Skip to content
ADE Index

Aider vs Hermes Agent vs OpenCode vs uji

Up to four tools, row by row. We do not guess: a cell we have not checked says so.

How they differ

Pick this if…

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

Checked for Aider, Hermes Agent and OpenCode, not yet for uji: Price (Aider: ; Hermes Agent: ; OpenCode: ), Bring your own key (Aider: ; Hermes Agent: ; OpenCode: )

Checked for Aider and OpenCode, not yet for Hermes Agent and uji: Systems (Aider: ; 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 uji’s capabilities yet. 28 capabilities are checked for at least two of these tools. On 3 rows a maker’s docs say nothing; 11 differ only in a limit. 6 others are checked for one tool only.

Differences only11

Showing 11 that differ and 3 rows where a maker’s docs say nothing. Hidden: 14 where the checked answers match and 6 checked for one tool only.

  • Yesthe maker documents it
  • 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

A maker’s docs say nothing3

MCP serversNot yet checked: uji
local and remote
local and remote
Not yet checked for uji
SubagentsNot yet checked: uji
Not yet checked for uji
Git worktreesNot yet checked: uji
Not yet checked for uji

Differ only in a limit11

HooksNot yet checked: uji
Lint/test commands after each edit
Not yet checked for uji
Editor integrationNot yet checked: uji
Terminal plus --watch-files
ACP editors
ACP clients such as Zed
Not yet checked for uji
Plan modeNot yet checked: Hermes Agent, uji
Ask mode, then code mode
Not yet checked for Hermes Agent
Not yet checked for uji
Read-only modeNot yet checked: Hermes Agent, uji
Not yet checked for Hermes Agent
Plan profile; shell still asks
Not yet checked for uji
Review diffsNot yet checked: uji
Needs checkpoints on
In ACP permission requests
Not yet checked for uji
Undo file editsNot yet checked: uji
Opt-in; local and SSH only
Not yet checked for uji
Project instruction filesNot yet checked: uji
A conventions file you configure
Not yet checked for uji
Resume a sessionNot yet checked: uji
Opt-in flag
Not yet checked for uji
NotificationsNot yet checked: uji
Off by default
Not yet checked for uji
Runs in a containerNot yet checked: uji
Official Docker images
Official Docker setup
Official Docker image
Not yet checked for uji
Image inputNot yet checked: uji
Needs an image-capable model
Not yet checked for uji
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

Aider

Hermes Agent

OpenCode

uji

How to read the Index score

At a glance

Index score out of 100

Aider42Hermes Agent48OpenCode79uji12

Mindshare HN mentions, 90 days

Aider47Hermes Agent84OpenCode1,414uji2

Adoption GitHub stars, not scored

Aider50.2kHermes Agent264kOpenCode228kujiNot yet checked

Release days last 90 days

Aider0Hermes Agent19OpenCode28ujiNot yet checked

Lowest monthly plan billed monthly, lower is cheaper

AiderNot yet checkedHermes AgentNot yet checkedOpenCode$10/monthujiNot yet checked

Platforms systems and surfaces

Aider1Hermes AgentNot yet checkedOpenCode3ujiNot 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
AiderAider AI · CLI agent
Hermes AgentCLI agent
OpenCodeAnomaly · CLI agent
ujiCLI agent
Interface
Terminal chat: a prompt, a search/replace edit block for hello.py, then an auto-commit
Terminal UI with an inline diff, passing bun tests and a context sidebar
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 with switchable build and read-only plan agents
Modular coding agent whose components can be swapped at runtime
Category
CLI agent
CLI agent
CLI agent
CLI agent
Pricing
Starts at (billing shown)
Not yet checked
Lowest monthly plan
Not yet checked
Not yet checked
Not yet checked
Free tier
Not yet checked
Plans
Not yet checked
Bring your own key
Yes
Yes
Yes
Not yet checked
Runs on
Terminal
Yes
Not yet checked
Yes
Not yet checked
Web
Not yet checked
Not yet checked
Yes
Not yet checked
Windows
Not yet checked
Not yet checked
Yes
Not yet checked
Source and activity
Source
Not yet checked
GitHub stars
Most
Not yet checked
Release days, last 90 days
0
19
28Most
Not yet checked
Release days per week
None in 26 weeks
Not yet checked
Latest release, any channel
v0.86.0 9 Aug 2025
v2.3.2 18 Nov 2026
Not yet checked
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
79 #3 Score 78.8; ranked on the unrounded score
12 #107 Score 11.9; ranked on the unrounded score
Mindshare
4247 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
122 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
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
First ranked 18 Nov 2026
Full page

Watch Aider vs Hermes Agent vs OpenCode vs uji on YouTube

More comparisons

Build your own