Skip to content
ADE Index

Gemini CLI vs Muse Code vs Codex CLI vs Prime Agent

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. Gemini CLI has 1 other listing and Codex has 5 other listings, each with its own page.

How they differ

Price
SystemsGemini CLI 3 · Muse Code 4 · Codex CLI 4 · Prime Agent 2 · 1 in all
,
, ,
, ,
Show 1 shared
Pick this if…

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

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 Muse Code so far, so there is little to compare yet. 24 capabilities are checked for at least two of these tools. 3 get different answers: OS-level sandbox, Editor integration and Review diffs; on 1 more a maker’s docs say nothing; 6 differ only in a limit. 8 others are checked for one tool only.

Differences only9
  • Yesthe maker documents it
  • With add-onAdd-onsomething the maker publishes that you install or run
  • No, per makerNothe maker says it does not
  • Not in the maker’s docsNot foundwe searched the maker’s docs and found nothing; not a “no”
  • *its limit or add-on is named under the row
  • Emptynot yet checked
  • From the listingthe listing’s own facts; not one of the capabilities we check

Models, keys and usage

Bring your own keyFrom the listing
Named model providersFrom the listing
Listing names: Meta AI (Llama)
,,,
Listing also names: LM Studio
,,,,,,,,
+6 more model providers
,,,,,
Listing also names 10 othersSpaceXSI (Grok), Amazon Bedrock, Moonshot AI, Vercel AI Gateway, GitHub Copilot, OpenCode Go, Hugging Face, OpenCode Console (OpenCode Zen), Cloudflare AI Gateway, Cloudflare Workers AI
Local modelsNot yet checked: Gemini CLI, Muse Code, Prime Agent
Not yet checked for Gemini CLI
Not yet checked for Muse Code
Not yet checked for Prime Agent
Custom OpenAI-compatible endpointNot yet checked: Gemini CLI, Muse Code, Prime Agent
Not yet checked for Gemini CLI
Not yet checked for Muse Code
Not yet checked for Prime Agent
Token and cost usageNot yet checked: Muse Code
Not yet checked for Muse Code

MCP, hooks, skills and subagents

MCP serversNot yet checked: Muse Code
local and remote
Not yet checked for Muse Code
local and remote
HooksNot yet checked: Muse Code
Not yet checked for Muse Code
Quality gates, autonomous mode
SkillsNot yet checked: Muse Code
Not yet checked for Muse Code
SubagentsNot yet checked: Muse Code
Not yet checked for Muse Code
PluginsNot yet checked: Muse Code
Not yet checked for Muse Code
Custom commandsNot yet checked: Muse Code, Prime Agent
Not yet checked for Muse Code
Not yet checked for Prime Agent

Editors, scripts and CI

Editor integrationNot yet checked: Muse Code
Gemini CLI Companion extension
Not yet checked for Muse Code
Codex editor extension
ACP editors such as Zed
Headless mode
JSON outputNot yet checked: Muse Code
Not yet checked for Muse Code
GitHub integrationNot yet checked: Gemini CLI, Muse Code, Prime Agent
Not yet checked for Gemini CLI
Not yet checked for Muse Code
Codex GitHub Action
Not yet checked for Prime Agent

Review, steer and undo

Plan modeNot yet checked: Muse Code, Prime Agent
Not yet checked for Muse Code
Not yet checked for Prime Agent
Read-only modeNot yet checked: Muse Code, Prime Agent
Not yet checked for Muse Code
Not yet checked for Prime Agent
Review diffsNot yet checked: Muse Code
Gemini CLI Companion extension
Not yet checked for Muse Code
Edits made through the edit skill
Undo file editsNot yet checked: Muse Code, Codex CLI, Prime Agent
Not yet checked for Muse Code
Not yet checked for Codex CLI
Not yet checked for Prime Agent

Parallel agents

Git worktreesNot yet checked: Muse Code, Prime Agent
Experimental; turn on first
Not yet checked for Muse Code
Local execution only
Not yet checked for Prime Agent

Context and memory

Project instruction filesNot yet checked: Muse Code
Not yet checked for Muse Code
For child agents started in a folder
Memory across sessionsNot yet checked: Muse Code, Prime Agent
Not yet checked for Muse Code
Off by default; local memories
Not yet checked for Prime Agent
Resume a sessionNot yet checked: Muse Code
Not yet checked for Muse Code
Browse past sessionsNot yet checked: Muse Code
Not yet checked for Muse Code

Remote and mobile control

Remote controlNot yet checked: Gemini CLI, Muse Code, Prime Agent
Not yet checked for Gemini CLI
Not yet checked for Muse Code
To a running app server
Not yet checked for Prime Agent
NotificationsNot yet checked: Muse Code, Prime Agent
Experimental; off by default
Not yet checked for Muse Code
Not yet checked for Prime Agent

Sandbox, permissions and privacy

OS-level sandbox
Opt-in; Seatbelt is macOS only
Linux/WSL2 needs bubblewrap
Approval modesNot yet checked: Muse Code, Prime Agent
Not yet checked for Muse Code
Not yet checked for Prime Agent
Runs in a containerNot yet checked: Muse Code, Codex CLI, Prime Agent
Opt-in Docker or Podman sandbox
Not yet checked for Muse Code
Not yet checked for Codex CLI
Not yet checked for Prime Agent
Telemetry opt-outNot yet checked: Gemini CLI, Muse Code, Codex CLI
Not yet checked for Gemini CLI
Not yet checked for Muse Code
Not yet checked for Codex CLI

Images, web and your computer

Image inputNot yet checked: Muse Code, Prime Agent
Not yet checked for Muse Code
Not yet checked for Prime Agent
Fetch URLsNot yet checked: Muse Code, Codex CLI, Prime Agent
Not yet checked for Muse Code
Not yet checked for Codex CLI
Not yet checked for Prime Agent
Voice inputNot yet checked: Gemini CLI, Muse Code
Not yet checked for Gemini CLI
Not yet checked for Muse Code
Only in builds with voice
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

Gemini CLI

Muse Code

Codex CLI

Prime Agent

How to read the Index score

At a glance

Index score out of 100

Gemini CLI44Muse Code39Codex CLI91Prime Agent29

Mindshare HN mentions, 90 days

Gemini CLI58Muse Code36Codex CLI4,237Prime Agent14

Adoption GitHub stars, not scored

Gemini CLI109kMuse CodeNo public repositoryCodex CLI136kPrime Agent22.8k

Release days last 90 days

Gemini CLI12Muse CodeNot yet checkedCodex CLI32Prime Agent15

Lowest monthly plan billed monthly, lower is cheaper

Gemini CLINot yet checkedMuse CodeNot yet checkedCodex CLI$20/monthPrime AgentNot yet checked

Platforms systems and surfaces

Gemini CLI3Muse Code4Codex CLI4Prime Agent2

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
Gemini CLIgoogle-gemini · CLI agent
Muse CodeMeta · CLI agent
Codex CLIOpenAI · CLI agent
Prime AgentPrime Intellect · CLI agent
Interface
Terminal session after an MCP tool call generated three image files
Codex CLI explaining a codebase, with an updated plan checklist
What it is
Open-source terminal agent for enterprise Gemini Code Assist workflows on Google Cloud
Coding agent for the terminal and CI, built for Muse Spark
Coding agent from OpenAI that runs locally on your computer
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
Category
CLI agentGemini CLI family
CLI agent
CLI agentCodex family
CLI agent
Pricing
Starts at (billing shown)
Lowest monthly plan
Not yet checked
Not yet checked
Not yet checked
Free tier
Not yet checked
Not yet checked
Not yet checked
Plans
Not yet checked
Not yet checked
Runs on
Linux
Yes
Yes
Yes
Not yet checked
Terminal
Yes
Yes
Yes
Yes
Windows
Not yet checked
Yes
Yes
Yes
macOS
Yes
Yes
Yes
Not yet checked
Models and agents
Models
Not yet checked
Muse EmberMuse SparkMuse WonderMuse Wonder Full
GPT-6.2 AstraGPT-6.2 SolGPT-6.1 TerraGPT-6.1 SolGPT-6 Luna
Not yet checked
Drives these agents
Not yet checked
Not yet checked
Not yet checked
Not yet checked
Source and activity
Source
Not yet checked
GitHub stars
No public repository
Most
Release days, last 90 days
12
Not yet checked
32Most
15
Release days per week
Not yet checked
Latest release, any channel
v0.68.0 10 Nov 2026
Not yet checked
v0.10.5 18 Nov 2026
Index score
Score and rank
44 #18 Score 44.3; 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
29 #39 Score 29.4; ranked on the unrounded score
Mindshare
4458 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
2914 Hacker News mentions in the last 90 days
Adoption, not scored
95108,907 stars, read 18 Nov 2026
No public repository
97135,675 stars, read 18 Nov 2026
8222,805 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 Gemini CLI vs Muse Code vs Codex CLI vs Prime Agent on YouTube

More comparisons

Build your own