Skip to content
ADE Index

Antigravity CLI vs Hermes Agent vs Kolega Code 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 and Codex has 5 other listings, each with its own page.

How they differ

Pick this if…

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

Checked for Antigravity CLI, Hermes Agent and Codex CLI, not yet for Kolega Code: Price (Antigravity CLI: ; Hermes Agent: ; Codex CLI: )

Checked for Hermes Agent and Codex CLI, not yet for Antigravity CLI and Kolega Code: Bring your own key (Hermes Agent: ; Codex CLI: )

Checked for Antigravity CLI, Kolega Code and Codex CLI, not yet for Hermes Agent: Systems (Antigravity CLI: , , ; Kolega Code: , ; 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 Kolega Code’s capabilities yet. 29 capabilities are checked for at least two of these tools. 2 get different answers: Editor integration and Browser automation; 10 differ only in a limit. 5 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
,,,,,,,,
+30 more model providers
,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
Listing also names 11 othersSpaceXSI (Grok), Amazon Bedrock, Moonshot AI, Vercel AI Gateway, OpenCode Console (OpenCode Zen), Alibaba (Qwen), Meta AI (Llama), Microsoft Foundry (Azure AI Foundry), Nebius Token Factory (Nebius AI Studio), Novita AI, Command Code
,,
,,,
Listing also names: LM Studio
Local modelsNot yet checked: Antigravity CLI, Kolega Code
Not yet checked for Antigravity CLI
Not yet checked for Kolega Code
Custom OpenAI-compatible endpointNot yet checked: Antigravity CLI, Kolega Code
Not yet checked for Antigravity CLI
Not yet checked for Kolega Code
Token and cost usageNot yet checked: Kolega Code
Not yet checked for Kolega Code

MCP, hooks, skills and subagents

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

Editors, scripts and CI

Editor integrationNot yet checked: Kolega Code
ACP editors, through agy acp
ACP editors
Not yet checked for Kolega Code
Codex editor extension
Headless modeNot yet checked: Kolega Code
Not yet checked for Kolega Code
JSON outputNot yet checked: Kolega Code
Not yet checked for Kolega Code
GitHub integrationNot yet checked: Antigravity CLI, Hermes Agent, Kolega Code
Not yet checked for Antigravity CLI
Not yet checked for Hermes Agent
Not yet checked for Kolega Code
Codex GitHub Action

Review, steer and undo

Plan modeNot yet checked: Hermes Agent, Kolega Code
Not yet checked for Hermes Agent
Not yet checked for Kolega Code
Read-only modeNot yet checked: Antigravity CLI, Hermes Agent, Kolega Code
Not yet checked for Antigravity CLI
Not yet checked for Hermes Agent
Not yet checked for Kolega Code
Review diffsNot yet checked: Kolega Code
Needs checkpoints on
Not yet checked for Kolega Code
Undo file editsNot yet checked: Antigravity CLI, Kolega Code, Codex CLI
Not yet checked for Antigravity CLI
Opt-in; local and SSH only
Not yet checked for Kolega Code
Not yet checked for Codex CLI

Parallel agents

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

Context and memory

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

Remote and mobile control

Remote controlNot yet checked: Kolega Code
Same Google Account in the browser
Not yet checked for Kolega Code
To a running app server
Steer from a phoneNot yet checked: Kolega Code, Codex CLI
Same Google Account on the phone
Unblocks Kanban workers
Not yet checked for Kolega Code
Not yet checked for Codex CLI
NotificationsNot yet checked: Kolega Code
Off by default
Not yet checked for Kolega Code

Sandbox, permissions and privacy

OS-level sandboxNot yet checked: Hermes Agent, Kolega Code
Opt-in; Windows 11 24H2+
Not yet checked for Hermes Agent
Not yet checked for Kolega Code
Linux/WSL2 needs bubblewrap
Approval modesNot yet checked: Kolega Code
Auto mode depends on account
Not yet checked for Kolega Code
Runs in a containerNot yet checked: Antigravity CLI, Kolega Code, Codex CLI
Not yet checked for Antigravity CLI
Official Docker setup
Not yet checked for Kolega Code
Not yet checked for Codex CLI

Images, web and your computer

Image inputNot yet checked: Kolega Code
Not yet checked for Kolega Code
Fetch URLsNot yet checked: Hermes Agent, Kolega Code, Codex CLI
Not yet checked for Hermes Agent
Not yet checked for Kolega Code
Not yet checked for Codex CLI
Browser automationNot yet checked: Kolega Code, Codex CLI
Chrome DevTools MCP; Chrome 144+
Not yet checked for Kolega Code
Not yet checked for Codex CLI
Voice inputNot yet checked: Kolega Code
Interactive TUI; not business accounts
Not yet checked for Kolega Code
Only in builds with voice
Not yet checked: , , ,

3 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

Antigravity CLI

Hermes Agent

Kolega Code

Codex CLI

How to read the Index score

At a glance

Index score out of 100

Antigravity CLI44Hermes Agent48Kolega CodeNot enough data yetCodex CLI91

Mindshare HN mentions, 90 days

Antigravity CLI56Hermes Agent84Kolega Code0Codex CLI4,237

Adoption GitHub stars, not scored

Antigravity CLINo public repositoryHermes Agent264kKolega Code22Codex CLI136k

Release days last 90 days

Antigravity CLINot yet checkedHermes Agent19Kolega Code25Codex CLI32

Lowest monthly plan billed monthly, lower is cheaper

Antigravity CLIStarting at $30 per seat/monthHermes AgentNot yet checkedKolega CodeNot yet checkedCodex CLI$20/month

Platforms systems and surfaces

Antigravity CLI4Hermes AgentNot yet checkedKolega Code2Codex 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
Antigravity CLIGoogle · CLI agent
Hermes AgentCLI agent
Kolega Codekolega-ai · CLI agent
Codex CLIOpenAI · CLI agent
Interface
Codex CLI explaining a codebase, with an updated plan checklist
What it is
Terminal interface to Antigravity agents, with concurrent subagents
Terminal agent for writing, reviewing and running code in local projects
Agentic coding in the terminal: the model writes its own multi-agent workflows (Gigacode).
Coding agent from OpenAI that runs locally on your computer
Category
CLI agentAntigravity family
CLI agent
CLI agent
CLI agentCodex family
Pricing
Starts at (billing shown)
Not yet checked
Lowest monthly plan
Not yet checked
Not yet checked
Free tier
Not yet checked
Not yet checked
Plans
Not yet checked
Bring your own key
Not yet checked
Yes
Not yet checked
Yes
Runs on
Linux
Yes
Not yet checked
Not yet checked
Yes
Terminal
Yes
Not yet checked
Yes
Yes
Windows
Yes
Not yet checked
Yes
Yes
macOS
Yes
Not yet checked
Not yet checked
Yes
Models and agents
Models
Gemini 4 NeonGemini 4 CarbonGemini 4 ArgonGemini 4 HydrogenGemini 3.8 FlashClaude Sonnet 5.5Claude Opus 5.5
Not yet checked
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
Not yet checked
19
25
32Most
Release days per week
Not yet checked
Latest release, any channel
Not yet checked
v0.53.0 18 Nov 2026
Index score
Score and rank
44 #19 Score 43.9; ranked on the unrounded score
48 #14 Score 48.2; ranked on the unrounded score
Not enough data yet
91 #2 Score 90.7; ranked on the unrounded score
Mindshare
4456 Hacker News mentions in the last 90 days
4884 Hacker News mentions in the last 90 days
00 Hacker News mentions in the last 90 days
914,237 Hacker News mentions in the last 90 days
Adoption, not scored
No public repository
100264,230 stars, read 18 Nov 2026
2622 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
First ranked 18 Nov 2026
First ranked 18 Nov 2026
Not ranked
First ranked 18 Nov 2026
Full page

Watch Antigravity CLI vs Hermes Agent vs Kolega Code vs Codex CLI on YouTube

More comparisons

Build your own