Skip to content
ADE Index

mini-SWE-agent vs Crush

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

How they differ

Model providersmini-SWE-agent 3 · Crush 2 · 1 in common
,
Show 1 shared
Pick this if…

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

Sourced for mini-SWE-agent, not yet for Crush: Price (· )

Sourced for Crush, not yet for mini-SWE-agent: Editors and systems (, )

Same for both (1): Bring your own key: Yes
  • Bring your own key: Yes ·

Neither tool has a sourced value yet for: agents it runs.

Dotted values open their quote. A capability not shown is not yet sourced; the tool may still have it.

About these tools

mini-SWE-agent

How to read the Index score

At a glance

Index score out of 100

mini-SWE-agent21Crush23

Mindshare HN mentions, 90 days

mini-SWE-agent6Crush7

Adoption GitHub stars, not scored

mini-SWE-agent9.7kCrush29.1k

Release days last 90 days

mini-SWE-agent0Crush16

Platforms listed surfaces

mini-SWE-agent1Crush2

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

2 of 4
mini-SWE-agentSWE-agent · CLI agent
Crushcharmbracelet · CLI agent
Interface
mini-SWE-agent interface
Crush TUI viewing a Go file while thinking, with session sidebar showing model, cost and LSPs
What it is
The 100 line AI agent that solves GitHub issues or helps you in your command line.
Not yet verified
Category
CLI agent
CLI agent
Pricing
Starts at (billing shown)
Not yet verified
Lowest monthly plan
Not yet verified
Not yet verified
Free tier
Not yet verified
Plans
  • Open-source softwareFree
Not yet verified
Bring your own key
Yes
Yes
Runs on
Android
Not yet verified
Yes
Terminal
Yes
Yes
Models and agents
Model providers
AnthropicOpenAIOpenRouter
GoogleOllamaOpenRouter
Models
AnthropicOpenAIOpenRouterPortkey
Not yet verified
Drives these agents
Not yet verified
Not yet verified
Source and activity
Source
GitHub stars
Most
Release days, last 90 days
0
16
Release days per week
Latest release, any channel
v2.4.6 23 Jul 2026
nightly 18 Nov 2026
Index score
Score and rank
21 #70 Score 21.1; ranked on the unrounded score
23 #64 Score 22.6; ranked on the unrounded score
Mindshare
216 Hacker News mentions in the last 90 days
237 Hacker News mentions in the last 90 days
Adoption, not scored
759,713 stars, read 18 Nov 2026
8429,112 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.
Rank history
First ranked 18 Nov 2026
First ranked 18 Nov 2026
Full page

Watch mini-SWE-agent vs Crush on YouTube

More comparisons

Build your own