Skip to content
ADE Index

Amp vs Muse Code vs Codex CLI vs Pi

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

This page compares the four CLI agents only. Amp has 2 other listings and Codex has 5 other listings, each with its own page.

How they differ

Price
Pick this if…

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

Same for all 4 (1): Systems: Terminal, macOS, Windows, Linux
  • Systems: Terminal, macOS, Windows, Linux · · ·

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

Dotted values open their quote.

What each can do

Select an answer to see the maker’s sentence, or what we searched.

Only 2 capabilities are checked for Amp so far, so there is little to compare yet. 21 capabilities are checked for at least two of these tools. 6 get different answers, among them Approval modes, Subagents, Plan mode and Notifications; 2 differ only in a limit. 11 others are checked for one tool only.

Differences only8

Showing 8 that differ. Hidden: 13 where the checked answers match and 11 checked for one tool only.

  • Yesthe maker documents it
  • With add-onAdd-onsomething the maker publishes that you install or run
  • No, per makerNothe maker says it does not
  • *its limit or add-on is named under the row
  • Emptynot yet checked

Different answers6

Approval modesNot yet checked: Amp, Muse Code
Not yet checked for Amp
Not yet checked for Muse Code
SubagentsNot yet checked: Amp, Muse Code
Not yet checked for Amp
Not yet checked for Muse Code
Not built in; Subagent example
Plan modeNot yet checked: Amp, Muse Code
Not yet checked for Amp
Not yet checked for Muse Code
Not built in; Plan Mode example
Read-only modeNot yet checked: Amp, Muse Code
Not yet checked for Amp
Not yet checked for Muse Code
Not built in; Plan Mode example
NotificationsNot yet checked: Amp, Muse Code
Not yet checked for Amp
Not yet checked for Muse Code
Maker's notify example
OS-level sandboxNot yet checked: Amp
Not yet checked for Amp
Linux/WSL2 needs bubblewrap
Gondolin micro-VM example

Differ only in a limit2

Remote controlNot yet checked: Muse Code, Pi
Not yet checked for Muse Code
To a running app server
Not yet checked for Pi
Image inputNot yet checked: Amp, Muse Code
Not yet checked for Amp
Not yet checked for Muse Code
Needs a compatible terminal
Not yet checked: , , ,

5 capabilities are not yet checked for any of these tools and are not shown. Each answer is about the CLI agent in its column. Something the maker publishes separately, such as an editor plugin or a GitHub Action, shows as “With add-on”, even when it has its own listing here. How capabilities are checked

About these tools

Amp

Muse Code

Codex CLI

Pi

How to read the Index score

At a glance

Index score out of 100

Amp36Muse Code39Codex CLI91Pi78

Mindshare HN mentions, 90 days

Amp26Muse Code36Codex CLI4,237Pi1,310

Adoption GitHub stars, not scored

AmpNo public repositoryMuse CodeNo public repositoryCodex CLI136kPi123k

Release days last 90 days

AmpNot yet checkedMuse CodeNot yet checkedCodex CLI32Pi19

Lowest monthly plan billed monthly, lower is cheaper

Amp$20/moMuse CodeNot yet checkedCodex CLI$20/monthPiNot yet checked

Platforms systems and surfaces

Amp6Muse Code4Codex CLI4Pi4

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
4 of 4
AmpAmp · CLI agent
Muse CodeMeta · CLI agent
Codex CLIOpenAI · CLI agent
PiEarendil Works · CLI agent
Interface
Amp app: thread list, an agent summary of a CLI fix, and a code diff pane
Codex CLI explaining a codebase, with an updated plan checklist
pi startup listing loaded context, skills and extensions, then reading docs and running bash
What it is
Agent and development environment for building from anywhere
Coding agent for the terminal and CI, built for Muse Spark
Coding agent from OpenAI that runs locally on your computer
Minimal, extensible agent harness that you can make your own
Category
CLI agentAmp family
CLI agent
CLI agentCodex family
CLI agent
Pricing
Starts at (billing shown)
Lowest monthly plan
Not yet checked
Not yet checked
Free tier
Yes
Not yet checked
Not yet checked
Plans
  • Individual (displayed tier)$20/mo
Not yet checked
Runs on
Android
Yes
Not yet checked
Not yet checked
Not yet checked
iOS
Yes
Not yet checked
Not yet checked
Not yet checked
Models and agents
Models
GPT-5.6Claude Fable 5.2
Muse EmberMuse SparkMuse WonderMuse Wonder Full
GPT-6.2 AstraGPT-6.2 SolGPT-6.1 TerraGPT-6.1 SolGPT-6 Luna
Not yet checked
Source and activity
Source
Not yet checked
Not yet checked
GitHub stars
No public repository
No public repository
Most
Release days, last 90 days
Not yet checked
Not yet checked
32Most
19
Release days per week
Not yet checked
Not yet checked
Latest release, any channel
Not yet checked
Not yet checked
v1.5.2 10 Nov 2026
Index score
Score and rank
36 #30 Score 35.8; ranked on the unrounded score
39 #28 Score 39.2; ranked on the unrounded score
91 #2 Score 90.7; ranked on the unrounded score
78 #4 Score 77.9; ranked on the unrounded score
Mindshare
3626 Hacker News mentions in the last 90 days
3936 Hacker News mentions in the last 90 days
914,237 Hacker News mentions in the last 90 days
781,310 Hacker News mentions in the last 90 days
Adoption, not scored
No public repository
No public repository
97135,675 stars, read 18 Nov 2026
96122,575 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.
—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
First ranked 18 Nov 2026
Full page

Watch Amp vs Muse Code vs Codex CLI vs Pi on YouTube

More comparisons

Build your own