpenHands →
- Kimi Code