Skip to content
ADE Index

AI DevKit vs dev-loop vs Perch vs Squadra

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

How they differ

Pick this if…

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

Sourced for AI DevKit and Perch, not yet for dev-loop and Squadra: Price (AI DevKit: ; Perch: )

Sourced for Squadra, not yet for AI DevKit, dev-loop and Perch: Editors and systems (, )

None of these tools has a sourced value yet for: model providers, bring your own key, agents it runs.

Dotted values open their quote. A capability not shown is not yet sourced; the tool may still have it.

About these tools

AI DevKit

dev-loop

Perch

Squadra

How to read the Index score

At a glance

Index score out of 100

AI DevKit17dev-loopNot enough data yetPerch12Squadra8

Mindshare HN mentions, 90 days

AI DevKit4dev-loop0Perch2Squadra1

Adoption GitHub stars, not scored

AI DevKit1.7kdev-loopNot yet verifiedPerch31Squadra1.3k

Release days last 90 days

AI DevKit0dev-loop29Perch18Squadra14

Platforms listed surfaces

AI DevKitNot yet verifieddev-loopNot yet verifiedPerchNot yet verifiedSquadra2

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

4 of 4
AI DevKitHoang Nguyen · Agent add-on
dev-loopAgent add-on
PerchAgent add-on
SquadraStefano 0x640x610x670x6f · Agent add-on
Interface
AI DevKit interface
Squadra interface
What it is
Local config, session console, memory and messaging for coding agents
Claude Code plugin for verified implementation loops and project knowledge
Mac companion for answering coding-agent prompts and returning to sessions
Coordinate coding agents through shared tasks, prechecks and independent review
Category
Agent add-on
Agent add-on
Agent add-on
Agent add-on
Pricing
Starts at (billing shown)
Not yet verified
Not yet verified
Not yet verified
Not yet verified
Lowest monthly plan
Not yet verified
Not yet verified
Not yet verified
Not yet verified
Free tier
Not yet verified
Yes
Plans
  • Open-source softwareFree
Not yet verified
  • Open-source softwareFree
Not yet verified
Bring your own key
Not yet verified
Not yet verified
Not yet verified
Not yet verified
Runs on
Windows
Not yet verified
Not yet verified
Not yet verified
Yes
macOS
Not yet verified
Not yet verified
Not yet verified
Yes
Models and agents
Model providers
Not yet verified
Not yet verified
Not yet verified
Not yet verified
Models
Not yet verified
Not yet verified
Not yet verified
Not yet verified
Drives these agents
Not yet verified
Not yet verified
Not yet verified
Not yet verified
Source and activity
Source
GitHub stars
Most
Not yet verified
Release days, last 90 days
0
29Most
18
14
Release days per week
Latest release, any channel
v0.5.0 15 Jan 2026
v1.34.11 12 Nov 2026
v0.5.6 16 Nov 2026
v3.15.1 9 Nov 2026
Index score
Score and rank
17 #81 Score 17.5; ranked on the unrounded score
Not enough data yet
12 #108 Score 11.9; ranked on the unrounded score
8 #155 Score 7.5; ranked on the unrounded score
Mindshare
174 Hacker News mentions in the last 90 days
00 Hacker News mentions in the last 90 days
122 Hacker News mentions in the last 90 days
81 Hacker News mention in the last 90 days
Adoption, not scored
611,669 stars, read 18 Nov 2026
Not yet verified
2831 stars, read 17 Nov 2026
591,282 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
Not ranked
First ranked 18 Nov 2026
First ranked 18 Nov 2026
Full page

Watch AI DevKit vs dev-loop vs Perch vs Squadra on YouTube

More comparisons

Build your own