Skip to content
ADE Index

Claude Code CLI vs Codex CLI vs Pi vs postal

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 Codex has 5 other listings, each with its own page.

How they differ

SystemsClaude Code CLI 4 · Codex CLI 4 · Pi 4 · postal 1 · 1 in all
, ,
, ,
, ,
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 Claude Code CLI, Codex CLI and Pi, not yet for postal: Price (Claude Code CLI: ; Codex CLI: ; Pi: ), Bring your own key (Claude Code CLI: ; Codex CLI: ; Pi: )

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 postal’s capabilities yet. 30 capabilities are checked for at least two of these tools. 7 get different answers, among them Approval modes, Subagents, Plan mode and Undo file edits; 6 differ only in a limit. 7 others are checked for one tool only.

Differences only13
  • 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

Named model providersFrom the listing
,,,
Listing also names: Microsoft Foundry (Azure AI Foundry)
,,,
Listing also names: LM Studio
,,,,,,,,
+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, postal
Not yet checked for Claude Code CLI
Not yet checked for postal
Custom OpenAI-compatible endpointNot yet checked: Claude Code CLI, postal
Not yet checked for Claude Code CLI
Not yet checked for postal
Token and cost usageNot yet checked: postal
Token view for API users
Not yet checked for postal

MCP, hooks, skills and subagents

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

Editors, scripts and CI

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

Review, steer and undo

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

Parallel agents

Parallel sessionsNot yet checked: Codex CLI, Pi, postal
Not yet checked for Codex CLI
Not yet checked for Pi
Not yet checked for postal
Git worktreesNot yet checked: Pi, postal
Local execution only
Not yet checked for Pi
Not yet checked for postal

Context and memory

Project instruction filesNot yet checked: postal
Not yet checked for postal
Memory across sessionsNot yet checked: Pi, postal
Off by default; local memories
Not yet checked for Pi
Not yet checked for postal
Resume a sessionNot yet checked: postal
Not yet checked for postal
Browse past sessionsNot yet checked: postal
Not yet checked for postal

Remote and mobile control

Remote controlNot yet checked: Pi, postal
Needs a Claude plan, not an API key
To a running app server
Not yet checked for Pi
Not yet checked for postal
Steer from a phoneNot yet checked: Codex CLI, Pi, postal
Needs a Claude plan, not an API key
Not yet checked for Codex CLI
Not yet checked for Pi
Not yet checked for postal
NotificationsNot yet checked: postal
Depends on the terminal
Maker's notify example
Not yet checked for postal

Sandbox, permissions and privacy

OS-level sandboxNot yet checked: postal
Not on native Windows
Linux/WSL2 needs bubblewrap
Gondolin micro-VM example
Not yet checked for postal
Approval modesNot yet checked: postal
Not yet checked for postal
Runs in a containerNot yet checked: Claude Code CLI, Codex CLI, postal
Not yet checked for Claude Code CLI
Not yet checked for Codex CLI
The repo's Docker recipe
Not yet checked for postal
Telemetry opt-outNot yet checked: Codex CLI, postal
Not yet checked for Codex CLI
Not yet checked for postal

Images, web and your computer

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

Codex CLI

Pi

postal

How to read the Index score

At a glance

Index score out of 100

Claude Code CLI92Codex CLI91Pi78postalNot enough data yet

Mindshare HN mentions, 90 days

Claude Code CLI4,602Codex CLI4,237Pi1,310postal0

Adoption GitHub stars, not scored

Claude Code CLI156kCodex CLI136kPi123kpostal212

Release days last 90 days

Claude Code CLI57Codex CLI32Pi19postal6

Lowest monthly plan billed monthly, lower is cheaper

Claude Code CLI$20/moCodex CLI$20/monthPiNot yet checkedpostalNot yet checked

Platforms systems and surfaces

Claude Code CLI5Codex CLI4Pi4postal1

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
Claude Code CLIAnthropic · CLI agent
Codex CLIOpenAI · CLI agent
PiEarendil Works · CLI agent
postalandrefetch · CLI agent
Interface
Terminal session listing file searches and reads while tests run
Codex CLI explaining a codebase, with an updated plan checklist
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
Coding agent from OpenAI that runs locally on your computer
Minimal, extensible agent harness that you can make your own
An open-source, asynchronous, terminal-based AI coding agent that reads your code, executes tools, and helps you build.
Category
CLI agentClaude Code family
CLI agentCodex family
CLI agent
CLI agent
Pricing
Starts at (billing shown)
Not yet checked
Lowest monthly plan
Not yet checked
Not yet checked
Free tier
Not yet checked
Not yet checked
Not yet checked
Plans
Not yet checked
Bring your own key
Yes
Yes
Yes
Not yet checked
Runs on
Linux
Yes
Yes
Yes
Not yet checked
Terminal
Yes
Yes
Yes
Yes
Web
Yes
Not yet checked
Not yet checked
Not yet checked
Windows
Yes
Yes
Yes
Not yet checked
macOS
Yes
Yes
Yes
Not yet checked
Models and agents
Models
Not yet checked
GPT-6.2 AstraGPT-6.2 SolGPT-6.1 TerraGPT-6.1 SolGPT-6 Luna
Not yet checked
Not yet checked
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
57Most
32
19
6
Release days per week
Latest release, any channel
v2.1.327 17 Nov 2026
v1.5.2 10 Nov 2026
v0.0.39 17 Nov 2026
Index score
Score and rank
92 #1 Score 91.6; ranked on the unrounded score
91 #2 Score 90.7; ranked on the unrounded score
78 #4 Score 77.9; ranked on the unrounded score
Not enough data yet
Mindshare
924,602 Hacker News mentions in the last 90 days
914,237 Hacker News mentions in the last 90 days
781,310 Hacker News mentions in the last 90 days
00 Hacker News mentions in the last 90 days
Adoption, not scored
98156,056 stars, read 18 Nov 2026
97135,675 stars, read 18 Nov 2026
96122,575 stars, read 18 Nov 2026
44212 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
Not ranked
Full page

Watch Claude Code CLI vs Codex CLI vs Pi vs postal on YouTube

More comparisons

Build your own