DevFlow vs Jules: 7 dimensions, sourced
DevFlow and Jules are compared on 7 dimensions below, each read from Google's own documentation on 1 Oct 2026; 3 cases where Jules fits better are listed too.
Jules is an experimental coding agent that integrates with GitHub, works autonomously in a virtual machine and generates a plan you can approve before any code changes.↗
Each claim about the other product was read on 1 Oct 2026 from the page its ↗ link opens. Cells in the DevFlow column are written from files in DevFlow's own codebase, named next to each cell; that codebase is not public. A comparison left unchecked for 90 days is flagged for review.
| Dimension | DevFlow | Jules |
|---|---|---|
| Where it runs | On the hosted instance at devflow.fraway.io. A self-hosted install is not self-serve: it is arranged with Fraway on request.site/src/lib/site.tsENTITLEMENTS.mdweb/src/lib/components/billing/PlanCards.svelte | Each task runs in a fresh, cloud-based virtual machine where Jules clones your repository, installs dependencies and makes changes.↗ |
| Where your code goes | On the hosted instance at devflow.fraway.io, DevFlow clones repositories into worktrees on the servers that run it. Prompts, which include code, go to the model provider the workspace chooses.CLAUDE.mdsite/src/lib/site.ts | Jules connects to the GitHub repositories you grant and clones the chosen repository into the task VM; its FAQ states that Jules does not train on private repository content.↗ |
| Model choice | Each workspace stores its own key for OpenRouter, Anthropic, OpenAI or Google. On Pro and higher plans, managed OpenRouter inference can stand in when no OpenRouter key is stored.internal/relay/providers.gointernal/entitlement/entitlement.goCLAUDE.md | Gemini models. The plans table lists Gemini 2.5 Pro for the base Jules plan, and higher (Jules in Pro) or priority (Jules in Ultra) access to the latest model, starting with Gemini 3 Pro.↗ |
| Isolation | Each task gets its own git worktree. Agent CLIs run under a Landlock sandbox or, when enabled, in a per-invocation container; test and build commands run in non-root containers capped at 4 CPUs and 4 GB of memory by default.CLAUDE.mdinternal/agent/depcache.go | Jules runs each task inside a short-lived virtual machine running Ubuntu Linux, where it clones the repository, installs dependencies and runs tests.↗ |
| Verification | Runs the repository's configured test commands plus an AI code review and records both in a merge evidence report. A repository with no configured commands is not built or tested, and the report shows the skipped check.CLAUDE.mdinternal/agent/evidence.gointernal/agent/gate_command.go | A critic agent reviews every proposed change adversarially before completion, flagging subtle bugs, missed edge cases and inefficient code.↗ |
| Human gates | A person approves, edits or rejects the plan before code is written, and a person marks the task done, which starts the squash, push and pull request when GitHub is connected. Opt-in autopilot keeps both gates.CLAUDE.mdinternal/agent/evidence.go | Jules presents a plan you approve before code is written; if you navigate away, Jules auto-approves the plan on a timer.↗ |
| Pricing model | The self-serve plans are Free, Pro and Team; an Enterprise plan is arranged with Fraway on request. Model usage is paid to the provider whose key the workspace stores, or through managed inference on Pro and above.internal/entitlement/entitlement.goENTITLEMENTS.mdweb/src/lib/components/billing/PlanCards.svelte | Three plans with daily task limits: Jules (15), Jules in Pro (100) and Jules in Ultra (300); the paid tiers come with Google AI Pro and Google AI Ultra subscriptions.↗ |
How to read the table
- Where it runs compares hosted machines, machines you operate, and the options in between.
- Where your code goes compares where a checkout lives and which hosting services each product works with.
- Model choice compares fixed model sets, model pickers and keys you bring yourself.
- Isolation compares virtual machines, containers, sandboxes and network limits.
- Verification compares test runs, reviewing models and security scans.
- Human gates compares plan approval, pull request review and approval of individual actions.
- Pricing model compares plans, usage credits and the model spend you pay directly.
Where Jules fits better
- You want to start without paying: there is a plan available without cost, with 15 tasks per day and 3 concurrent tasks.↗↗
- You already subscribe to Google AI Pro or Google AI Ultra, which include the Pro and Ultra tiers of Jules.↗
- You want a hosted agent you can leave while it works, with a browser notification when the task completes or needs your input.↗
What Google documents
A failed Jules task is retried automatically; if it keeps failing, it is marked as failed and you are notified.↗
Long-running processes such as dev servers or watch scripts are not currently supported in setup scripts, so setup uses discrete install and test commands.↗
Preinstalled toolchains in the VM include Node.js, Bun, Python, Go, Java and Rust.↗
Paid plans are accessed through a Google AI Plans subscription, which is currently available only for individual Google accounts ending in @gmail.com.↗
How DevFlow runs the work
A DevFlow task moves from planning to a plan review, then to decomposition into at most 8 subtasks, implementation, verification and a written summary. Each task gets its own branch, named after its task ID, in a worktree under the repository's .devflow/worktrees directory.
By default, every agent invocation has a hard limit of 90 minutes and is stopped after 45 minutes without output. A workspace can also set a monthly spend cap, and a task over that cap fails with a reason before it starts.
On Pro and higher plans, finalization also runs dependency scanners for the languages DevFlow detects, such as govulncheck for Go modules and pnpm audit for Node packages, each stopped after 300 seconds by default. Scan results go into the evidence report and do not block the pipeline.
What DevFlow records along the way
A task that finishes implementation gets a merge evidence report listing the models that did the work, each subtask's verifier outcome, the build checks, the security scan summary, the final review and the people who approved the plan and clicked Mark Done. The report is added to the pull request body, and later rework refreshes it there.
Agent processes start with an allowlisted environment instead of inheriting the server's own. Provider keys and GitHub tokens are encrypted at rest with AES-256-GCM.
FAQ
Does Jules ask for plan approval the way DevFlow does?
Jules presents a plan before writing code, and if you navigate away it auto-approves that plan on a timer. In DevFlow, code is written only after a person approves the plan, including on tasks that autopilot starts.
Where does Jules run code compared with DevFlow?
Jules runs each task in a fresh, cloud-based virtual machine where it clones the repository. DevFlow gives each task a git worktree on the machine that runs DevFlow and runs test commands in non-root containers.