Skip to content
ADE Index

Aider vs Felan Code vs OpenCode

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

How they differ

SystemsAider 1 · Felan Code 1 · OpenCode 2 · 1 in all
Nothing the others do not have
Nothing the others do not have
Show 1 shared
Pick this if…

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

Checked for Aider and OpenCode, not yet for Felan Code: Price (Aider: ; OpenCode: ), Bring your own key (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 Felan Code’s capabilities yet. 20 capabilities are checked for at least two of these tools. On 3 rows a maker’s docs say nothing; 10 differ only in a limit. 10 others are checked for one tool only.

Differences only10

Showing 10 that differ and 3 rows where a maker’s docs say nothing. Hidden: 7 where the checked answers match and 10 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: Felan Code
Not yet checked for Felan Code
local and remote
SubagentsNot yet checked: Felan Code
Not yet checked for Felan Code
Git worktreesNot yet checked: Felan Code
Not yet checked for Felan Code

Differ only in a limit10

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

7 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

Felan Code

OpenCode

How to read the Index score

At a glance

Index score out of 100

Aider42Felan Code8OpenCode79

Mindshare HN mentions, 90 days

Aider47Felan Code1OpenCode1,414

Adoption GitHub stars, not scored

Aider50.2kFelan CodeNot yet checkedOpenCode228k

Release days last 90 days

Aider0Felan CodeNot yet checkedOpenCode28

Lowest monthly plan billed monthly, lower is cheaper

AiderNot yet checkedFelan CodeNot yet checkedOpenCode$10/month

Platforms systems and surfaces

Aider1Felan Code1OpenCode3

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
Felan CodeCLI agent
OpenCodeAnomaly · CLI 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
Model-portable coding agent for verifiable software work
Coding agent with switchable build and read-only plan agents
Pricing
Starts at (billing shown)
Not yet checked
Lowest monthly plan
Not yet checked
Not yet checked
Free tier
Not yet checked
Plans
Not yet checked
Bring your own key
Yes
Not yet checked
Yes
Runs on
Web
Not yet checked
Not yet checked
Yes
Windows
Not yet checked
Not yet checked
Yes
Source and activity
Source
Not yet checked
GitHub stars
Not yet checked
Most
Release days, last 90 days
0
Not yet checked
28
Release days per week
Not yet checked
Latest release, any channel
v0.86.0 9 Aug 2025
Not yet checked
v2.3.2 18 Nov 2026
Index score
Score and rank
42 #22 Score 42.0; ranked on the unrounded score
8 #153 Score 7.5; ranked on the unrounded score
79 #3 Score 78.8; ranked on the unrounded score
Mindshare
4247 Hacker News mentions in the last 90 days
81 Hacker News mention in the last 90 days
791,414 Hacker News mentions in the last 90 days
Adoption, not scored
8950,162 stars, read 18 Nov 2026
Not yet checked
100227,631 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 Felan Code vs OpenCode on YouTube

More comparisons

Build your own