Skip to content
ADE Index

Hermes Agent vs Codex CLI vs plank

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. 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 and Codex CLI, not yet for plank: Price (Hermes Agent: ; Codex CLI: ), Bring your own key (Hermes Agent: ; Codex CLI: )

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

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 plank’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

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: Alibaba (Qwen)
Local modelsNot yet checked: plank
Not yet checked for plank
Custom OpenAI-compatible endpointNot yet checked: plank
Not yet checked for plank
Token and cost usageNot yet checked: plank
Not yet checked for plank

MCP, hooks, skills and subagents

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

Editors, scripts and CI

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

Review, steer and undo

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

Parallel agents

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

Context and memory

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

Remote and mobile control

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

Sandbox, permissions and privacy

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

Images, web and your computer

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

plank

How to read the Index score

At a glance

Index score out of 100

Hermes Agent48Codex CLI91plankNot enough data yet

Mindshare HN mentions, 90 days

Hermes Agent84Codex CLI4,237plank0

Adoption GitHub stars, not scored

Hermes Agent264kCodex CLI136kplank36

Release days last 90 days

Hermes Agent19Codex CLI32plank17

Lowest monthly plan billed monthly, lower is cheaper

Hermes AgentNot yet checkedCodex CLI$20/monthplankNot yet checked

Platforms systems and surfaces

Hermes AgentNot yet checkedCodex CLI4plank4

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
Hermes AgentCLI agent
Codex CLIOpenAI · CLI agent
plankaovestdipaperino · 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
Interactive terminal coding agent in Rust — runs the DeepSeek V4 Flash model locally on macOS (Metal), with a Ratatui TUI, a full tool suite, MCP, and persistent sessions.
Category
CLI agent
CLI agentCodex family
CLI agent
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
Yes
Yes
Not yet checked
Runs on
Linux
Not yet checked
Yes
Yes
Terminal
Not yet checked
Yes
Yes
Windows
Not yet checked
Yes
Yes
macOS
Not yet checked
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
Drives these agents
Not yet checked
Not yet checked
Not yet checked
Source and activity
Source
GitHub stars
Most
Release days, last 90 days
19
32Most
17
Release days per week
Latest release, any channel
v7.0.9 23 Oct 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
Not enough data yet
Mindshare
4884 Hacker News mentions in the last 90 days
914,237 Hacker News mentions in the last 90 days
00 Hacker News mentions in the last 90 days
Adoption, not scored
100264,230 stars, read 18 Nov 2026
97135,675 stars, read 18 Nov 2026
3036 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
Not ranked
Full page

Watch Hermes Agent vs Codex CLI vs plank on YouTube

More comparisons

Build your own