Skip to content
ADE Index

Hermes Agent vs Codex CLI vs OpenCode vs par-code

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 par-code: Price (Hermes Agent: ; Codex CLI: ; OpenCode: ), Model providers (Hermes Agent: , , , , , , SpaceXSI (Grok), Moonshot AI, Amazon Bedrock, , , , , , Alibaba (Qwen), , , Vercel AI Gateway, OpenCode Console (OpenCode Zen), , , , , Microsoft Foundry (Azure AI Foundry), , , , , , , , Novita AI, , Command Code, , , , , QwenCloud, , , , , , Nebius Token Factory (Nebius AI Studio), , ; Codex CLI: , , , , LM Studio; OpenCode: , , , , , SpaceXSI (Grok), , , , GitHub Copilot, , ), Bring your own key (Hermes Agent: ; Codex CLI: ; OpenCode: )

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

Not yet checked for any of these tools: agents it runs.

Provider names use the same listing as each tool page. 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 par-code’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

Models, keys and usage

Local modelsNot yet checked: par-code
Not yet checked for par-code
Custom OpenAI-compatible endpointNot yet checked: par-code
Not yet checked for par-code
Token and cost usageNot yet checked: par-code
Not yet checked for par-code

MCP, hooks, skills and subagents

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

Editors, scripts and CI

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

Review, steer and undo

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

Parallel agents

Parallel sessionsNot yet checked: Codex CLI, par-code
Not yet checked for Codex CLI
Not yet checked for par-code
Git worktreesNot yet checked: par-code
Local execution only
Not yet checked for par-code

Context and memory

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

Remote and mobile control

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

Sandbox, permissions and privacy

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

Images, web and your computer

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

Codex CLI

OpenCode

par-code

How to read the Index score

At a glance

Index score out of 100

Hermes Agent48Codex CLI91OpenCode79par-codeNot enough data yet

Mindshare HN mentions, 90 days

Hermes Agent84Codex CLI4,237OpenCode1,414par-code0

Adoption GitHub stars, not scored

Hermes Agent264kCodex CLI136kOpenCode228kpar-codeNot yet checked

Release days last 90 days

Hermes Agent19Codex CLI32OpenCode28par-code7

Lowest monthly plan billed monthly, lower is cheaper

Hermes AgentNot yet checkedCodex CLI$20/monthOpenCode$10/monthpar-codeNot yet checked

Platforms listed surfaces

Hermes AgentNot yet checkedCodex CLI4OpenCode3par-code1

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
OpenCodeAnomaly · CLI agent
par-codeCLI 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
Coding agent from OpenAI that runs locally on your computer
Coding agent with switchable build and read-only plan agents
OCaml terminal coding agent with project memory and plan modes
Category
CLI agent
CLI agentCodex family
CLI agent
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
Yes
Not yet checked
Runs on
Linux
Not yet checked
Yes
Not yet checked
Not yet checked
Terminal
Not yet checked
Yes
Yes
Yes
Web
Not yet checked
Not yet checked
Yes
Not yet checked
Windows
Not yet checked
Yes
Yes
Not yet checked
macOS
Not yet checked
Yes
Not yet checked
Not yet checked
Models and agents
Model providers
AnthropicOpenAIGoogleOllamaOpenRouterDeepSeekSpaceXSI (Grok)Moonshot AI
+39 more model providers
Amazon BedrockLM StudioZ.aiMistralGroqMiniMaxAlibaba (Qwen)FireworksOpenCode GoVercel AI GatewayOpenCode Console (OpenCode Zen)Together AIAzure OpenAILiteLLMllama.cppMicrosoft Foundry (Azure AI Foundry)CerebrasHugging FaceNVIDIAvLLMXiaomiStepFunDeepInfraNovita AITencentCommand CodeGMI CloudKilo CodeLocalAIPerplexityQwenCloudSGLangActual ComputerArcee AIClawRouterJanNebius Token Factory (Nebius AI Studio)Nous PortalRamp Router
OpenAIGoogleOllamaAmazon BedrockLM Studio
AnthropicOpenAIGoogleOllamaOpenRouterSpaceXSI (Grok)Amazon BedrockLM Studio
+4 more model providers
OpenCode GoGitHub CopilotvLLMAzure
and others; list may be partial
Not yet checked
Models
Nous PortalOpenAI CodexAnthropicOpenRouterFireworks AINovitaAIAI GatewayGLMKimiMiniMaxxAIQwen Cloud
OpenAIGPT-6.2 AstraGPT-6.2 SolGPT-6.1 TerraGPT-6.1 SolGPT-6 Luna
OpenAIAmazon BedrockGoogleOllama
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
Not yet checked
Release days, last 90 days
19
32Most
28
7
Release days per week
Latest release, any channel
v2.3.2 18 Nov 2026
v0.15.2 18 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
79 #3 Score 78.8; 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
791,414 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
100227,631 stars, read 18 Nov 2026
Not yet checked
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
Not ranked
Full page

Watch Hermes Agent vs Codex CLI vs OpenCode vs par-code on YouTube

More comparisons

Build your own