Devin

An AI software engineer for autonomous coding work

Devin helps engineering teams delegate coding tasks like migrations, refactors, and bug fixes. It works with Slack, Teams, Linear, and Jira, then plans, tests, and opens PRs for human review.

Agenticness = how independently a tool can take action, scored across 9 dimensions. Scored independently by David Kooi, Skylark Creations — see full rubric →

See pricing ↓

Code Execution

File Access

Multi-Agent

Cloud Hosted

Copilot (Human-in-Loop)

Fully Autonomous

Visit Devin

Is this your tool? Claim this listing to manage your content and analytics.

Recent activity

What's happened with Devin lately

May 22, 2026
Score change
Agenticness score 16 → 14 ↓16 → 14/36(-2)
May 22, 2026
Score change
Agenticness score 11 → 16 ↑11 → 16/36(+5)

News mentions sourced from our news feed; score changes from periodic re-evaluations.

Ask about Devin

Get answers based on Devin's actual documentation

Try asking:

About

What It Is

Devin is an AI coding agent built for software engineering teams. According to the site, it is designed to help developers work through large engineering tasks such as migrations, refactors, and backlog cleanup by taking on repetitive implementation work in parallel cloud agents.

What to Know

Devin is fairly agentic for a coding tool: the content shows it can break work into subtasks, make changes, run tests, and produce PRs with a human in the loop. That makes it more suitable for structured engineering work than for open-ended...

Key Features

Delegates coding tasks to cloud agents

Breaks work into ticket, plan, test, and PR stages

Integrates with Slack, Teams, Linear, and Jira

Tests code changes before handing them off

Creates pull requests for native review

Use Cases

Large codebase migrations where repetitive refactoring needs to be delegated

Modernizing monoliths into smaller modules

Fixing high-volume lint or style issues across many files

Agenticness: Adaptive Collaborator

Proposes and executes multi-step plans with your approval.

High evidence

Last evaluated: May 22, 2026

This tool has strong action capabilities but limited safety controls. Use with appropriate oversight.

Dimension Breakdown

Action Capability

Autonomy

Planning

Adaptation

State & Memory

Reliability

Interoperability

Safety

Operator Sovereignty

How agenticness works →

Related Tools

See all Coding Agents tools compared

Kilo Code

Agenticness15/36·Adaptive Collaborator

Coding Agents

Kilo Code is the v5.x community fork of Roo Code (which was archived May 15, 2026). Open-source VS Code extension for agentic coding — Apache 2.0 licensed, BYOK across many providers, runs locally as an IDE extension.

OpenHands

Agenticness18/36·Adaptive Collaborator

Coding Agents

OpenHands (formerly OpenDevin) is a fully autonomous open-source AI coding agent. MIT-licensed core, plans + executes Python actions via CodeAct, uses browser + terminal + files. ~72% on SWE-bench Verified with Sonnet 4.5 via the OpenHands Software Agent SDK (arXiv:2511.03690).

Augment Code

Agenticness17/36·Adaptive Collaborator

Coding Agents

Augment Code is an enterprise-focused AI coding agent built around a 200K-token Context Engine. Closed-source SaaS with strong SWE-bench Verified results (70.6% self-reported) and the highest accuracy on the only public benchmark for AI-assisted code review.

AICode

Agenticness17/36·Adaptive Collaborator

Coding Agents

AICode is a VS Code extension for enterprise teams working in large legacy codebases. It maps dependencies and architecture, audits specifications before coding, and keeps changes reviewable inside your infrastructure.

Enterprise

Chrome Extension

B2B

Stay in the loop

Get the weekly agentic AI briefing

New tools, top picks, and trends — delivered every Thursday.

Ask about Devin

About

Dimension Breakdown

Categories

Ask about Devin

Related Tools

Get the weekly agentic AI briefing