Skip to content
ADE Index

Hazzel vs Codex CLI vs Qwen Code

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

How they differ

Qwen Code is built on Gemini CLI: This project was originally based on Google Gemini CLI v0.8.2. raw.githubusercontent.com

Price
SystemsHazzel 1 · Codex CLI 4 · Qwen Code 1 · 1 in all
Nothing the others do not have
, ,
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.

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 Hazzel’s capabilities yet. 18 capabilities are checked for at least two of these tools. 4 differ only in a limit. 14 others are checked for one tool only.

Differences only4
  • 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

Bring your own keyFrom the listing
Named model providersFrom the listing
,,,,,,
Listing also names: Google
,,,
Listing also names: LM Studio
,,,,,,,,
+2 more model providers
,
+ providers you add
Listing also names: Alibaba (Qwen), OCI Enterprise AI (OCI Generative AI)
Local modelsNot yet checked: Hazzel
Not yet checked for Hazzel
Custom OpenAI-compatible endpointNot yet checked: Hazzel, Qwen Code
Not yet checked for Hazzel
Not yet checked for Qwen Code
Token and cost usageNot yet checked: Hazzel, Qwen Code
Not yet checked for Hazzel
Not yet checked for Qwen Code

MCP, hooks, skills and subagents

MCP serversNot yet checked: Hazzel
Not yet checked for Hazzel
local and remote
HooksNot yet checked: Hazzel
Not yet checked for Hazzel
SkillsNot yet checked: Hazzel
Not yet checked for Hazzel
SubagentsNot yet checked: Hazzel
Not yet checked for Hazzel
PluginsNot yet checked: Hazzel, Qwen Code
Not yet checked for Hazzel
Not yet checked for Qwen Code
Custom commandsNot yet checked: Hazzel
Not yet checked for Hazzel

Editors, scripts and CI

Editor integrationNot yet checked: Hazzel
Not yet checked for Hazzel
Codex editor extension
VS Code extension (beta)
Headless modeNot yet checked: Hazzel
Not yet checked for Hazzel
JSON outputNot yet checked: Hazzel, Qwen Code
Not yet checked for Hazzel
Not yet checked for Qwen Code
GitHub integrationNot yet checked: Hazzel, Qwen Code
Not yet checked for Hazzel
Codex GitHub Action
Not yet checked for Qwen Code

Review, steer and undo

Plan modeNot yet checked: Hazzel
Not yet checked for Hazzel
Read-only modeNot yet checked: Hazzel
Not yet checked for Hazzel
Review diffsNot yet checked: Hazzel, Qwen Code
Not yet checked for Hazzel
Not yet checked for Qwen Code

Parallel agents

Git worktreesNot yet checked: Hazzel
Not yet checked for Hazzel
Local execution only

Context and memory

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

Remote and mobile control

Remote controlNot yet checked: Hazzel
Not yet checked for Hazzel
To a running app server
Via chat-app Channels
Steer from a phoneNot yet checked: Hazzel, Codex CLI
Not yet checked for Hazzel
Not yet checked for Codex CLI
Via chat-app Channels
NotificationsNot yet checked: Hazzel, Qwen Code
Not yet checked for Hazzel
Not yet checked for Qwen Code

Sandbox, permissions and privacy

OS-level sandboxNot yet checked: Hazzel
Not yet checked for Hazzel
Linux/WSL2 needs bubblewrap
Approval modesNot yet checked: Hazzel
Not yet checked for Hazzel
Telemetry opt-outNot yet checked: Hazzel, Codex CLI
Not yet checked for Hazzel
Not yet checked for Codex CLI

Images, web and your computer

Image inputNot yet checked: Hazzel, Qwen Code
Not yet checked for Hazzel
Not yet checked for Qwen Code
Browser automationNot yet checked: Hazzel, Codex CLI
Not yet checked for Hazzel
Not yet checked for Codex CLI
Needs the Chrome extension
Computer useNot yet checked: Hazzel, Codex CLI
Not yet checked for Hazzel
Not yet checked for Codex CLI
Add the Node REPL MCP server
Voice inputNot yet checked: Hazzel, Qwen Code
Not yet checked for Hazzel
Only in builds with voice
Not yet checked for Qwen Code
Not yet checked: , ,

5 capabilities are not yet checked for any of these tools and are 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

Hazzel

Codex CLI

Qwen Code

How to read the Index score

At a glance

Index score out of 100

Hazzel23Codex CLI91Qwen Code25

Mindshare HN mentions, 90 days

Hazzel7Codex CLI4,237Qwen Code9

Adoption GitHub stars, not scored

Hazzel29Codex CLI136kQwen Code30.7k

Release days last 90 days

Hazzel18Codex CLI32Qwen Code30

Lowest monthly plan billed monthly, lower is cheaper

HazzelNot yet checkedCodex CLI$20/monthQwen CodeNot yet checked

Platforms systems and surfaces

Hazzel1Codex CLI4Qwen Code2

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
Hazzelmukundzha · CLI agent
Codex CLIOpenAI · CLI agent
Qwen CodeQwen · CLI agent
Interface
Codex CLI explaining a codebase, with an updated plan checklist
Terminal session editing two JS files with inline diffs, then rerunning vitest
What it is
A terminal coding harness
Coding agent from OpenAI that runs locally on your computer
An open-source AI coding agent that lives in your terminal.
Category
CLI agent
CLI agentCodex family
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
Not yet checked
Yes
Not yet checked
Terminal
Yes
Yes
Yes
Web
Not yet checked
Not yet checked
Yes
Windows
Not yet checked
Yes
Not yet checked
macOS
Not yet checked
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
Drives these agents
Not yet checked
Not yet checked
Not yet checked
Source and activity
Source
GitHub stars
Most
Release days, last 90 days
18
32Most
30
Release days per week
Latest release, any channel
v1.6.2 26 Oct 2026
Index score
Score and rank
23 #64 Score 22.6; ranked on the unrounded score
91 #2 Score 90.7; ranked on the unrounded score
25 #53 Score 25.0; ranked on the unrounded score
Mindshare
237 Hacker News mentions in the last 90 days
914,237 Hacker News mentions in the last 90 days
259 Hacker News mentions in the last 90 days
Adoption, not scored
2829 stars, read 18 Nov 2026
97135,675 stars, read 18 Nov 2026
8530,733 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 Hazzel vs Codex CLI vs Qwen Code on YouTube

More comparisons

Build your own