agentboards.org
Compare/AWS Transform vs Devin

AWS TransformvsDevin

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

AWS Transform
Amazon Web Services · Autonomous SWE
#125
Panel
6.0
0 spec wins
Reliability
5.5
Usefulness
5.7
Cost
4.7
Longevity
8.2

“It migrates Fujitsu GS21 mainframes, a sentence that will find exactly the four people who needed to read it.”

Devin
Cognition · Autonomous SWE
#139MCP
Panel
5.3
7 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.”

Spec by spec

SpecAWS TransformDevin
Architecture
CategoryAutonomous SWEAutonomous SWE
Runscloudcloud, sandbox, local
Platformswebweb, macos, linux, windows
Context windownot documentednot documented
Protocols
MCP clientNoYes
MCP serverNoYes
Capabilities
Runs terminal commandsNoYes
Multi-file editsYesYes
Git operationsYesYes
Browser controlNoYesCloud 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).
Sandboxed executionNoYesCloud 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).
Multi-agent orchestrationYesAWS describes specialised agents per domain (mainframe, .NET, VMware, discovery and planning) working across the phases of a transformation. Yes
Headless / CI modeNoYes
Models
BackboneAmazon BedrockUndisclosed (Cognition-managed models)
Bring your own modelNoNoA 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.
Local modelsNoNoNo base URL, gateway or local endpoint setting exists in the Devin CLI config reference (https://docs.devin.ai/cli/reference/configuration/config-file).
Cost
Pricing modelusagemixed
Starts atn/a$20/mo
Free tierNoYes
Bring your own keyNoNoUsage 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.
Openness
Open sourceNoNo
Licenseproprietaryproprietary
GitHub starsn/an/a

Which one would each critic pick

CriticAWS TransformDevinPick
El Juez——not enough reviews
El Amigo6.06.3Devin — The most complete autonomous stack here, with a cloud VM, browser and pull requests; pay for it if you can hand off whole tickets, not if you want a pair.
El Crítico5.85.3AWS Transform — A migration fails quietly through changed behaviour, not a stack trace, and the service documentation describes no verification step that would catch it.
El Profesor6.05.0AWS Transform — Specialised agents are assigned per domain across discovery, wave planning, landing zones and network migration, and the models behind them are never named.
La Inversora8.06.8AWS Transform — Billed straight through the AWS account, and the pricing page did not render a readable rate card at listing, which is a strong position and a weak disclosure.
La Jefa6.85.8AWS Transform — Seats are the wrong unit here; this is a programme billed to an account we already hold, with identity and audit inherited from the cloud contract legal signed.
El Hacker3.52.5AWS Transform — Proprietary, cloud only, no bring-your-own-key, no local option, no tool protocol, and the entry point is a button in a web console.

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.