Paraphrased from each maker’s own description. Select a line for the quote.
Capabilities not yet checked for all
cmux
· also Goose
· also T3 Code
Goose
· also cmux
HumanLayer
· also T3 Code
· also T3 Code
· also T3 Code
T3 Code
· also HumanLayer
· also HumanLayer
· also cmux
· also HumanLayer
Checked for Goose, not yet for cmux, HumanLayer and T3 Code: Model providers (,,,,,SpaceXSI (Grok),,,,,,,,Meta AI (Llama),,Microsoft Foundry (Azure AI Foundry),,,,,OVHcloud AI Endpoints,,FriendliAI,,,,,,,,,,Amazon SageMaker AI,,,,,,, )
Checked for cmux, Goose and HumanLayer, not yet for T3 Code: Bring your own key (cmux: ; Goose: ; HumanLayer: )
Checked for cmux, HumanLayer and T3 Code, not yet for Goose: Agents it runs (cmux: ,,,,, ; HumanLayer: , ; T3 Code: ,,,,, )
Checked for cmux, Goose and T3 Code, not yet for HumanLayer: Editors and systems (cmux: ,, ; Goose: ,,, ; T3 Code: ,, )
Same for all 4 (1): Agent teams
Agent teams · · ·
Provider names use the same listing as each tool page. Dotted values open their quote. A capability not shown is not yet checked; the tool may still have it.
Lowest monthly plan billed monthly, lower is cheaper
cmux
$50 /moGooseNot yet checkedHumanLayer
$100 /user/moT3 CodeNot yet checked
Platforms listed surfaces
cmux
3Goose
6HumanLayer
1T3 Code
6
Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only. After activation, the score is 80% mindshare plus 20% of the greater of mindshare and the vote score. GitHub stars do not affect the Index score. Mindshare uses a log scale; votes use the square-root curve and a 100-vote floor. Ranks use unrounded scores. Mindshare and adoption bars are log-scaled; the others are linear within this comparison. How the score is built
AnthropicOpenAIGoogleOpenRouterOllamaSpaceXSI (Grok)Amazon BedrockGroq+32 more model providers
LM StudioMistralGitHub CopilotAzure OpenAICerebrasMeta AI (Llama)LiteLLMMicrosoft Foundry (Azure AI Foundry)Novita AIPerplexityVeniceScalewayOVHcloud AI EndpointsAtomic ChatFriendliAIDatabricksTrustedRouterAvianLemonadeAI/ML APIDocker Model RunnerEmpirioLabs AINEAR AI CloudTetrate Agent Router ServiceAmazon SageMaker AIGondolallmmanOnysoft AI GatewayRamaLamaRoutstrSayGMSnowflake
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.