Editors and systemsDeepSeek Harness 2 · Goose 4 · T3 Code 3 · ZCode 3
DeepSeek Harness,
Goose,,,
T3 Code,,
ZCode,,
Pick this if…
Goose
T3 Code
ZCode
Paraphrased from each maker’s own description. Select a line for the quote.
Capabilities not yet checked for all
DeepSeek Harness
· also T3 Code and ZCode
Goose
· also ZCode
· also T3 Code
T3 Code
· also ZCode
· also Goose
· also ZCode
· also DeepSeek Harness and ZCode
ZCode
· also Goose
· also T3 Code
· also T3 Code
· also DeepSeek Harness and T3 Code
Checked for DeepSeek Harness, Goose and T3 Code, not yet for ZCode: Price (DeepSeek Harness: ; Goose: ; T3 Code: )
Checked for DeepSeek Harness, Goose and ZCode, not yet for T3 Code: Model providers (DeepSeek Harness: ,,,Moonshot AI,Z.ai; Goose: ,,,,,SpaceXSI (Grok),,,,,,,,Meta AI (Llama),,Microsoft Foundry (Azure AI Foundry),,,,,OVHcloud AI Endpoints,,FriendliAI,,,,,,,,,,Amazon SageMaker AI,,,,,,, ; ZCode: )
Checked for DeepSeek Harness and Goose, not yet for T3 Code and ZCode: Bring your own key (DeepSeek Harness: ; Goose: )
Checked for T3 Code and ZCode, not yet for DeepSeek Harness and Goose: Agents it runs (T3 Code: ,,,,, ; ZCode: )
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.
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 BedrockLM Studio+32 more model providers
GroqMistralGitHub CopilotAzure OpenAICerebrasMeta AI (Llama)LiteLLMMicrosoft Foundry (Azure AI Foundry)Novita AIPerplexityScalewayVeniceOVHcloud AI EndpointsAtomic ChatFriendliAIDatabricksTrustedRouterEmpirioLabs AINEAR AI CloudAI/ML APIAvianLemonadeDocker Model RunnerTetrate 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.