Devin

Devin — Fully delegated cloud engineer: file a task in Slack or the web app, get a PR back. Devin is the purest cloud-delegate on this page — there is no local client. You describe a task in Slack or the web app and it works in its own VM with a shell, editor and browser, then opens a pull request. That model suits well-specified, self-contained tickets and suits nothing else. Pricing is ACU-based with a low entry plan, and the underlying models are Cognition's business rather than yours. Built by Cognition. Founded 2023. Series C+. Licensed Proprietary.

We track it in 1 comparison — Coding agents — so every claim below is a cell in a table you can open and check rather than an impression. Across those rosters it sits against 16 other tools, and what follows is where it visibly separates from them.

Where it wins.

• Opens PRs — Yes, which only 6 of 16 tools here manage.
• Background agents — Yes, which only 5 of 16 tools here manage.
• Token markup — Yes, which only 3 of 16 tools here manage.
• Repo indexing — hybrid index + agentic, tied for best across 2 of 16 tools.

Each of those is ranked against the whole roster on its category page, not against a hand-picked subset, so a first place here means first of everything we list.

Where it gives ground.

• BYOK — No. Claude Code records Yes.
• Subagents — No. Claude Code records Yes.
• Pricing model — opaque credits, 14th of 16. opencode records BYOK tokens only.
• Model breadth — no model choice, 15th of 16. opencode records any provider / router.

None of these disqualify it on their own. They are the fields to check against your own requirements before you commit, because they are the ones where a competitor genuinely does better.

Provenance. 22 of 26 tracked fields carry a value for Devin, and 4 of those cite a document you can open. Last verified 2026-01-15. Every figure keeps its own provenance — measured by us, claimed by the vendor, inferred, or community-reported — and we would rather print a dash than a guess.

Its nearest neighbour in our data is Aider. Devin is ahead on Opens PRs (Yes against No) and Background agents (Yes against No). Aider takes BYOK (Yes against No) and Model breadth (any provider / router against no model choice). That pattern repeats across the rest of the roster — see Devin alternatives for the other rivals, each compared the same way.

Company

Cognition

Founded

2023

Funding

Series C+

Licence

Proprietary

Fields we track

22 of 26

Last verified

2026-01-15

The clearest expression of full delegation: no local client, no model picker, a pull request or nothing. A real fit for well-specified tickets on a repo with good tests, and a poor one for anything exploratory. ACU pricing means you learn the cost afterwards.

Opens PRs

●Yes1st of 16

Inferredverified 2026-01-15

BYOK

○No15th of 16

Inferredverified 2026-01-15

Subagents

○No10th of 14

Inferred

Background agents

●Yes1st of 16

Inferredverified 2026-01-15

Pricing model

opaque credits14th of 16

Vendor-claimedverified 2026-01-15source

Model breadth

no model choice15th of 16

Inferred

Checkpoint & undo

○No14th of 16

Inferred

Token markup

●Yes1st of 16

Inferred

Devin is the right call in these situations, each one drawn from a field we actually record:

• Backlogs of small, well-specified tickets nobody wants to pick up.
• Teams who want work dispatched from Slack rather than a terminal.
• Opens PRs is your binding constraint. Devin records Yes, which only 6 of the 16 tools in the Coding agents roster do. We define that field as a first-class path to a pull request: a built-in command, a vendor-published GitHub App with its own identity, or a hosted runner.
• Background agents is your binding constraint. Devin records Yes, which only 5 of the 16 tools in the Coding agents roster do. We define that field as can you fire off a task that keeps running once the client is closed — on vendor infrastructure or a detached local runner — and check back later?
• Token markup is your binding constraint. Devin records Yes, which only 3 of the 16 tools in the Coding agents roster do.
• Repo indexing is your binding constraint. Devin records hybrid index + agentic, the best figure in the Coding agents roster.

Reach for something else when any of the following is a requirement rather than a nice-to-have:

• BYOK. Devin records No on the Coding agents table. Claude Code records Yes on the same field. If that is a hard requirement rather than a preference, start elsewhere.
• Subagents. Devin records No on the Coding agents table. Claude Code records Yes on the same field. If that is a hard requirement rather than a preference, start elsewhere.
• Pricing model. Devin records opaque credits, 14th of 16 in the Coding agents roster. opencode records BYOK tokens only on the same field. If that is a hard requirement rather than a preference, start elsewhere.
• Model breadth. Devin records no model choice, 15th of 16 in the Coding agents roster. opencode records any provider / router on the same field. If that is a hard requirement rather than a preference, start elsewhere.
• Checkpoint & undo. Devin records No on the Coding agents table. Claude Code records Yes on the same field. If that is a hard requirement rather than a preference, start elsewhere.

We publish this block because a comparison that only lists what a tool is good at is marketing. Every figure above sits on the same page as its source, and the field definitions are on the category tables if you want to check how we measured them.

What we don't know. 4 of the 26 fields we track for Devin are still blank: MCP, GitHub stars, Terminal-Bench and Bench model. Those render as dashes rather than as zeroes or assumptions, because an empty cell and a bad cell are not the same thing and only one of them is honest. If you know any of these figures and can point at a document, tell us.