Skip to content
ADE Index

Amp vs Claude Code CLI vs Kimi Code CLI

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

About these tools

Claude Code CLI

Terminal coding agent · Source

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
How to read the Index score

At a glance

Index score out of 100

Amp36Claude Code CLI92Kimi Code CLI30

Mindshare HN mentions, 90 days

Amp27Claude Code CLI4,658Kimi Code CLI15

Adoption GitHub stars, not scored

AmpNo public repositoryClaude Code CLI156kKimi Code CLI8.2k

Release days last 90 days

AmpNot yet verifiedClaude Code CLI57Kimi Code CLI26

Lowest monthly plan billed monthly, lower is cheaper

AmpNot yet verifiedClaude Code CLI$20/moKimi Code CLINot yet verified

Platforms listed surfaces

Amp6Claude Code CLI6Kimi Code CLI1

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

3 of 4
AmpAmp · CLI agent
Claude Code CLIAnthropic · CLI agent
Kimi Code CLIMoonshot AI · CLI agent
Interface
Amp app: thread list, an agent summary of a CLI fix, and a code diff pane
Terminal session listing file searches and reads while tests run
Kimi Code welcome box, a question, visible thinking and the start of the reply
What it is
Terminal coding agent
Terminal coding agent
Terminal coding agent
Category
CLI agentAmp family
CLI agentClaude Code family
CLI agentKimi Code family
Pricing
Starts at (billing shown)
Not yet verified
Lowest monthly plan
Not yet verified
Not yet verified
Free tier
Yes
Not yet verified
Not yet verified
Plans
Not yet verified
Bring your own key
Yes
Not yet verified
Not yet verified
Runs on
Android
Yes
Not yet verified
Not yet verified
JetBrains
Not yet verified
Yes
Not yet verified
Linux
Yes
Yes
Not yet verified
Terminal
Yes
Yes
Yes
Web
Not yet verified
Yes
Not yet verified
Windows
Yes
Yes
Not yet verified
iOS
Yes
Not yet verified
Not yet verified
macOS
Yes
Yes
Not yet verified
Models and agents
Model providers
OpenAIAnthropic
Anthropic
Kimi
Models
GPT-5.6Claude Fable 5.2
Not yet verified
Not yet verified
Drives these agents
Not yet verified
Not yet verified
Not yet verified
Source and activity
Source
Not yet verified
GitHub stars
No public repository
Most
Release days, last 90 days
Not yet verified
57Most
26
Release days per week
Not yet verified
Latest release, any channel
Not yet verified
v2.1.327 17 Nov 2026
Index score
Score and rank
36 #29 Score 36.2; ranked on the unrounded score
92 #1 Score 91.7; ranked on the unrounded score
30 #34 Score 30.1; ranked on the unrounded score
Mindshare
3627 Hacker News mentions in the last 90 days
924,658 Hacker News mentions in the last 90 days
3015 Hacker News mentions in the last 90 days
Adoption, not scored
No public repository
98156,056 stars, read 18 Nov 2026
748,246 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

More comparisons

Build your own