Skip to content
ADE Index

caudra vs Claude Code CLI vs Gemini CLI vs Pi

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

This page compares the four CLI agents only. Claude Code has 4 other listings and Gemini CLI has 1 other listing, each with its own page.

How they differ

caudra is a fork of Maki: Caudra is an independent fork of Maki. raw.githubusercontent.com

Price
Systemscaudra 4 · Claude Code CLI 4 · Gemini CLI 3 · Pi 4 · 3 in all
Nothing the others do not have
Show 3 shared
, ,
Pick this if…

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

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 caudra’s capabilities yet. 27 capabilities are checked for at least two of these tools. 8 get different answers, among them Approval modes, Subagents, Plan mode and Review diffs; 4 differ only in a limit. 10 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
  • No, per makerNothe maker says it does not
  • *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
,,,,,,,,
+62 more model providers
,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
and others; list may be partial
Listing also names 14 othersSpaceXSI (Grok), LM Studio, OpenCode Console (OpenCode Zen), Alibaba (Qwen), Nebius Token Factory (Nebius AI Studio), TypeSafe AI, Kilo Code, Command Code, CoreWeave (Weights & Biases), FriendliAI, Meituan, Neuralwatt Cloud, Qiniu Cloud, OCI Enterprise AI (OCI Generative AI)
,,,
Listing also names: Microsoft Foundry (Azure AI Foundry)
,,,,,,,,
+17 more model providers
,,,,,,,,,,,,,,,,
and others; list may be partial
Listing also names 5 othersSpaceXSI (Grok), Z.ai, OpenCode Console (OpenCode Zen), Meta AI (Llama), Microsoft Foundry (Azure AI Foundry)
Local modelsNot yet checked: caudra, Claude Code CLI, Gemini CLI
Not yet checked for caudra
Not yet checked for Claude Code CLI
Not yet checked for Gemini CLI
Custom OpenAI-compatible endpointNot yet checked: caudra, Claude Code CLI, Gemini CLI
Not yet checked for caudra
Not yet checked for Claude Code CLI
Not yet checked for Gemini CLI
Token and cost usageNot yet checked: caudra
Not yet checked for caudra
Token view for API users

MCP, hooks, skills and subagents

MCP serversNot yet checked: caudra
Not yet checked for caudra
local and remote
local and remote
local and remote
HooksNot yet checked: caudra
Not yet checked for caudra
SkillsNot yet checked: caudra
Not yet checked for caudra
SubagentsNot yet checked: caudra
Not yet checked for caudra
Not built in; Subagent example
PluginsNot yet checked: caudra
Not yet checked for caudra
Custom commandsNot yet checked: caudra
Not yet checked for caudra

Editors, scripts and CI

Editor integrationNot yet checked: caudra, Pi
Not yet checked for caudra
VS Code extension or JetBrains plugin
Gemini CLI Companion extension
Not yet checked for Pi
Headless modeNot yet checked: caudra
Not yet checked for caudra
JSON outputNot yet checked: caudra
Not yet checked for caudra
GitHub integrationNot yet checked: caudra, Gemini CLI, Pi
Not yet checked for caudra
Claude Code GitHub Action
Not yet checked for Gemini CLI
Not yet checked for Pi
Commit attribution controlNot yet checked: caudra, Gemini CLI, Pi
Not yet checked for caudra
Not yet checked for Gemini CLI
Not yet checked for Pi

Review, steer and undo

Plan modeNot yet checked: caudra
Not yet checked for caudra
Not built in; Plan Mode example
Read-only modeNot yet checked: caudra
Not yet checked for caudra
Through plan mode
Not built in; Plan Mode example
Review diffsNot yet checked: caudra, Pi
Not yet checked for caudra
Gemini CLI Companion extension
Not yet checked for Pi
Undo file editsNot yet checked: caudra
Not yet checked for caudra
Maker's git-checkpoint example

Parallel agents

Parallel sessionsNot yet checked: caudra, Gemini CLI, Pi
Not yet checked for caudra
Not yet checked for Gemini CLI
Not yet checked for Pi
Git worktreesNot yet checked: caudra, Pi
Not yet checked for caudra
Experimental; turn on first
Not yet checked for Pi

Context and memory

Project instruction filesNot yet checked: caudra
Not yet checked for caudra
Memory across sessionsNot yet checked: caudra, Pi
Not yet checked for caudra
Not yet checked for Pi
Resume a sessionNot yet checked: caudra
Not yet checked for caudra
Browse past sessionsNot yet checked: caudra
Not yet checked for caudra

Remote and mobile control

Remote controlNot yet checked: caudra, Gemini CLI, Pi
Not yet checked for caudra
Needs a Claude plan, not an API key
Not yet checked for Gemini CLI
Not yet checked for Pi
Steer from a phoneNot yet checked: caudra, Gemini CLI, Pi
Not yet checked for caudra
Needs a Claude plan, not an API key
Not yet checked for Gemini CLI
Not yet checked for Pi
NotificationsNot yet checked: caudra
Not yet checked for caudra
Depends on the terminal
Experimental; off by default
Maker's notify example

Sandbox, permissions and privacy

OS-level sandboxNot yet checked: caudra
Not yet checked for caudra
Not on native Windows
Opt-in; Seatbelt is macOS only
Gondolin micro-VM example
Approval modesNot yet checked: caudra
Not yet checked for caudra
Runs in a containerNot yet checked: caudra, Claude Code CLI
Not yet checked for caudra
Not yet checked for Claude Code CLI
Opt-in Docker or Podman sandbox
The repo's Docker recipe
Telemetry opt-outNot yet checked: caudra, Gemini CLI
Not yet checked for caudra
Not yet checked for Gemini CLI

Images, web and your computer

Image inputNot yet checked: caudra
Not yet checked for caudra
Needs a compatible terminal
Fetch URLsNot yet checked: caudra, Pi
Not yet checked for caudra
Not yet checked for Pi
Browser automationNot yet checked: caudra, Gemini CLI, Pi
Not yet checked for caudra
Claude in Chrome extension
Not yet checked for Gemini CLI
Not yet checked for Pi
Computer useNot yet checked: caudra, Gemini CLI, Pi
Not yet checked for caudra
macOS only; Pro, Max or Ultra plan
Not yet checked for Gemini CLI
Not yet checked for Pi
Voice inputNot yet checked: caudra, Gemini CLI, Pi
Not yet checked for caudra
Claude.ai sign-in; no cloud or SSH
Not yet checked for Gemini CLI
Not yet checked for Pi
Not yet checked: , , ,

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

caudra

Claude Code CLI

Gemini CLI

Pi

How to read the Index score

At a glance

Index score out of 100

caudra19Claude Code CLI92Gemini CLI44Pi78

Mindshare HN mentions, 90 days

caudra5Claude Code CLI4,602Gemini CLI58Pi1,310

Adoption GitHub stars, not scored

caudra11Claude Code CLI156kGemini CLI109kPi123k

Release days last 90 days

caudra0Claude Code CLI57Gemini CLI12Pi19

Lowest monthly plan billed monthly, lower is cheaper

caudraNot yet checkedClaude Code CLI$20/moGemini CLINot yet checkedPiNot yet checked

Platforms systems and surfaces

caudra4Claude Code CLI5Gemini CLI3Pi4

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
caudracaudra · CLI agent
Claude Code CLIAnthropic · CLI agent
Gemini CLIgoogle-gemini · CLI agent
PiEarendil Works · CLI agent
Interface
Terminal session listing file searches and reads while tests run
Terminal session after an MCP tool call generated three image files
pi startup listing loaded context, skills and extensions, then reading docs and running bash
What it is
Caudra is growing from a terminal coding agent into a complete AI workspace: a cockpit to run agents, persistent agents with memory, and the TUI agent you can use today.
Terminal coding tool that executes routine tasks and handles git workflows
Open-source terminal agent for enterprise Gemini Code Assist workflows on Google Cloud
Minimal, extensible agent harness that you can make your own
Category
CLI agent
CLI agentClaude Code family
CLI agentGemini CLI family
CLI agent
Pricing
Starts at (billing shown)
Lowest monthly plan
Not yet checked
Not yet checked
Not yet checked
Free tier
Not yet checked
Not yet checked
Plans
Not yet checked
Runs on
Linux
Yes
Yes
Yes
Yes
Terminal
Yes
Yes
Yes
Yes
Web
Not yet checked
Yes
Not yet checked
Not yet checked
Windows
Yes
Yes
Not yet checked
Yes
macOS
Yes
Yes
Yes
Yes
Models and agents
Drives these agents
Not yet checked
Not yet checked
Not yet checked
Not yet checked
Source and activity
Source
GitHub stars
Most
Release days, last 90 days
0
57Most
12
19
Release days per week
Latest release, any channel
v0.2.0-preview.17 30 Oct 2026
v2.1.327 17 Nov 2026
v0.68.0 10 Nov 2026
v1.5.2 10 Nov 2026
Index score
Score and rank
19 #75 Score 19.5; ranked on the unrounded score
92 #1 Score 91.6; ranked on the unrounded score
44 #18 Score 44.3; ranked on the unrounded score
78 #4 Score 77.9; ranked on the unrounded score
Mindshare
195 Hacker News mentions in the last 90 days
924,602 Hacker News mentions in the last 90 days
4458 Hacker News mentions in the last 90 days
781,310 Hacker News mentions in the last 90 days
Adoption, not scored
2011 stars, read 18 Nov 2026
98156,056 stars, read 18 Nov 2026
95108,907 stars, read 18 Nov 2026
96122,575 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
First ranked 18 Nov 2026
First ranked 18 Nov 2026
First ranked 18 Nov 2026
Full page

Watch caudra vs Claude Code CLI vs Gemini CLI vs Pi on YouTube

More comparisons

Build your own