Skip to content
ADE Index

Claude Code CLI vs Hermes Agent vs OpenCode vs TokenCode

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. Claude Code has 4 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 Claude Code CLI, Hermes Agent and OpenCode, not yet for TokenCode: Price (Claude Code CLI: ; Hermes Agent: ; OpenCode: ), Model providers (Claude Code CLI: , , , Microsoft Foundry (Azure AI Foundry), ; 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, , , , , , , , , , ; OpenCode: , , , , , SpaceXSI (Grok), , , GitHub Copilot, , , ), Bring your own key (Claude Code CLI: ; Hermes Agent: ; OpenCode: )

Checked for Claude Code CLI and OpenCode, not yet for Hermes Agent and TokenCode: Systems (Claude Code 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 TokenCode’s capabilities yet. 32 capabilities are checked for at least two of these tools. 2 get different answers: Editor integration and Browser automation; 10 differ only in a limit. 5 others are checked for one tool only.

Differences only12
  • 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: Claude Code CLI, TokenCode
Not yet checked for Claude Code CLI
Not yet checked for TokenCode
Custom OpenAI-compatible endpointNot yet checked: Claude Code CLI, TokenCode
Not yet checked for Claude Code CLI
Not yet checked for TokenCode
Token and cost usageNot yet checked: TokenCode
Token view for API users
Not yet checked for TokenCode

MCP, hooks, skills and subagents

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

Editors, scripts and CI

Editor integrationNot yet checked: TokenCode
VS Code extension or JetBrains plugin
ACP editors
ACP clients such as Zed
Not yet checked for TokenCode
Headless modeNot yet checked: TokenCode
Not yet checked for TokenCode
JSON outputNot yet checked: TokenCode
Not yet checked for TokenCode
GitHub integrationNot yet checked: Hermes Agent, OpenCode, TokenCode
Claude Code GitHub Action
Not yet checked for Hermes Agent
Not yet checked for OpenCode
Not yet checked for TokenCode
Commit attribution controlNot yet checked: Hermes Agent, OpenCode, TokenCode
Not yet checked for Hermes Agent
Not yet checked for OpenCode
Not yet checked for TokenCode

Review, steer and undo

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

Parallel agents

Parallel sessionsNot yet checked: TokenCode
Not yet checked for TokenCode
Git worktreesNot yet checked: TokenCode
Not yet checked for TokenCode

Context and memory

Project instruction filesNot yet checked: TokenCode
Not yet checked for TokenCode
Memory across sessionsNot yet checked: OpenCode, TokenCode
Not yet checked for OpenCode
Not yet checked for TokenCode
Resume a sessionNot yet checked: TokenCode
Not yet checked for TokenCode
Browse past sessionsNot yet checked: TokenCode
Not yet checked for TokenCode

Remote and mobile control

Remote controlNot yet checked: OpenCode, TokenCode
Needs a Claude plan, not an API key
Not yet checked for OpenCode
Not yet checked for TokenCode
Steer from a phoneNot yet checked: OpenCode, TokenCode
Needs a Claude plan, not an API key
Unblocks Kanban workers
Not yet checked for OpenCode
Not yet checked for TokenCode
NotificationsNot yet checked: TokenCode
Depends on the terminal
Not yet checked for TokenCode

Sandbox, permissions and privacy

OS-level sandboxNot yet checked: Hermes Agent, OpenCode, TokenCode
Not on native Windows
Not yet checked for Hermes Agent
Not yet checked for OpenCode
Not yet checked for TokenCode
Approval modesNot yet checked: TokenCode
Not yet checked for TokenCode
Runs in a containerNot yet checked: Claude Code CLI, TokenCode
Not yet checked for Claude Code CLI
Official Docker setup
Official Docker image
Not yet checked for TokenCode
Telemetry opt-outNot yet checked: Hermes Agent, OpenCode, TokenCode
Not yet checked for Hermes Agent
Not yet checked for OpenCode
Not yet checked for TokenCode

Images, web and your computer

Image inputNot yet checked: TokenCode
Needs an image-capable model
Not yet checked for TokenCode
Fetch URLsNot yet checked: Hermes Agent, TokenCode
Not yet checked for Hermes Agent
Not yet checked for TokenCode
Browser automationNot yet checked: OpenCode, TokenCode
Claude in Chrome extension
Not yet checked for OpenCode
Not yet checked for TokenCode
Computer useNot yet checked: Hermes Agent, OpenCode, TokenCode
macOS only; Pro, Max or Ultra plan
Not yet checked for Hermes Agent
Not yet checked for OpenCode
Not yet checked for TokenCode
Voice inputNot yet checked: OpenCode, TokenCode
Claude.ai sign-in; no cloud or SSH
Not yet checked for OpenCode
Not yet checked for TokenCode
Not yet checked: , , ,

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

Claude Code CLI

Hermes Agent

OpenCode

TokenCode

How to read the Index score

At a glance

Index score out of 100

Claude Code CLI92Hermes Agent48OpenCode79TokenCodeNot enough data yet

Mindshare HN mentions, 90 days

Claude Code CLI4,602Hermes Agent84OpenCode1,414TokenCode0

Adoption GitHub stars, not scored

Claude Code CLI156kHermes Agent264kOpenCode228kTokenCode35

Release days last 90 days

Claude Code CLI57Hermes Agent19OpenCode28TokenCode0

Lowest monthly plan billed monthly, lower is cheaper

Claude Code CLI$20/moHermes AgentNot yet checkedOpenCode$10/monthTokenCodeNot yet checked

Platforms systems and surfaces

Claude Code CLI5Hermes AgentNot yet checkedOpenCode3TokenCodeNot 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
Claude Code CLIAnthropic · CLI agent
Hermes AgentCLI agent
OpenCodeAnomaly · CLI agent
TokenCodeyzfly · CLI agent
Interface
Terminal session listing file searches and reads while tests run
Terminal UI with an inline diff, passing bun tests and a context sidebar
What it is
Terminal coding tool that executes routine tasks and handles git workflows
Terminal agent for writing, reviewing and running code in local projects
Coding agent with switchable build and read-only plan agents
A Go terminal coding agent that races up to 1,000 agents in parallel and keeps the best.
Category
CLI agentClaude Code family
CLI agent
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
Yes
Not yet checked
Not yet checked
Not yet checked
Terminal
Yes
Not yet checked
Yes
Not yet checked
Web
Yes
Not yet checked
Yes
Not yet checked
Windows
Yes
Not yet checked
Yes
Not yet checked
macOS
Yes
Not yet checked
Not yet checked
Not yet checked
Models and agents
Model providers
AnthropicGoogleAmazon BedrockMicrosoft Foundry (Azure AI Foundry)Claude apps gateway+ providers you add
OpenAIAnthropicOpenRouterGoogleOllamaSpaceXSI (Grok)DeepSeekAmazon Bedrock
+41 more model providers
LM StudioMoonshot AIGroqZ.aiMistralFireworksMiniMaxOpenCode GoTogether AIvLLMAzure OpenAIHugging FaceVercel AI GatewayCerebrasOpenCode Console (OpenCode Zen)llama.cppAlibaba (Qwen)XiaomiNVIDIAMeta AI (Llama)LiteLLMMicrosoft Foundry (Azure AI Foundry)Nebius Token Factory (Nebius AI Studio)Novita AIPerplexityDeepInfraGMI CloudStepFunKilo CodeArcee AICommand CodeSGLangTencentUpstageLocalAIClawRouterJanNous PortalActual ComputerQwenCloudRamp Router
OpenAIAnthropicOpenRouterGoogleOllamaSpaceXSI (Grok)Amazon BedrockLM Studio
+4 more model providers
GitHub CopilotOpenCode GovLLMAzure
Not every provider checked yet
Not yet checked
Models
AnthropicAmazon BedrockMicrosoft FoundryGoogleClaude
Nous PortalOpenAI CodexAnthropicOpenRouterFireworks AINovitaAIAI GatewayGLMKimiMiniMaxxAIQwen Cloud
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
57Most
19
28
0
Release days per week
Latest release, any channel
v2.1.327 17 Nov 2026
v2.3.2 18 Nov 2026
Not yet checked
Index score
Score and rank
92 #1 Score 91.6; ranked on the unrounded score
48 #14 Score 48.2; ranked on the unrounded score
79 #3 Score 78.8; ranked on the unrounded score
Not enough data yet
Mindshare
924,602 Hacker News mentions in the last 90 days
4884 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
98156,056 stars, read 18 Nov 2026
100264,230 stars, read 18 Nov 2026
100227,631 stars, read 18 Nov 2026
2935 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 Claude Code CLI vs Hermes Agent vs OpenCode vs TokenCode on YouTube

More comparisons

Build your own