Skip to content
ADE Index

Crush vs Hermes Agent vs mini-SWE-agent

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

How they differ

Model providersCrush 42 · Hermes Agent 49 · mini-SWE-agent 10 · 7 in all
,,,,,,,,
+27 more model providers
,,,,,,,,,,,,,,,,,,,,,,,,,,
+ providers you addNot every provider checked yet
,,,,,,,,
+34 more model providers
,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
,,+ providers you add
Show 7 shared
,,,,,,
Pick this if…

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

Checked for Hermes Agent and mini-SWE-agent, not yet for Crush: Price (Hermes Agent: ; mini-SWE-agent: )

Checked for Crush, not yet for Hermes Agent and mini-SWE-agent: Editors and systems (, )

Same for all 3 (1): Bring your own key: Yes
  • 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

Hermes Agent

mini-SWE-agent

How to read the Index score

At a glance

Index score out of 100

Crush23Hermes Agent48mini-SWE-agent21

Mindshare HN mentions, 90 days

Crush7Hermes Agent84mini-SWE-agent6

Adoption GitHub stars, not scored

Crush29.1kHermes Agent264kmini-SWE-agent9.7k

Release days last 90 days

Crush16Hermes Agent19mini-SWE-agent0

Platforms listed surfaces

Crush2Hermes AgentNot yet checkedmini-SWE-agent1

Readers who say they use it

Already use any of these? Tick it. Several is fine.

Votes can only raise a score: up to 20% of it reflects votes, 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. A vote is a signed-in reader ticking “I use this”. Since votes joined the score on 18 Nov 2026, 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
Crushcharmbracelet · CLI agent
Hermes AgentCLI agent
mini-SWE-agentSWE-agent · CLI agent
Interface
Crush TUI viewing a Go file while thinking, with session sidebar showing model, cost and LSPs
mini-SWE-agent interface
What it is
Not yet checked
Terminal agent for writing, reviewing and running code in local projects
The 100 line AI agent that solves GitHub issues or helps you in your command line.
Category
CLI agent
CLI agent
CLI agent
Pricing
Starts at (billing shown)
Not yet checked
Lowest monthly plan
Not yet checked
Not yet checked
Not yet checked
Free tier
Not yet checked
Plans
Not yet checked
Bring your own key
Yes
Yes
Yes
Runs on
Android
Yes
Not yet checked
Not yet checked
Terminal
Yes
Not yet checked
Yes
Models and agents
Model providers
OpenAIAnthropicGoogleOpenRouterOllamaSpaceXSI (Grok)DeepSeekAmazon Bedrock
+34 more model providers
LM StudioMoonshot AIZ.aiGroqFireworksMiniMaxGitHub CopilotOpenCode GoHugging FaceVercel AI GatewayAzure OpenAICerebrasllama.cppOpenCode Console (OpenCode Zen)Alibaba (Qwen)BasetenLiteLLM ProxyNebius Token Factory (Nebius AI Studio)ScalewayChutesSyntheticVeniceAIHubMixCortecsio.netCharm HyperCoralBricksNeuralwatt CloudQiniu CloudPioneerAtlas CloudAvianPareto InferenceoMLX
+ providers you addNot every provider checked yetCrush reaches 36 of these only through its bundled Catwalk catalog ·
OpenAIAnthropicGoogleOpenRouterOllamaSpaceXSI (Grok)DeepSeekAmazon Bedrock
+41 more model providers
LM StudioMoonshot AIZ.aiGroqFireworksMistralMiniMaxOpenCode GoTogether AIvLLMHugging FaceVercel AI GatewayAzure OpenAICerebrasllama.cppOpenCode 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
OpenAIAnthropicGoogleOpenRouterOllamaDeepSeekvLLMLiteLLM Proxy
+2 more model providers
RequestyPrisma AIRS AI Gateway (Portkey)
+ providers you add
Models
Not yet checked
Nous PortalOpenAI CodexAnthropicOpenRouterFireworks AINovitaAIAI GatewayGLMKimiMiniMaxxAIQwen Cloud
AnthropicOpenAIOpenRouterPortkey
Drives these agents
Not yet checked
Not yet checked
Not yet checked
Source and activity
Source
GitHub stars
Most
Release days, last 90 days
16
19Most
0
Release days per week
Latest release, any channel
nightly 18 Nov 2026
v2.4.6 23 Jul 2026
Index score
Score and rank
23 #64 Score 22.6; ranked on the unrounded score
48 #14 Score 48.2; ranked on the unrounded score
21 #70 Score 21.1; ranked on the unrounded score
Mindshare
237 Hacker News mentions in the last 90 days
4884 Hacker News mentions in the last 90 days
216 Hacker News mentions in the last 90 days
Adoption, not scored
8429,112 stars, read 18 Nov 2026
100264,230 stars, read 18 Nov 2026
759,713 stars, read 18 Nov 2026
Rank history
First ranked 18 Nov 2026
First ranked 18 Nov 2026
First ranked 18 Nov 2026
Full page

Watch Crush vs Hermes Agent vs mini-SWE-agent on YouTube

More comparisons

Build your own