Skip to content
ADE Index

devx vs GPT Engineer vs Hermes Agent

Up to four tools, row by row. We do not guess: a cell we have not checked says so.

How they differ

Model providersdevx 134 · GPT Engineer 5 · Hermes Agent 49 · 3 in all
,,,,,,,,
+123 more model providers
,,,,,,,,,,,,,,LiteLLM Proxy,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+ providers you addNot every provider checked yet
,+ providers you add
,,,,,,,,
+38 more model providers
,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
Show 3 shared
,,
Pick this if…

Paraphrased from each maker’s own description. Select a line for the quote.

Checked for devx and GPT Engineer, not yet for Hermes Agent: Editors and systems (devx: , , , ; GPT Engineer: , )

Same for all 3 (2): Price: Free (open source) · Bring your own key: Yes
  • Price: Free (open source) · ·
  • Bring your own key: Yes · ·

Not yet checked for any of these tools: agents it runs.

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.

About these tools

devx

Hermes Agent

How to read the Index score

At a glance

Index score out of 100

devx8GPT Engineer8Hermes Agent48

Mindshare HN mentions, 90 days

devx1GPT Engineer1Hermes Agent84

Adoption GitHub stars, not scored

devxNot yet checkedGPT Engineer55kHermes Agent264k

Release days last 90 days

devxNot yet checkedGPT Engineer0Hermes Agent19

Platforms listed surfaces

devx4GPT Engineer2Hermes AgentNot yet checked

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

Differences only
3 of 4
devxCLI agent
GPT EngineerDeprecatedAnton Osika · CLI agent
Hermes AgentCLI agent
Interface
What it is
Terminal coding agent for Termux, Windows, macOS and Linux
CLI platform to experiment with codegen.
Terminal agent for writing, reviewing and running code in local projects
Category
CLI agent
CLI agentDeprecated
CLI agent
Runs on
Android
Yes
Not yet checked
Not yet checked
Linux
Yes
Not yet checked
Not yet checked
Terminal
Not yet checked
Yes
Not yet checked
Windows
Yes
Yes
Not yet checked
macOS
Yes
Not yet checked
Not yet checked
Models and agents
Model providers
OpenAIAnthropicGoogleOpenRouterOllamaSpaceXSI (Grok)DeepSeekLM Studio
+126 more model providers
Moonshot AIGroqZ.aiMistralFireworksMiniMaxGitHub CopilotOpenCode GoHugging FaceCerebrasOpenCode Console (OpenCode Zen)Alibaba (Qwen)XiaomiNVIDIABasetenMeta AI (Llama)Cloudflare Workers AILiteLLM ProxyNebius Token Factory (Nebius AI Studio)Novita AIPerplexityRequestyScalewayChutesGMI CloudInceptionStepFunSyntheticCoreWeave (Weights & Biases)FriendliAIKilo CodeNanoGPTOVHcloud AI EndpointsSiliconFlowTokenHubAtomic ChatMeituanPoePoolsideArcee AICrusoeDatabricksEden AIio.netOpperTrustedRouterZenMuxai&Charm HyperCoralBricksCortecsDigitalOceanEmpirioLabs AIHelicone AI GatewayHetznerModelScopeMorphNeuralwatt CloudQiniu CloudSakana AISarvamTensorX302.AIAbliterationAKI.IOClinePassDaoXEGreenPTimpossiblInceptronKenariMixlayerNEAR AI CloudOrcaRouterPioneerSnowflake CortexTencentThinking MachinesUmans Code (Umans AI)UpstageWafer超算互联网 (SCNet)Abacus.AIAI-ROUTERAmbientAnyAPIAurikoBergetBlue Claw NetworkClaudin.io (Claudinio)CloudFerro SherlockCrossModeld.runDInferenceFastRouterFreeModelFrogBotHPC-AI.COMJalapeno CloudJieKou AIKosmik ComputeLLM GatewayLLMTRLucidQueryLynkrMega NovaModalModelisOfoxAI (Ofox)PrivatemodeRadeon Cloud (AMD GPU Cloud)RegoloSTACKIT AI Model ServingSubconsciousSubModelThe GridTinfoil InferenceVultr Serverless InferenceXpersonaZeldoc.ai夸娥云Inference.netInfomaniakMerge GatewayNeon AI GatewayVivgrid
+ providers you addNot every provider checked yet
OpenAIAnthropicOpenRouterAzure OpenAIllama.cpp+ providers you add
OpenAIAnthropicGoogleOpenRouterOllamaSpaceXSI (Grok)DeepSeekAmazon Bedrock
+41 more model providers
LM StudioMoonshot AIGroqZ.aiMistralFireworksMiniMaxOpenCode GovLLMTogether AIHugging FaceAzure OpenAICerebrasllama.cppVercel AI GatewayOpenCode Console (OpenCode Zen)Alibaba (Qwen)XiaomiNVIDIAMeta AI (Llama)LiteLLM ProxyMicrosoft Foundry (Azure AI Foundry)Nebius Token Factory (Nebius AI Studio)Novita AIDeepInfraPerplexityGMI CloudStepFunKilo CodeArcee AICommand CodeSGLangTencentUpstageClawRouterJanLocalAINous PortalActual ComputerQwenCloudRamp Router
Models
OpenRouterGoogle GeminiDeepSeekGroqMistralOpenAIAnthropicAlibabaOllamaLM Studio
Not yet checked
Nous PortalOpenAI CodexAnthropicOpenRouterFireworks AINovitaAIAI GatewayGLMKimiMiniMaxxAIQwen Cloud
Source and activity
Source
Not yet checked
GitHub stars
Not yet checked
Most
Release days, last 90 days
Not yet checked
0
19
Release days per week
Not yet checked
None in 26 weeks
Latest release, any channel
Not yet checked
v0.3.1 6 Jun 2024
Index score
Score and rank
8 #153 Score 7.5; ranked on the unrounded score
8 #153 DeprecatedScore 7.5; ranked on the unrounded score
48 #14 Score 48.2; ranked on the unrounded score
Mindshare
81 Hacker News mention in the last 90 days
81 Hacker News mention in the last 90 days
4884 Hacker News mentions in the last 90 days
Adoption, not scored
Not yet checked
8954,952 stars, read 18 Nov 2026
100264,230 stars, read 18 Nov 2026
Votes
—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.
Rank history
First ranked 18 Nov 2026
First ranked 18 Nov 2026
First ranked 18 Nov 2026
Full page

Watch devx vs GPT Engineer vs Hermes Agent on YouTube

More comparisons

Build your own