# Devin — Cloud AI software engineer that takes a ticket, works in its own VM, and opens a pull request. > Source: The Agents Index — https://theagentsindex.com/devin (structured, researched, re-verified) > Facts last verified: 2026-09-02 Devin is Cognition's autonomous AI software engineer: you delegate a ticket and it writes, runs and tests the code in its own cloud VM with a shell, browser and editor. Cognition sizes it for backlog work a person could finish in about three hours. | Fact | Value | | --- | --- | | Website | https://devin.ai | | Price | from $20/month | | Free tier | Yes | Free plan: limited Devin usage, 1 member, with access to Devin Review and DeepWiki. Free users can upgrade to any paid plan at any time from Settings > Plans. ## What it does **Writes code** · Yes — Implements entire features from a prompt or a Linear/Jira ticket, running and testing the code it writes. > Devin is an autonomous AI software engineer that can write, run and test code. > — https://docs.devin.ai/get-started/devin-intro · Introducing Devin, opening paragraph **Debugs and fixes** · Yes — Reproducing and fixing bugs is named as a core task, including bugs arriving as tickets or bug reports. > Ask Devin to tackle Linear/Jira tickets, implement entirely new features, repro and fix bugs, build internal tools, and more! > — https://docs.devin.ai/get-started/devin-intro · Introducing Devin, opening paragraph **Writes tests** · Yes — Analyses the repository's existing test style and writes additional tests to raise coverage. > Devin can bridge this gap by analyzing a codebase’s existing test suite style and increasing coverage of less critical but still important functions. > — https://docs.devin.ai/use-cases/tutorials/code-coverage · Improving Code Coverage With Devin, first paragraph **Reviews code** · Yes — Devin Review reviews pull requests anyone authored, reorganising and explaining large diffs in the Devin webapp. > Devin Review is a full-service code review platform within the Devin webapp that turns large, complex PRs into intuitively organized diffs and precise explanations. > — https://docs.devin.ai/work-with-devin/devin-review · Devin Review, opening paragraph **Whole-codebase work** · Yes — Migrations spanning many files, modules or whole repositories are the stated use for fanning work out to parallel sessions. > This is the most powerful way to tackle work that spans many files, modules, or repositories — migrations, bulk test coverage, parallel research, and more. > — https://docs.devin.ai/work-with-devin/advanced-capabilities · Managed Devins section **Ships it** · Partly — Stops at the pull request in your repository; your team merges and ships through its existing pipeline. > Most Devin work follows the normal software delivery path: Devin works in your repository, opens a pull request, and your team reviews, merges, and ships it through its existing pipeline. > — https://docs.devin.ai/product-guides/deployment-capabilities · Devin app deployments, opening paragraph ## How much it does unattended **Runs autonomously** · Yes — Automations and schedules start sessions from events, so Devin works the task with nobody tagging it. > Instead of manually tagging Devin every time a bug is reported or a CI check fails, you define the trigger once and Devin handles each event as it arrives. > — https://docs.devin.ai/product-guides/automations · Automations, opening paragraph **Multi-agent** · Yes — A coordinator Devin delegates to child sessions running in parallel, each on its own isolated VM. > Devin can break down large tasks and delegate them to a team of managed Devins working in parallel, each running in its own isolated VM. > — https://docs.devin.ai/work-with-devin/advanced-capabilities · Managed Devins, first paragraph **Agent permissions** · Yes — Graded modes from prompt-before-writing up to full bypass, plus an OS-sandboxed autonomous mode. > In Normal mode (the default), read-only operations are auto-approved while writes and shell commands require your explicit approval. > — https://docs.devin.ai/cli/reference/permissions · Default Permission Behavior, paragraph below the mode table ## Which models it runs on **Claude** · Yes — Anthropic models are selectable in Devin CLI, where opus and sonnet resolve to the latest in each family. > We typically support the latest and greatest models from Anthropic, OpenAI, Google, and Cognition within minutes of their launch. > — https://docs.devin.ai/cli/models · Available Models section **GPT** · Yes — OpenAI models are selectable in Devin CLI, with gpt among the three the vendor recommends trying first. > At minimum we recommend trying swe, gpt, and opus. We find that the vast majority of use-cases can be covered by these three. > — https://docs.devin.ai/cli/models · Model Selection Tips section **Open models** · Yes — Open-weight models including DeepSeek, Kimi and GLM are selectable in Devin CLI. > We also support a number of leading open source models like DeepSeek, Kimi, and GLM. > — https://docs.devin.ai/cli/models · Available Models section **Model choice** · Partly — You pick the model in Devin CLI, or leave it to the Adaptive router; cloud Devin sessions document no model selector. > Devin CLI supports multiple AI models. You can choose the best model for your task to optimize for maximum capability, speed, or cost efficiency. > — https://docs.devin.ai/cli/models · Models, opening paragraph ## Where you use it **In your editor** · Yes — Runs inside JetBrains IDEs from the AI Chat panel over the Agent Client Protocol, including Remote Development. > JetBrains IDEs can run Devin as an agent inside AI Chat using the Agent Client Protocol (ACP). > — https://docs.devin.ai/cli/acp/jetbrains · JetBrains, opening paragraph **On the command line** · Yes — Devin CLI is a local terminal agent working on your own files, installed by curl script, Homebrew cask or Windows installer. > Devin CLI is a local coding agent that runs directly in your terminal. It works with your local files and environment, giving you fast, interactive assistance right where you code. > — https://docs.devin.ai/cli · Devin CLI vs. Devin section **In your pipeline** · Yes — Creates pull requests and answers PR comments inside your repositories once the SCM integration is installed. > Integrating Devin with your GitHub organization enables Devin to create pull requests, respond to PR comments, and collaborate directly within your repositories. > — https://docs.devin.ai/integrations/gh · GitHub, overview paragraph above Setting up the Integration **In a browser** · Yes — Hosted web app at app.devin.ai; each session carries its own shell, embedded IDE and browser you can take over. > To access Devin, sign up at app.devin.ai. Individual and Teams plans are available. > — https://docs.devin.ai/get-started/devin-intro · Getting Access section ## Whose machine it runs on **Self-hosted** · Partly — Outposts runs session execution on machines you operate, but the agent loop stays in Cognition's cloud. > Outposts lets you run Devin sessions inside infrastructure you control — your own VMs, containers, Kubernetes clusters, or even a Mac Mini on your desk. > — https://docs.devin.ai/cloud/outposts/overview · Devin Outposts: self-hosted infrastructure, first paragraph **Open source** · Partly — Only the Outposts Kubernetes orchestration operator is published as open source; no source distribution is documented for Devin itself. > deploy devin-outpost-k8s — our open-source operator that runs the loop on any Kubernetes cluster > — https://docs.devin.ai/cloud/outposts/overview · Devin Outposts overview, Orchestration paragraph ## What it costs to run **How it meters** · Yes — Metered by the work performed: plan quota then prepaid on-demand credits self-serve, Agent Compute Units on Enterprise. > Self-serve customers consume their plan's included quota first, then draw from prepaid on-demand credits. > — https://docs.devin.ai/admin/billing/usage · Usage, unit bullets at the top of the page **Free tier** · Yes — A Free plan you sign up for directly, with limited usage and an upgrade path to any paid plan. > The Free plan lets you try Devin with limited usage. > — https://docs.devin.ai/admin/billing/self-serve · Free section **API access** · Yes — REST API creates and drives sessions under an organization scope, with a separate enterprise scope for analytics and audit logs. > The Devin API enables you to integrate Devin into your applications, automate workflows, and build powerful tools. > — https://docs.devin.ai/api-reference/overview · API Overview, first paragraph **MCP server** · Yes — An authenticated MCP server at mcp.devin.ai lets any MCP client create sessions, query repositories and manage playbooks. > The Devin MCP server provides programmatic access to Devin's platform capabilities for both private and public repositories. > — https://docs.devin.ai/work-with-devin/devin-mcp · Devin MCP, first paragraph **Bring your own key** · Partly — Your own AWS KMS key encrypts data at rest, but only on the Enterprise Assured deployment; no bring-your-own-inference is documented. > With CMK, you provide your own AWS KMS key, and Cognition uses it to encrypt data stored in your dedicated tenant — including session data and VM snapshots. > — https://docs.devin.ai/enterprise/security-access/security/customer-managed-keys · Customer Managed Keys, Overview section ## Buying it for a team **A company can buy it** · Yes — The self-serve Teams plan buys for a whole organisation with unlimited members; Pro and Max cannot be shared. > The Teams plan is Devin's self-serve plan for teams of any size. > — https://docs.devin.ai/admin/billing/self-serve · Teams section **Seat model** · Yes — Teams charges $40 per full seat with unlimited free flex seats, under an $80/month account floor and no seat ceiling. > $40/month per seat, billed as a fixed recurring line item. > — https://docs.devin.ai/admin/billing/self-serve · Full seats vs. flex seats, Full seat card **Pooled budget** · Yes — Teams draw from one shared credit pool with no per-member balance, while each full seat also carries its own quota. > On the Teams plan, credits are shared across all members, with no per-member balance. Any teammate can draw from the shared pool. > — https://docs.devin.ai/admin/billing/self-serve · On-demand credits, bullet list **Admin controls** · Yes — Admins bind network, MCP, git and GitHub-token restrictions to an org, an automation or a single session; enterprises can enforce them as a floor. > Security profiles let you define reusable bundles of security restrictions — network access, MCP access, git access, and GitHub CLI credentials > — https://docs.devin.ai/product-guides/security-profiles · Security Profiles, first paragraph **Audit log** · Partly — Logins are recorded in an enterprise audit log; the docs describe audit logs only at the enterprise level. > Records the login in the enterprise audit log > — https://docs.devin.ai/enterprise/security-access/sso/guide · The User Login Experience, step 5 sub-bullets **Single sign-on** · Partly — SAML 2.0 and OIDC (Okta, Microsoft Entra ID, generic) on Devin Enterprise, configured by the Cognition team, with IdP group to role mapping. > Create an application in your identity provider (Okta, Microsoft Entra ID, or any SAML/OIDC-compliant IdP) and share the following credentials with your Cognition team > — https://docs.devin.ai/enterprise/security-access/sso/guide · 1. Setting Up SSO, Creating Your SSO Application ## What happens to your code **Opt out of training** · Partly — Training is on by default and the opt-out is paid-plans-only; opting out also enables Zero Data Retention with the model providers. > By default, we may use your data for model training purposes to improve and enhance the Services. If you're on a paid plan, you can opt out at any time on the Data Controls settings page. > — https://docs.devin.ai/admin/security · Privacy & Intellectual Property, How is your data used to improve Devin? **Data residency** · Partly — The AWS region holding a dedicated tenant is not published; the vendor confirms it on request. > Contact your Cognition account team to confirm the AWS region of your dedicated tenant. > — https://docs.devin.ai/enterprise/security-access/security/customer-managed-keys · Prerequisites, Info callout **Getting out** · Partly — Purchased on-demand credits roll over and never expire; no account-wide data export is documented beyond invoices and per-resource API reads. > Roll over month-to-month. Purchased credits never expire. > — https://docs.devin.ai/admin/billing/self-serve · On-demand credits, first bullet **Certifications** · Partly — SOC 2 Type II since September 2024; the Trust Center additionally lists ISO/IEC 27001:2022 and CCPA, behind an NDA request. > Cognition has been SOC 2 Type II certified since September 2024. > — https://docs.devin.ai/enterprise/security-access/security/enterprise-security · Third-Party Audits and Certification ## Provenance 1 of 26 sources behind the facts above are independent of the vendor. ## Coverage elsewhere Pages about this product that the vendor does not control. The label states how independent each one is. | Source | Kind | Read | | --- | --- | --- | | cognition.com | Independent source | 2026-08-23 | | awesomeagents.ai | Independent source | 2026-08-23 | | themodernblog.com | Independent source | 2026-08-23 | ## What changed - 2026-09-02 — Capabilities · Commercial terms · Free tier - 2026-08-31 — Capabilities · Commercial terms · Free tier · Price - 2026-08-23 — One-liner · Summary - 2026-08-16 — One-liner · Summary ## Correcting this record Anything marked "Not established" is a question we have not answered — it is not a No. If you represent Devin, or anything here is wrong or out of date, you can supply it with a source: the operations this site accepts from an agent are listed at https://theagentsindex.com/.well-known/agents.json — that catalogue needs no key to read, and each entry states its own auth. Supplying evidence is free. Nothing that can be bought here changes what a field says, whether a gap is closed, or how this record is scored.