Skip to content
ADE Index

Aider vs Hermes Agent vs Codex CLI

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

Price
Pick this if…

Paraphrased from each maker’s own description. Select a line for the quote.

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

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.

28 capabilities are checked for at least two of these tools. One gets a different answer: Editor integration; on 3 more a maker’s docs say nothing; 11 differ only in a limit. 8 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
  • Not in the maker’s docsNot foundwe searched the maker’s docs and found nothing; not a “no”
  • *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

Bring your own keyFrom the listing
Named model providersFrom the listing
,,,,,,,,
+3 more model providers
,,
Not every provider checked yet
Listing also names: Google, SpaceXSI (Grok)
,,,,,,,,
+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
Local models
Custom OpenAI-compatible endpoint
Token and cost usage

MCP, hooks, skills and subagents

MCP servers
local and remote
local and remote
Hooks
Lint/test commands after each edit
SkillsNot yet checked: Aider
Not yet checked for Aider
Subagents
PluginsNot yet checked: Aider
Not yet checked for Aider
Custom commands

Editors, scripts and CI

Editor integration
Terminal plus --watch-files
ACP editors
Codex editor extension
Headless mode
JSON outputNot yet checked: Aider
Not yet checked for Aider
GitHub integrationNot yet checked: Aider, Hermes Agent
Not yet checked for Aider
Not yet checked for Hermes Agent
Codex GitHub Action
Commit attribution controlNot yet checked: Hermes Agent, Codex CLI
Not yet checked for Hermes Agent
Not yet checked for Codex CLI

Review, steer and undo

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

Parallel agents

Parallel sessionsNot yet checked: Aider, Codex CLI
Not yet checked for Aider
Not yet checked for Codex CLI
Git worktrees
Local execution only

Context and memory

Project instruction files
A conventions file you configure
Memory across sessionsNot yet checked: Aider
Not yet checked for Aider
Off by default; local memories
Resume a session
Opt-in flag
Browse past sessionsNot yet checked: Aider
Not yet checked for Aider

Remote and mobile control

Remote controlNot yet checked: Aider
Not yet checked for Aider
To a running app server
Steer from a phoneNot yet checked: Aider, Codex CLI
Not yet checked for Aider
Unblocks Kanban workers
Not yet checked for Codex CLI
Notifications
Off by default

Sandbox, permissions and privacy

OS-level sandboxNot yet checked: Aider, Hermes Agent
Not yet checked for Aider
Not yet checked for Hermes Agent
Linux/WSL2 needs bubblewrap
Approval modesNot yet checked: Aider
Not yet checked for Aider
Runs in a containerNot yet checked: Codex CLI
Official Docker images
Official Docker setup
Not yet checked for Codex CLI
Telemetry opt-outNot yet checked: Hermes Agent, Codex CLI
With --analytics-disable
Not yet checked for Hermes Agent
Not yet checked for Codex CLI

Images, web and your computer

Image input
Fetch URLsNot yet checked: Hermes Agent, Codex CLI
Not yet checked for Hermes Agent
Not yet checked for Codex CLI
Browser automationNot yet checked: Aider, Codex CLI
Not yet checked for Aider
Not yet checked for Codex CLI
Voice input
Only in builds with voice
Not yet checked: , ,

One capability is not yet checked for any of these tools and is 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

Aider

Hermes Agent

Codex CLI

How to read the Index score

At a glance

Index score out of 100

Aider42Hermes Agent48Codex CLI91

Mindshare HN mentions, 90 days

Aider47Hermes Agent84Codex CLI4,237

Adoption GitHub stars, not scored

Aider50.2kHermes Agent264kCodex CLI136k

Release days last 90 days

Aider0Hermes Agent19Codex CLI32

Lowest monthly plan billed monthly, lower is cheaper

AiderNot yet checkedHermes AgentNot yet checkedCodex CLI$20/month

Platforms systems and surfaces

Aider1Hermes AgentNot yet checkedCodex CLI4

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
AiderAider AI · CLI agent
Hermes AgentCLI agent
Codex CLIOpenAI · CLI agent
Interface
Terminal chat: a prompt, a search/replace edit block for hello.py, then an auto-commit
Codex CLI explaining a codebase, with an updated plan checklist
What it is
Pair program with LLMs to start a new project or build on your existing codebase
Terminal agent for writing, reviewing and running code in local projects
Coding agent from OpenAI that runs locally on your computer
Category
CLI agent
CLI agent
CLI agentCodex family
Pricing
Starts at (billing shown)
Lowest monthly plan
Not yet checked
Not yet checked
Free tier
Not yet checked
Plans
Runs on
Linux
Not yet checked
Not yet checked
Yes
Terminal
Yes
Not yet checked
Yes
Windows
Not yet checked
Not yet checked
Yes
macOS
Not yet checked
Not yet checked
Yes
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
Drives these agents
Not yet checked
Not yet checked
Not yet checked
Source and activity
Source
GitHub stars
Most
Release days, last 90 days
0
19
32Most
Release days per week
None in 26 weeks
Latest release, any channel
v0.86.0 9 Aug 2025
Index score
Score and rank
42 #22 Score 42.0; ranked on the unrounded score
48 #14 Score 48.2; ranked on the unrounded score
91 #2 Score 90.7; ranked on the unrounded score
Mindshare
4247 Hacker News mentions in the last 90 days
4884 Hacker News mentions in the last 90 days
914,237 Hacker News mentions in the last 90 days
Adoption, not scored
8950,162 stars, read 18 Nov 2026
100264,230 stars, read 18 Nov 2026
97135,675 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
First ranked 18 Nov 2026
Full page

Watch Aider vs Hermes Agent vs Codex CLI on YouTube

More comparisons

Build your own