Skip to content
ADE Index

Hermes Agent vs Mercury CLI vs Codex CLI vs OpenCode

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 OpenCode, not yet for Mercury CLI: Price (Hermes Agent: ; Codex CLI: ; OpenCode: ), Bring your own key (Hermes Agent: ; Codex CLI: ; OpenCode: )

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

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 Mercury CLI’s capabilities yet. 29 capabilities are checked for at least two of these tools. One gets a different answer: Editor integration; 9 differ only in a limit. 5 others are checked for one tool only.

Differences only10
  • 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
,,,,,,,,
+28 more model providers
,,,,,,,,,,,,,,,,,,,,,,,,,,,
Listing also names 11 othersSpaceXSI (Grok), Amazon Bedrock, Moonshot AI, Vercel AI Gateway, Alibaba (Qwen), OpenCode Console (OpenCode Zen), Microsoft Foundry (Azure AI Foundry), Nebius Token Factory (Nebius AI Studio), Novita AI, Command Code, QwenCloud
,,,,,,,
Listing also names: Alibaba (Qwen)
,,,
Listing also names: LM Studio
,,,,,,,,
+2 more model providers
,
and others; list may be partial
Listing also names: SpaceXSI (Grok), GitHub Copilot
Local modelsNot yet checked: Mercury CLI
Not yet checked for Mercury CLI
Custom OpenAI-compatible endpointNot yet checked: Mercury CLI
Not yet checked for Mercury CLI
Token and cost usageNot yet checked: Mercury CLI
Not yet checked for Mercury CLI

MCP, hooks, skills and subagents

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

Editors, scripts and CI

Editor integrationNot yet checked: Mercury CLI
ACP editors
Not yet checked for Mercury CLI
Codex editor extension
ACP clients such as Zed
Headless modeNot yet checked: Mercury CLI
Not yet checked for Mercury CLI
JSON outputNot yet checked: Mercury CLI
Not yet checked for Mercury CLI
GitHub integrationNot yet checked: Hermes Agent, Mercury CLI, OpenCode
Not yet checked for Hermes Agent
Not yet checked for Mercury CLI
Codex GitHub Action
Not yet checked for OpenCode

Review, steer and undo

Plan modeNot yet checked: Hermes Agent, Mercury CLI
Not yet checked for Hermes Agent
Not yet checked for Mercury CLI
Read-only modeNot yet checked: Hermes Agent, Mercury CLI
Not yet checked for Hermes Agent
Not yet checked for Mercury CLI
Plan profile; shell still asks
Review diffsNot yet checked: Mercury CLI
Needs checkpoints on
Not yet checked for Mercury CLI
In ACP permission requests
Undo file editsNot yet checked: Mercury CLI, Codex CLI
Opt-in; local and SSH only
Not yet checked for Mercury CLI
Not yet checked for Codex CLI

Parallel agents

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

Context and memory

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

Remote and mobile control

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

Sandbox, permissions and privacy

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

Images, web and your computer

Image inputNot yet checked: Mercury CLI
Not yet checked for Mercury CLI
Needs an image-capable model
Fetch URLsNot yet checked: Hermes Agent, Mercury CLI, Codex CLI
Not yet checked for Hermes Agent
Not yet checked for Mercury CLI
Not yet checked for Codex CLI
Browser automationNot yet checked: Mercury CLI, Codex CLI, OpenCode
Not yet checked for Mercury CLI
Not yet checked for Codex CLI
Not yet checked for OpenCode
Voice inputNot yet checked: Mercury CLI, OpenCode
Not yet checked for Mercury CLI
Only in builds with voice
Not yet checked for OpenCode
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

Hermes Agent

Mercury CLI

Codex CLI

OpenCode

How to read the Index score

At a glance

Index score out of 100

Hermes Agent48Mercury CLINot enough data yetCodex CLI91OpenCode79

Mindshare HN mentions, 90 days

Hermes Agent84Mercury CLI0Codex CLI4,237OpenCode1,414

Adoption GitHub stars, not scored

Hermes Agent264kMercury CLI31Codex CLI136kOpenCode228k

Release days last 90 days

Hermes Agent19Mercury CLI10Codex CLI32OpenCode28

Lowest monthly plan billed monthly, lower is cheaper

Hermes AgentNot yet checkedMercury CLINot yet checkedCodex CLI$20/monthOpenCode$10/month

Platforms systems and surfaces

Hermes AgentNot yet checkedMercury CLI4Codex CLI4OpenCode3

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
Mercury CLIWhq02 · CLI agent
Codex CLIOpenAI · CLI agent
OpenCodeAnomaly · CLI agent
Interface
Codex CLI explaining a codebase, with an updated plan checklist
Terminal UI with an inline diff, passing bun tests and a context sidebar
What it is
Terminal agent for writing, reviewing and running code in local projects
Mercury CLI: multiple AI coding sessions in one terminal.
Coding agent from OpenAI that runs locally on your computer
Coding agent with switchable build and read-only plan agents
Category
CLI agent
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
Not yet checked
Yes
Yes
Runs on
Linux
Not yet checked
Yes
Yes
Not yet checked
Terminal
Not yet checked
Yes
Yes
Yes
Web
Not yet checked
Not yet checked
Not yet checked
Yes
Windows
Not yet checked
Yes
Yes
Yes
macOS
Not yet checked
Yes
Yes
Not yet checked
Models and agents
Models
Not yet checked
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
Not yet checked
Source and activity
Source
GitHub stars
Most
Release days, last 90 days
19
10
32Most
28
Release days per week
Latest release, any channel
v1.0.11 16 Nov 2026
v2.3.2 18 Nov 2026
Index score
Score and rank
48 #14 Score 48.2; ranked on the unrounded score
Not enough data yet
91 #2 Score 90.7; ranked on the unrounded score
79 #3 Score 78.8; ranked on the unrounded score
Mindshare
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
791,414 Hacker News mentions in the last 90 days
Adoption, not scored
100264,230 stars, read 18 Nov 2026
2831 stars, read 18 Nov 2026
97135,675 stars, read 18 Nov 2026
100227,631 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
Not ranked
First ranked 18 Nov 2026
First ranked 18 Nov 2026
Full page

Watch Hermes Agent vs Mercury CLI vs Codex CLI vs OpenCode on YouTube

More comparisons

Build your own