agentboards.org
Compare/Devin vs Jules

DevinvsJules

Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.

Devin
Cognition · Autonomous SWE
#139MCP
Panel
5.3
2 spec wins
Reliability
5.3
Usefulness
5.8
Cost
4.3
Longevity
5.5

“Replaced ACUs with credits in April 2026, so now the meter runs in a unit you already understand.”

Jules
Google · Autonomous SWE
#141MCP
Panel
5.7
1 spec wins
Reliability
5.3
Usefulness
5.8
Cost
6.3
Longevity
5.3

“Fifteen free tasks a day, as long as you are over 18 and using a personal Gmail rather than the company account.”

Spec by spec

SpecDevinJules
Architecture
CategoryAutonomous SWEAutonomous SWE
Runscloud, sandbox, localcloud, sandbox
Platformsweb, macos, linux, windowsweb, macos, linux, windows
Context windownot documentednot documented
Protocols
MCP clientYesYes
MCP serverYesNo
Capabilities
Runs terminal commandsYesYes
Multi-file editsYesYes
Git operationsYesYes
Browser controlYesCloud sessions ship a first-party interactive Browser tool alongside the shell and IDE, with saved browser profiles for authenticated sites (https://docs.devin.ai/work-with-devin/browser-auth). YesThe default VM image includes Playwright and chromedriver, and Jules renders a front end and returns screenshots to verify its work (https://jules.google/docs/environment).
Sandboxed executionYesCloud sessions run on a dedicated Devin machine built from environment blueprints and snapshots, and the Devin CLI adds OS-level isolation locally (https://docs.devin.ai/cli/sandbox). YesEach task gets a secure, short-lived Ubuntu VM with internet access (https://jules.google/docs/environment).
Multi-agent orchestrationYesNo
Headless / CI modeYesYesScriptable through `jules remote new --repo ... --session "..."` and the REST API (https://jules.google/docs/cli/reference).
Models
BackboneUndisclosed (Cognition-managed models)Gemini 3 Flash, Gemini 3.1 Pro
Bring your own modelNoA cross-provider model picker (`--model` / `/model` / config `agent.model`) selects between Anthropic, OpenAI, Google, Cognition and open-source models, but every one of them is served by Cognition: the CLI model reference documents no API key, base URL, gateway, Bedrock, Vertex or Azure deployment of your own, matching pricing.byok = false. NoJules runs only on Google-hosted Gemini models; there is no provider picker, custom base URL, gateway or cloud deployment of your own.
Local modelsNoNo base URL, gateway or local endpoint setting exists in the Devin CLI config reference (https://docs.devin.ai/cli/reference/configuration/config-file). NoTasks run in a Google-hosted VM with no configurable model endpoint, so no local LLM can be used.
Cost
Pricing modelmixedsubscription
Starts at$20/mo$19.99/mo
Free tierYesYes
Bring your own keyNoUsage is billed in Cognition ACUs and no LLM provider key can be supplied; Devin Outposts (https://docs.devin.ai/cloud/outposts/overview) only moves session compute onto your own machines. NoAccess comes from a Google AI plan; no Gemini API key or Google Cloud project of your own can be attached.
Openness
Open sourceNoNo
Licenseproprietaryproprietary
GitHub starsn/an/a

Which one would each critic pick

CriticDevinJulesPick
El Juez——not enough reviews
El Amigo6.36.8Jules — Use Jules for the backlog you never get to, fifteen free tasks a day on a personal Google account, and do not adopt it as a team tool because the paid plans do not accept business accounts yet.
El Crítico5.36.3Jules — Jules runs your repo in a VM you cannot inspect on a model you cannot choose, and the failure mode is a pull request built on an environment that never installed correctly.
El Profesor5.06.3Jules — Jules has the correct autonomous architecture, an isolated VM, a plan reviewed before edits, tests run in place, and publishes no benchmark by which to judge what it does with it.
La Inversora6.86.0Devin — Well funded, acquisitive, and repricing in public; the Windsurf purchase bought distribution, and the April 2026 plan change says the ACU math was not working.
La Jefa5.84.8Devin — Teams at $80 plus $40 per full seat with shared credits, and Enterprise by quote; the free flex seats are the part finance will like.
El Hacker2.54.3Jules — A closed VM, Gemini only, a curated MCP list and no key of my own; the CLI and REST API are the only handles, and they are decent handles.

Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.

Want a third column? The compare tool handles any two agents. Three-way comparisons are on the roadmap once the spec rows are all verified.