Skip to content
ADE Index

ancient vs Antigravity CLI vs Claude Code CLI vs Codex CLI

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. Antigravity has 3 other listings, Claude Code has 4 other listings and Codex has 5 other listings, each with its own page.

How they differ

Systemsancient 0 · Antigravity CLI 3 · Claude Code CLI 3 · Codex CLI 3
Nothing the others do not have
, ,
, ,
, ,
Pick this if…

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

Checked for Antigravity CLI, Claude Code CLI and Codex CLI, not yet for ancient: Price (Antigravity CLI: ; Claude Code CLI: ; Codex CLI: )

Checked for Claude Code CLI and Codex CLI, not yet for ancient and Antigravity CLI: Bring your own key (Claude Code CLI: ; Codex CLI: )

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.

We have not checked ancient’s capabilities yet. 30 capabilities are checked for at least two of these tools. One gets a different answer: Editor integration; 11 differ only in a limit. 6 others are checked for one tool only.

Differences only12
  • Yesthe maker documents it
  • With add-onAdd-onsomething the maker publishes that you install or run
  • *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

Named model providersFrom the listing
,,,
,,,
Listing also names: Microsoft Foundry (Azure AI Foundry)
,,,
Listing also names: LM Studio
Local modelsNot yet checked: ancient, Antigravity CLI, Claude Code CLI
Not yet checked for ancient
Not yet checked for Antigravity CLI
Not yet checked for Claude Code CLI
Custom OpenAI-compatible endpointNot yet checked: ancient, Antigravity CLI, Claude Code CLI
Not yet checked for ancient
Not yet checked for Antigravity CLI
Not yet checked for Claude Code CLI
Token and cost usageNot yet checked: ancient
Not yet checked for ancient
Token view for API users

MCP, hooks, skills and subagents

MCP serversNot yet checked: ancient
Not yet checked for ancient
local and remote
local and remote
local and remote
HooksNot yet checked: ancient
Not yet checked for ancient
SkillsNot yet checked: ancient
Not yet checked for ancient
SubagentsNot yet checked: ancient
Not yet checked for ancient
Google AI Pro or Ultra plan
PluginsNot yet checked: ancient
Not yet checked for ancient
Custom commandsNot yet checked: ancient
Not yet checked for ancient

Editors, scripts and CI

Editor integrationNot yet checked: ancient
Not yet checked for ancient
ACP editors, through agy acp
VS Code extension or JetBrains plugin
Codex editor extension
Headless modeNot yet checked: ancient
Not yet checked for ancient
JSON outputNot yet checked: ancient
Not yet checked for ancient
GitHub integrationNot yet checked: ancient, Antigravity CLI
Not yet checked for ancient
Not yet checked for Antigravity CLI
Claude Code GitHub Action
Codex GitHub Action
Commit attribution controlNot yet checked: ancient, Antigravity CLI, Codex CLI
Not yet checked for ancient
Not yet checked for Antigravity CLI
Not yet checked for Codex CLI

Review, steer and undo

Plan modeNot yet checked: ancient
Not yet checked for ancient
Read-only modeNot yet checked: ancient, Antigravity CLI
Not yet checked for ancient
Not yet checked for Antigravity CLI
Through plan mode
Review diffsNot yet checked: ancient
Not yet checked for ancient
Undo file editsNot yet checked: ancient, Antigravity CLI, Codex CLI
Not yet checked for ancient
Not yet checked for Antigravity CLI
Not yet checked for Codex CLI

Parallel agents

Parallel sessionsNot yet checked: ancient, Codex CLI
Not yet checked for ancient
Not yet checked for Codex CLI
Git worktreesNot yet checked: ancient, Antigravity CLI
Not yet checked for ancient
Not yet checked for Antigravity CLI
Local execution only

Context and memory

Project instruction filesNot yet checked: ancient
Not yet checked for ancient
Memory across sessionsNot yet checked: ancient
Not yet checked for ancient
Off by default; local memories
Resume a sessionNot yet checked: ancient
Not yet checked for ancient
Browse past sessionsNot yet checked: ancient
Not yet checked for ancient

Remote and mobile control

Remote controlNot yet checked: ancient
Not yet checked for ancient
Same Google Account in the browser
Needs a Claude plan, not an API key
To a running app server
Steer from a phoneNot yet checked: ancient, Codex CLI
Not yet checked for ancient
Same Google Account on the phone
Needs a Claude plan, not an API key
Not yet checked for Codex CLI
NotificationsNot yet checked: ancient
Not yet checked for ancient
Off by default
Depends on the terminal

Sandbox, permissions and privacy

OS-level sandboxNot yet checked: ancient
Not yet checked for ancient
Opt-in; Windows 11 24H2+
Not on native Windows
Linux/WSL2 needs bubblewrap
Approval modesNot yet checked: ancient
Not yet checked for ancient
Auto mode depends on account
Telemetry opt-outNot yet checked: ancient, Antigravity CLI, Codex CLI
Not yet checked for ancient
Not yet checked for Antigravity CLI
Not yet checked for Codex CLI

Images, web and your computer

Image inputNot yet checked: ancient
Not yet checked for ancient
Fetch URLsNot yet checked: ancient, Codex CLI
Not yet checked for ancient
Not yet checked for Codex CLI
Browser automationNot yet checked: ancient, Codex CLI
Not yet checked for ancient
Chrome DevTools MCP; Chrome 144+
Claude in Chrome extension
Not yet checked for Codex CLI
Computer useNot yet checked: ancient, Antigravity CLI, Codex CLI
Not yet checked for ancient
Not yet checked for Antigravity CLI
macOS only; Pro, Max or Ultra plan
Not yet checked for Codex CLI
Voice inputNot yet checked: ancient
Not yet checked for ancient
Interactive TUI; not business accounts
Claude.ai sign-in; no cloud or SSH
Only in builds with voice
Not yet checked: , , ,

One capability is not yet checked for any of these tools and is 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

ancient

Antigravity CLI

Claude Code CLI

Codex CLI

How to read the Index score

At a glance

Index score out of 100

ancientNot enough data yetAntigravity CLI44Claude Code CLI92Codex CLI91

Mindshare HN mentions, 90 days

ancient0Antigravity CLI56Claude Code CLI4,602Codex CLI4,237

Adoption GitHub stars, not scored

ancient6Antigravity CLINo public repositoryClaude Code CLI156kCodex CLI136k

Release days last 90 days

ancient0Antigravity CLINot yet checkedClaude Code CLI57Codex CLI32

Lowest monthly plan billed monthly, lower is cheaper

ancientNot yet checkedAntigravity CLIStarting at $30 per seat/monthClaude Code CLI$20/moCodex CLI$20/month

Platforms systems and surfaces

ancient1Antigravity CLI4Claude Code CLI5Codex CLI4

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
ancientD-engahmed · CLI agent
Antigravity CLIGoogle · CLI agent
Claude Code CLIAnthropic · CLI agent
Codex CLIOpenAI · CLI agent
Interface
Terminal session listing file searches and reads while tests run
Codex CLI explaining a codebase, with an updated plan checklist
What it is
An AI-powered terminal coding assistant inspired by ClaudeCode CLI.
Terminal interface to Antigravity agents, with concurrent subagents
Terminal coding tool that executes routine tasks and handles git workflows
Coding agent from OpenAI that runs locally on your computer
Category
CLI agent
CLI agentAntigravity family
CLI agentClaude Code family
CLI agentCodex family
Pricing
Starts at (billing shown)
Not yet checked
Lowest monthly plan
Not yet checked
Free tier
Not yet checked
Not yet checked
Not yet checked
Plans
Not yet checked
Bring your own key
Not yet checked
Not yet checked
Yes
Yes
Runs on
Linux
Not yet checked
Yes
Yes
Yes
Terminal
Yes
Yes
Yes
Yes
Web
Not yet checked
Not yet checked
Yes
Not yet checked
Windows
Not yet checked
Yes
Yes
Yes
macOS
Not yet checked
Yes
Yes
Yes
Models and agents
Models
Not yet checked
Gemini 4 NeonGemini 4 CarbonGemini 4 ArgonGemini 4 HydrogenGemini 3.8 FlashClaude Sonnet 5.5Claude Opus 5.5
Not yet checked
GPT-6.2 AstraGPT-6.2 SolGPT-6.1 TerraGPT-6.1 SolGPT-6 Luna
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
0
Not yet checked
57Most
32
Release days per week
Not yet checked
Latest release, any channel
Not yet checked
Not yet checked
v2.1.327 17 Nov 2026
Index score
Score and rank
Not enough data yet
44 #19 Score 43.9; ranked on the unrounded score
92 #1 Score 91.6; ranked on the unrounded score
91 #2 Score 90.7; ranked on the unrounded score
Mindshare
00 Hacker News mentions in the last 90 days
4456 Hacker News mentions in the last 90 days
924,602 Hacker News mentions in the last 90 days
914,237 Hacker News mentions in the last 90 days
Adoption, not scored
166 stars, read 18 Nov 2026
No public repository
98156,056 stars, read 18 Nov 2026
97135,675 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
Not ranked
First ranked 18 Nov 2026
First ranked 18 Nov 2026
First ranked 18 Nov 2026
Full page

Watch ancient vs Antigravity CLI vs Claude Code CLI vs Codex CLI on YouTube

More comparisons

Build your own