Skip to content
ADE Index

Claude Code CLI vs Grok Build 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 three CLI agents only. Claude Code has 4 other listings, each with its own page.

How they differ

Price
Pick this if…

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

Same for all 3 (1): Systems: Terminal, macOS, Windows, Linux
  • Systems: Terminal, macOS, Windows, Linux · ·

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.

28 capabilities are checked for at least two of these tools. 8 get different answers, among them Approval modes, Subagents, Editor integration and Plan mode; 4 differ only in a limit. 9 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
,,,
Listing also names: Microsoft Foundry (Azure AI Foundry)
,,,
Listing also names: SpaceXSI (Grok), Amazon Bedrock
,,,,,,,,
+17 more model providers
,,,,,,,,,,,,,,,,
Not every provider checked yet
Listing also names 5 othersSpaceXSI (Grok), Z.ai, OpenCode Console (OpenCode Zen), Meta AI (Llama), Microsoft Foundry (Azure AI Foundry)
Local modelsNot yet checked: Claude Code CLI
Not yet checked for Claude Code CLI
Custom OpenAI-compatible endpointNot yet checked: Claude Code CLI
Not yet checked for Claude Code CLI
Token and cost usage
Token view for API users
Optional status line

MCP, hooks, skills and subagents

MCP servers
local and remote
local and remote
local and remote
Hooks
Skills
Subagents
Not built in; Subagent example
Plugins
Custom commands

Editors, scripts and CI

Editor integrationNot yet checked: Pi
VS Code extension or JetBrains plugin
ACP editors
Not yet checked for Pi
Headless mode
JSON output
GitHub integrationNot yet checked: Grok Build, Pi
Claude Code GitHub Action
Not yet checked for Grok Build
Not yet checked for Pi
Commit attribution controlNot yet checked: Grok Build, Pi
Not yet checked for Grok Build
Not yet checked for Pi

Review, steer and undo

Plan mode
Not built in; Plan Mode example
Read-only mode
Through plan mode
Writes limited to ~/.grok and temp
Not built in; Plan Mode example
Review diffsNot yet checked: Grok Build, Pi
Not yet checked for Grok Build
Not yet checked for Pi
Undo file editsNot yet checked: Grok Build
Not yet checked for Grok Build
Maker's git-checkpoint example

Parallel agents

Parallel sessionsNot yet checked: Pi
Not yet checked for Pi
Git worktreesNot yet checked: Pi
Not yet checked for Pi

Context and memory

Project instruction files
Trusted folders only
Memory across sessionsNot yet checked: Pi
Experimental; off by default
Not yet checked for Pi
Resume a session
Browse past sessions

Remote and mobile control

Remote controlNot yet checked: Grok Build, Pi
Needs a Claude plan, not an API key
Not yet checked for Grok Build
Not yet checked for Pi
Steer from a phoneNot yet checked: Grok Build, Pi
Needs a Claude plan, not an API key
Not yet checked for Grok Build
Not yet checked for Pi
Notifications
Depends on the terminal
Maker's notify example

Sandbox, permissions and privacy

OS-level sandbox
Not on native Windows
Off by default
Gondolin micro-VM example
Approval modes
Runs in a containerNot yet checked: Claude Code CLI, Grok Build
Not yet checked for Claude Code CLI
Not yet checked for Grok Build
The repo's Docker recipe
Telemetry opt-outNot yet checked: Grok Build
Not yet checked for Grok Build

Images, web and your computer

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

Claude Code CLI

Grok Build

Pi

How to read the Index score

At a glance

Index score out of 100

Claude Code CLI92Grok Build40Pi78

Mindshare HN mentions, 90 days

Claude Code CLI4,602Grok Build40Pi1,310

Adoption GitHub stars, not scored

Claude Code CLI156kGrok Build27.8kPi123k

Release days last 90 days

Claude Code CLI57Grok Build0Pi19

Lowest monthly plan billed monthly, lower is cheaper

Claude Code CLI$20/moGrok BuildNot yet checkedPiNot yet checked

Platforms systems and surfaces

Claude Code CLI5Grok Build4Pi4

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
Claude Code CLIAnthropic · CLI agent
Grok Buildxai-org · CLI agent
PiEarendil Works · CLI agent
Interface
Terminal session listing file searches and reads while tests run
Grok Build TUI streaming a long answer, with token count, model and approval mode
pi startup listing loaded context, skills and extensions, then reading docs and running bash
What it is
Terminal coding tool that executes routine tasks and handles git workflows
TUI coding agent for interactive sessions, scripting, CI and ACP-compatible editors
Minimal, extensible agent harness that you can make your own
Category
CLI agentClaude Code family
CLI agent
CLI agent
Pricing
Starts at (billing shown)
Lowest monthly plan
Not yet checked
Not yet checked
Free tier
Not yet checked
Plans
Runs on
Linux
Yes
Yes
Yes
Terminal
Yes
Yes
Yes
Web
Yes
Not yet checked
Not yet checked
Windows
Yes
Yes
Yes
macOS
Yes
Yes
Yes
Models and agents
Drives these agents
Not yet checked
Not yet checked
Not yet checked
Source and activity
Source
GitHub stars
Most
Release days, last 90 days
57Most
0
19
Release days per week
Latest release, any channel
v2.1.327 17 Nov 2026
Not yet checked
v1.5.2 10 Nov 2026
Index score
Score and rank
92 #1 Score 91.6; ranked on the unrounded score
40 #26 Score 40.3; ranked on the unrounded score
78 #4 Score 77.9; ranked on the unrounded score
Mindshare
924,602 Hacker News mentions in the last 90 days
4040 Hacker News mentions in the last 90 days
781,310 Hacker News mentions in the last 90 days
Adoption, not scored
98156,056 stars, read 18 Nov 2026
8427,801 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.
Rank history
First ranked 18 Nov 2026
First ranked 18 Nov 2026
First ranked 18 Nov 2026
Full page

Watch Claude Code CLI vs Grok Build vs Pi on YouTube

More comparisons

Build your own