Skip to content
ADE Index

Agent Deck vs craig vs ZCode

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

About these tools

Agent Deck

Terminal session manager for Claude Code, Gemini, OpenCode and Codex · Source

craig

Orchestrator TUI with a branch, worktree and live terminal for each task · Source

The paneled terminal UI is enabled by default, including framed panes, integrated tabs, a compact workspace sidebar, and live summaries on the start and pause menus. No Panel polish preview toggle is required.

ZCode

Multi-agent coding workspace presented as the harness for GLM-5.3 · Source

How to read the Index score

At a glance

Index score out of 100

Agent Deck12craigNot enough data yetZCode39

Mindshare HN mentions, 90 days

Agent Deck2craig0ZCode36

Adoption GitHub stars, not scored

Agent Deck1.3kcraig8ZCodeNo public repository

Release days last 90 days

Agent Deck20craig5ZCodeNot yet verified

Lowest monthly plan billed monthly, lower is cheaper

Agent DeckNot yet verifiedcraigNot yet verifiedZCode$12.6/mo

Platforms listed surfaces

Agent Deck3craigNot yet verifiedZCode3

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

3 of 4
Agent DeckAshesh Goplani · Terminal & TUI
craighallsamuel90 · Terminal & TUI
ZCodeDesktop app
Interface
craig interface shown in the official README
ZCode interface
What it is
Terminal session manager for Claude Code, Gemini, OpenCode and Codex
Orchestrator TUI with a branch, worktree and live terminal for each task
Multi-agent coding workspace presented as the harness for GLM-5.3
Category
Agent workspace
Agent workspace
Agent workspace
What it does
Form
Terminal & TUI
Terminal & TUI
Desktop app
Parallel agents
Yes
Yes
Yes
Worktree isolation
Yes
Yes
Yes
Task board
Yes
Not established
Not established
Agent teams
Yes
Yes · preview
Not established
Review & diffs
Not established
Yes
Not established
Remote session control
Yes
Not established
Yes
Team collaboration
Not established
Not established
Not established
Agent & model switching
Yes
Yes
Yes
Pricing
Starts at (billing shown)
Not yet verified
Not yet verified
Lowest monthly plan
Not yet verified
Not yet verified
Free tier
Not yet verified
Not yet verified
Not yet verified
Plans
Not yet verified
Not yet verified
Bring your own key
Not yet verified
Not yet verified
Not yet verified
Runs on
Linux
Yes
Not yet verified
Yes
Windows
Yes
Not yet verified
Yes
macOS
Yes
Not yet verified
Yes
Models and agents
Model providers
Not yet verified
Not yet verified
Not yet verified
Models
Not yet verified
Not yet verified
20+ agent toolsGLM-5.3GLM-5.3-Flash
Drives these agents
Not yet verified
Not yet verified
Claude Code
Source and activity
Source
Not yet verified
GitHub stars
Most
No public repository
Release days, last 90 days
20Most
5
Not yet verified
Release days per week
Not yet verified
Latest release, any channel
v1.16.39 14 Nov 2026
craig-cli@0.21.0 9 Nov 2026
Not yet verified
Index score
Score and rank
12 #108 Score 11.9; ranked on the unrounded score
Not enough data yet
39 #28 Score 39.2; ranked on the unrounded score
Mindshare
122 Hacker News mentions in the last 90 days
00 Hacker News mentions in the last 90 days
3936 Hacker News mentions in the last 90 days
Adoption, not scored
591,274 stars, read 18 Nov 2026
188 stars, read 17 Nov 2026
No public repository
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
Not ranked
First ranked 18 Nov 2026
Full page

More comparisons

Build your own