Skip to content
ADE Index

autopilot vs Claude Code CLI vs Codex CLI vs uji

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

Pick this if…

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

Checked for autopilot, Claude Code CLI and Codex CLI, not yet for uji: Price (autopilot: ; Claude Code CLI: ; Codex CLI: ), Bring your own key (autopilot: ; Claude Code CLI: ; Codex CLI: ), Systems (autopilot: , , , ; Claude Code CLI: , , , ; Codex CLI: , , , )

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 autopilot’s capabilities yet. 26 capabilities are checked for at least two of these tools. 8 differ only in a limit. 10 others are checked for one tool only.

Differences only8
  • Yesthe maker documents it
  • With add-onAdd-onsomething the maker publishes that you install or run
  • *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
,,,,,,,,
+18 more model providers
,,,,,,,,,,,,,,,,,
+ providers you add
Listing also names: SpaceXSI (Grok)
,,,+ providers you add
Listing also names: Microsoft Foundry (Azure AI Foundry)
,,,
Listing also names: LM Studio
,,,,,,,,
+13 more model providers
,,,,,,,,,,,,
+ providers you add
Listing also names: SpaceXSI (Grok), Together AI, OpenCode Console (OpenCode Zen)
Local modelsNot yet checked: autopilot, Claude Code CLI, uji
Not yet checked for autopilot
Not yet checked for Claude Code CLI
Not yet checked for uji
Custom OpenAI-compatible endpointNot yet checked: autopilot, Claude Code CLI, uji
Not yet checked for autopilot
Not yet checked for Claude Code CLI
Not yet checked for uji
Token and cost usageNot yet checked: autopilot, uji
Not yet checked for autopilot
Token view for API users
Not yet checked for uji

MCP, hooks, skills and subagents

MCP serversNot yet checked: autopilot, uji
Not yet checked for autopilot
local and remote
local and remote
Not yet checked for uji
HooksNot yet checked: autopilot, uji
Not yet checked for autopilot
Not yet checked for uji
SkillsNot yet checked: autopilot, uji
Not yet checked for autopilot
Not yet checked for uji
SubagentsNot yet checked: autopilot, uji
Not yet checked for autopilot
Not yet checked for uji
PluginsNot yet checked: autopilot, uji
Not yet checked for autopilot
Not yet checked for uji
Custom commandsNot yet checked: autopilot, uji
Not yet checked for autopilot
Not yet checked for uji

Editors, scripts and CI

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

Review, steer and undo

Plan modeNot yet checked: autopilot, uji
Not yet checked for autopilot
Not yet checked for uji
Read-only modeNot yet checked: autopilot, uji
Not yet checked for autopilot
Through plan mode
Not yet checked for uji
Review diffsNot yet checked: autopilot, uji
Not yet checked for autopilot
Not yet checked for uji
Undo file editsNot yet checked: autopilot, Codex CLI, uji
Not yet checked for autopilot
Not yet checked for Codex CLI
Not yet checked for uji

Parallel agents

Parallel sessionsNot yet checked: autopilot, Codex CLI, uji
Not yet checked for autopilot
Not yet checked for Codex CLI
Not yet checked for uji
Git worktreesNot yet checked: autopilot, uji
Not yet checked for autopilot
Local execution only
Not yet checked for uji

Context and memory

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

Remote and mobile control

Remote controlNot yet checked: autopilot, uji
Not yet checked for autopilot
Needs a Claude plan, not an API key
To a running app server
Not yet checked for uji
Steer from a phoneNot yet checked: autopilot, Codex CLI, uji
Not yet checked for autopilot
Needs a Claude plan, not an API key
Not yet checked for Codex CLI
Not yet checked for uji
NotificationsNot yet checked: autopilot, uji
Not yet checked for autopilot
Depends on the terminal
Not yet checked for uji

Sandbox, permissions and privacy

OS-level sandboxNot yet checked: autopilot, uji
Not yet checked for autopilot
Not on native Windows
Linux/WSL2 needs bubblewrap
Not yet checked for uji
Approval modesNot yet checked: autopilot, uji
Not yet checked for autopilot
Not yet checked for uji
Telemetry opt-outNot yet checked: autopilot, Codex CLI, uji
Not yet checked for autopilot
Not yet checked for Codex CLI
Not yet checked for uji

Images, web and your computer

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

One capability is not yet checked for any of these tools and is not shown. 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

autopilot

Claude Code CLI

Codex CLI

uji

How to read the Index score

At a glance

Index score out of 100

autopilot8Claude Code CLI92Codex CLI91uji12

Mindshare HN mentions, 90 days

autopilot1Claude Code CLI4,602Codex CLI4,237uji2

Adoption GitHub stars, not scored

autopilot221Claude Code CLI156kCodex CLI136kujiNot yet checked

Release days last 90 days

autopilot34Claude Code CLI57Codex CLI32ujiNot yet checked

Lowest monthly plan billed monthly, lower is cheaper

autopilotNot yet checkedClaude Code CLI$20/moCodex CLI$20/monthujiNot yet checked

Platforms systems and surfaces

autopilot4Claude Code CLI5Codex CLI4ujiNot yet checked

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
autopilotdirectionally-local · CLI agent
Claude Code CLIAnthropic · CLI agent
Codex CLIOpenAI · CLI agent
ujiCLI agent
Interface
Terminal session listing file searches and reads while tests run
Codex CLI explaining a codebase, with an updated plan checklist
What it is
Open-source terminal coding agent and SDK.
Terminal coding tool that executes routine tasks and handles git workflows
Coding agent from OpenAI that runs locally on your computer
Modular coding agent whose components can be swapped at runtime
Category
CLI agent
CLI agentClaude Code family
CLI agentCodex family
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
Not yet checked
Web
Not yet checked
Yes
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
Not yet checked
GPT-6.2 AstraGPT-6.2 SolGPT-6.1 TerraGPT-6.1 SolGPT-6 Luna
Not yet checked
Drives these agents
Not yet checked
Not yet checked
Not yet checked
Not yet checked
Source and activity
Source
Not yet checked
GitHub stars
Most
Not yet checked
Release days, last 90 days
34
57Most
32
Not yet checked
Release days per week
Not yet checked
Latest release, any channel
v3.27.0 18 Nov 2026
v2.1.327 17 Nov 2026
Not yet checked
Index score
Score and rank
8 #153 Score 7.5; ranked on the unrounded score
92 #1 Score 91.6; ranked on the unrounded score
91 #2 Score 90.7; ranked on the unrounded score
12 #107 Score 11.9; ranked on the unrounded score
Mindshare
81 Hacker News mention in the last 90 days
924,602 Hacker News mentions in the last 90 days
914,237 Hacker News mentions in the last 90 days
122 Hacker News mentions in the last 90 days
Adoption, not scored
44221 stars, read 18 Nov 2026
98156,056 stars, read 18 Nov 2026
97135,675 stars, read 18 Nov 2026
Not yet checked
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 autopilot vs Claude Code CLI vs Codex CLI vs uji on YouTube

More comparisons

Build your own