Skip to content
ADE Index

Amp vs Hermes Agent 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 three 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.

Checked for Amp and Codex CLI, not yet for Hermes Agent: Systems (Amp: , , , ; 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.

Only 2 capabilities are checked for Amp so far, so there is little to compare yet. 25 capabilities are checked for at least two of these tools. One gets a different answer: Editor integration; 6 differ only in a limit. 8 others are checked for one tool only.

Differences only7
  • 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

Bring your own keyFrom the listing
Named model providersFrom the listing
,,,,,,,,
+5 more model providers
,,,,
+ providers you add
Listing also names: SpaceXSI (Grok), Meta AI (Llama)
,,,,,,,,
+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: Amp
Not yet checked for Amp
Custom OpenAI-compatible endpointNot yet checked: Amp
Not yet checked for Amp
Token and cost usageNot yet checked: Amp
Not yet checked for Amp

MCP, hooks, skills and subagents

MCP serversNot yet checked: Amp
Not yet checked for Amp
local and remote
local and remote
HooksNot yet checked: Amp
Not yet checked for Amp
SkillsNot yet checked: Amp
Not yet checked for Amp
SubagentsNot yet checked: Amp
Not yet checked for Amp
PluginsNot yet checked: Amp
Not yet checked for Amp
Custom commandsNot yet checked: Amp
Not yet checked for Amp

Editors, scripts and CI

Editor integrationNot yet checked: Amp
Not yet checked for Amp
ACP editors
Codex editor extension
Headless modeNot yet checked: Amp
Not yet checked for Amp
JSON outputNot yet checked: Amp
Not yet checked for Amp
GitHub integrationNot yet checked: Amp, Hermes Agent
Not yet checked for Amp
Not yet checked for Hermes Agent
Codex GitHub Action

Review, steer and undo

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

Parallel agents

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

Context and memory

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

Remote and mobile control

Remote control
To a running app server
Steer from a phoneNot yet checked: Codex CLI
Unblocks Kanban workers
Not yet checked for Codex CLI
NotificationsNot yet checked: Amp
Not yet checked for Amp

Sandbox, permissions and privacy

OS-level sandboxNot yet checked: Amp, Hermes Agent
Not yet checked for Amp
Not yet checked for Hermes Agent
Linux/WSL2 needs bubblewrap
Approval modesNot yet checked: Amp
Not yet checked for Amp
Runs in a containerNot yet checked: Amp, Codex CLI
Not yet checked for Amp
Official Docker setup
Not yet checked for Codex CLI

Images, web and your computer

Image inputNot yet checked: Amp
Not yet checked for Amp
Browser automationNot yet checked: Amp, Codex CLI
Not yet checked for Amp
Not yet checked for Codex CLI
Voice inputNot yet checked: Amp
Not yet checked for Amp
Only in builds with voice
Not yet checked: , ,

4 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

Hermes Agent

Codex CLI

How to read the Index score

At a glance

Index score out of 100

Amp36Hermes Agent48Codex CLI91

Mindshare HN mentions, 90 days

Amp26Hermes Agent84Codex CLI4,237

Adoption GitHub stars, not scored

AmpNo public repositoryHermes Agent264kCodex CLI136k

Release days last 90 days

AmpNot yet checkedHermes Agent19Codex CLI32

Lowest monthly plan billed monthly, lower is cheaper

Amp$20/moHermes AgentNot yet checkedCodex CLI$20/month

Platforms systems and surfaces

Amp6Hermes AgentNot yet checkedCodex 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
3 of 4
AmpAmp · CLI agent
Hermes AgentCLI agent
Codex CLIOpenAI · 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
What it is
Agent and development environment for building from anywhere
Terminal agent for writing, reviewing and running code in local projects
Coding agent from OpenAI that runs locally on your computer
Category
CLI agentAmp family
CLI agent
CLI agentCodex family
Pricing
Starts at (billing shown)
Lowest monthly plan
Not yet checked
Free tier
Yes
Not yet checked
Plans
  • Individual (displayed tier)$20/mo
Runs on
Android
Yes
Not yet checked
Not yet checked
Linux
Yes
Not yet checked
Yes
Terminal
Yes
Not yet checked
Yes
Windows
Yes
Not yet checked
Yes
iOS
Yes
Not yet checked
Not yet checked
macOS
Yes
Not yet checked
Yes
Models and agents
Models
GPT-5.6Claude Fable 5.2
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
Source and activity
Source
Not yet checked
GitHub stars
No public repository
Most
Release days, last 90 days
Not yet checked
19
32Most
Release days per week
Not yet checked
Latest release, any channel
Not yet checked
Index score
Score and rank
36 #30 Score 35.8; ranked on the unrounded score
48 #14 Score 48.2; ranked on the unrounded score
91 #2 Score 90.7; ranked on the unrounded score
Mindshare
3626 Hacker News mentions in the last 90 days
4884 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
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.
Rank history
First ranked 18 Nov 2026
First ranked 18 Nov 2026
First ranked 18 Nov 2026
Full page

Watch Amp vs Hermes Agent vs Codex CLI on YouTube

More comparisons

Build your own