Skip to content
ADE Index

Hermes Agent vs Codex CLI vs OpenCode vs San

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 San: Price (Hermes Agent: ; Codex CLI: ; OpenCode: ), Model providers (Hermes Agent: , , , , , , SpaceXSI (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, , , , , , , , , , , ; Codex CLI: , , , , LM Studio; OpenCode: , , , , , SpaceXSI (Grok), , , GitHub Copilot, , , ), Bring your own key (Hermes Agent: ; Codex CLI: ; OpenCode: )

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

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 San’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: San
Not yet checked for San
Custom OpenAI-compatible endpointNot yet checked: San
Not yet checked for San
Token and cost usageNot yet checked: San
Not yet checked for San

MCP, hooks, skills and subagents

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

Editors, scripts and CI

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

Review, steer and undo

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

Parallel agents

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

Context and memory

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

Remote and mobile control

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

Sandbox, permissions and privacy

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

Images, web and your computer

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

San

How to read the Index score

At a glance

Index score out of 100

Hermes Agent48Codex CLI91OpenCode79SanNot enough data yet

Mindshare HN mentions, 90 days

Hermes Agent84Codex CLI4,237OpenCode1,414San0

Adoption GitHub stars, not scored

Hermes Agent264kCodex CLI136kOpenCode228kSan149

Release days last 90 days

Hermes Agent19Codex CLI32OpenCode28San15

Lowest monthly plan billed monthly, lower is cheaper

Hermes AgentNot yet checkedCodex CLI$20/monthOpenCode$10/monthSanNot yet checked

Platforms systems and surfaces

Hermes AgentNot yet checkedCodex CLI4OpenCode3SanNot yet checked

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
Sangenai-io · 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
Coding agent from OpenAI that runs locally on your computer
Coding agent with switchable build and read-only plan agents
Open-source terminal agent runtime.
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
Not yet checked
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
AnthropicOpenAIGoogleOpenRouterOllamaDeepSeekSpaceXSI (Grok)Amazon Bedrock
+41 more model providers
GroqLM StudioMoonshot AIMistralZ.aiFireworksMiniMaxAzure OpenAIOpenCode GoTogether AIHugging FaceVercel AI GatewayvLLMCerebrasOpenCode Console (OpenCode Zen)Alibaba (Qwen)llama.cppNVIDIAXiaomiMeta AI (Llama)LiteLLMMicrosoft Foundry (Azure AI Foundry)Nebius Token Factory (Nebius AI Studio)Novita AIDeepInfraPerplexityStepFunGMI CloudKilo CodeCommand CodeTencentSGLangLocalAIUpstageArcee AIClawRouterNous PortalQwenCloudActual ComputerJanRamp Router
OpenAIGoogleOllamaAmazon BedrockLM Studio
AnthropicOpenAIGoogleOpenRouterOllamaSpaceXSI (Grok)Amazon BedrockLM Studio
+4 more model providers
GitHub CopilotOpenCode GovLLMAzure
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
Release days, last 90 days
19
32Most
28
15
Release days per week
Latest release, any channel
v2.3.2 18 Nov 2026
v1.25.4 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
41149 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
Not ranked
Full page

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

More comparisons

Build your own