Skip to content
ADE Index

Hermes Agent vs Codex CLI vs S1Code vs ZeroStack

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. 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 Hermes Agent, Codex CLI and ZeroStack, not yet for S1Code: Price (Hermes Agent: ; Codex CLI: ; ZeroStack: )

Checked for Codex CLI, S1Code and ZeroStack, not yet for Hermes Agent: Systems (Codex CLI: , , , ; S1Code: , , ; ZeroStack: , , , )

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 S1Code’s capabilities yet. 24 capabilities are checked for at least two of these tools. One gets a different answer: Editor integration; 5 differ only in a limit. 9 others are checked for one tool only.

Differences only6
  • 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
,,,,,,,,
+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
,,
Listing also names: TypeSafe AI
,,,,,,,,
+8 more model providers
,,,,,,,
+ providers you add
Listing also names: OpenCode Console (OpenCode Zen)
Local modelsNot yet checked: S1Code, ZeroStack
Not yet checked for S1Code
Not yet checked for ZeroStack
Custom OpenAI-compatible endpointNot yet checked: S1Code, ZeroStack
Not yet checked for S1Code
Not yet checked for ZeroStack
Token and cost usageNot yet checked: S1Code, ZeroStack
Not yet checked for S1Code
Not yet checked for ZeroStack

MCP, hooks, skills and subagents

MCP serversNot yet checked: S1Code, ZeroStack
local and remote
local and remote
Not yet checked for S1Code
Not yet checked for ZeroStack
HooksNot yet checked: S1Code, ZeroStack
Not yet checked for S1Code
Not yet checked for ZeroStack
SkillsNot yet checked: S1Code, ZeroStack
Not yet checked for S1Code
Not yet checked for ZeroStack
SubagentsNot yet checked: S1Code, ZeroStack
Not yet checked for S1Code
Not yet checked for ZeroStack
PluginsNot yet checked: S1Code, ZeroStack
Not yet checked for S1Code
Not yet checked for ZeroStack
Custom commandsNot yet checked: S1Code, ZeroStack
Not yet checked for S1Code
Not yet checked for ZeroStack

Editors, scripts and CI

Editor integrationNot yet checked: S1Code, ZeroStack
ACP editors
Codex editor extension
Not yet checked for S1Code
Not yet checked for ZeroStack
Headless modeNot yet checked: S1Code, ZeroStack
Not yet checked for S1Code
Not yet checked for ZeroStack
JSON outputNot yet checked: S1Code, ZeroStack
Not yet checked for S1Code
Not yet checked for ZeroStack
GitHub integrationNot yet checked: Hermes Agent, S1Code, ZeroStack
Not yet checked for Hermes Agent
Codex GitHub Action
Not yet checked for S1Code
Not yet checked for ZeroStack

Review, steer and undo

Plan modeNot yet checked: Hermes Agent, S1Code, ZeroStack
Not yet checked for Hermes Agent
Not yet checked for S1Code
Not yet checked for ZeroStack
Read-only modeNot yet checked: Hermes Agent, S1Code, ZeroStack
Not yet checked for Hermes Agent
Not yet checked for S1Code
Not yet checked for ZeroStack
Review diffsNot yet checked: S1Code, ZeroStack
Needs checkpoints on
Not yet checked for S1Code
Not yet checked for ZeroStack
Undo file editsNot yet checked: Codex CLI, S1Code, ZeroStack
Opt-in; local and SSH only
Not yet checked for Codex CLI
Not yet checked for S1Code
Not yet checked for ZeroStack

Parallel agents

Parallel sessionsNot yet checked: Codex CLI, S1Code, ZeroStack
Not yet checked for Codex CLI
Not yet checked for S1Code
Not yet checked for ZeroStack
Git worktreesNot yet checked: S1Code, ZeroStack
Local execution only
Not yet checked for S1Code
Not yet checked for ZeroStack

Context and memory

Project instruction filesNot yet checked: S1Code, ZeroStack
Not yet checked for S1Code
Not yet checked for ZeroStack
Memory across sessionsNot yet checked: S1Code, ZeroStack
Off by default; local memories
Not yet checked for S1Code
Not yet checked for ZeroStack
Resume a sessionNot yet checked: S1Code, ZeroStack
Not yet checked for S1Code
Not yet checked for ZeroStack
Browse past sessionsNot yet checked: S1Code, ZeroStack
Not yet checked for S1Code
Not yet checked for ZeroStack

Remote and mobile control

Remote controlNot yet checked: S1Code, ZeroStack
To a running app server
Not yet checked for S1Code
Not yet checked for ZeroStack
Steer from a phoneNot yet checked: Codex CLI, S1Code, ZeroStack
Unblocks Kanban workers
Not yet checked for Codex CLI
Not yet checked for S1Code
Not yet checked for ZeroStack
NotificationsNot yet checked: S1Code, ZeroStack
Not yet checked for S1Code
Not yet checked for ZeroStack

Sandbox, permissions and privacy

OS-level sandboxNot yet checked: Hermes Agent, S1Code, ZeroStack
Not yet checked for Hermes Agent
Linux/WSL2 needs bubblewrap
Not yet checked for S1Code
Not yet checked for ZeroStack
Approval modesNot yet checked: S1Code, ZeroStack
Not yet checked for S1Code
Not yet checked for ZeroStack
Runs in a containerNot yet checked: Codex CLI, S1Code, ZeroStack
Official Docker setup
Not yet checked for Codex CLI
Not yet checked for S1Code
Not yet checked for ZeroStack

Images, web and your computer

Image inputNot yet checked: S1Code, ZeroStack
Not yet checked for S1Code
Not yet checked for ZeroStack
Browser automationNot yet checked: Codex CLI, S1Code, ZeroStack
Not yet checked for Codex CLI
Not yet checked for S1Code
Not yet checked for ZeroStack
Voice inputNot yet checked: S1Code, ZeroStack
Only in builds with voice
Not yet checked for S1Code
Not yet checked for ZeroStack
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

Hermes Agent

Codex CLI

S1Code

ZeroStack

How to read the Index score

At a glance

Index score out of 100

Hermes Agent48Codex CLI91S1Code8ZeroStack8

Mindshare HN mentions, 90 days

Hermes Agent84Codex CLI4,237S1Code1ZeroStack1

Adoption GitHub stars, not scored

Hermes Agent264kCodex CLI136kS1CodeNot yet checkedZeroStack1.8k

Release days last 90 days

Hermes Agent19Codex CLI32S1CodeNot yet checkedZeroStack5

Lowest monthly plan billed monthly, lower is cheaper

Hermes AgentNot yet checkedCodex CLI$20/monthS1CodeNot yet checkedZeroStackNot yet checked

Platforms systems and surfaces

Hermes AgentNot yet checkedCodex CLI4S1Code3ZeroStack4

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
Hermes AgentCLI agent
Codex CLIOpenAI · CLI agent
S1CodePreviewCLI agent
ZeroStackGiuseppe Della Vedova · CLI agent
Interface
Codex CLI explaining a codebase, with an updated plan checklist
What it is
Terminal agent for writing, reviewing and running code in local projects
Coding agent from OpenAI that runs locally on your computer
Terminal coding agent with action inspection, diffs, approvals and verification
Lightweight coding agent written in Rust, optimized for memory footprint and performance
Category
CLI agent
CLI agentCodex family
CLI agentPreview
CLI agent
Pricing
Starts at (billing shown)
Not yet checked
Lowest monthly plan
Not yet checked
Not yet checked
Not yet checked
Free tier
Not yet checked
Not yet checked
Plans
Not yet checked
Runs on
Linux
Not yet checked
Yes
Yes
Yes
Terminal
Not yet checked
Yes
Yes
Yes
Windows
Not yet checked
Yes
Not yet checked
Yes
macOS
Not yet checked
Yes
Yes
Yes
Models and agents
Models
Not yet checked
GPT-6.2 AstraGPT-6.2 SolGPT-6.1 TerraGPT-6.1 SolGPT-6 Luna
Not yet checked
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
Most
Not yet checked
Release days, last 90 days
19
32Most
Not yet checked
5
Release days per week
Not yet checked
Latest release, any channel
Not yet checked
v1.8.6 11 Nov 2026
Index score
Score and rank
48 #14 Score 48.2; ranked on the unrounded score
91 #2 Score 90.7; ranked on the unrounded score
8 #153 PreviewScore 7.5; ranked on the unrounded score
8 #153 Score 7.5; ranked on the unrounded score
Mindshare
4884 Hacker News mentions in the last 90 days
914,237 Hacker News mentions in the last 90 days
81 Hacker News mention in the last 90 days
81 Hacker News mention in the last 90 days
Adoption, not scored
100264,230 stars, read 18 Nov 2026
97135,675 stars, read 18 Nov 2026
Not yet checked
611,759 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 Hermes Agent vs Codex CLI vs S1Code vs ZeroStack on YouTube

More comparisons

Build your own