Which is a Higher Coding Agent?

Open-source CLI instruments have created lots of pleasure within the developer and AI communities. With the discharge of Claude’s Codex CLI, OpenAI’s Codex CLI, and, extra just lately, Google’s Gemini CLI, there’s a sudden improve in curiosity in CLIs generally. By incorporating AI help into routine duties, these instruments are altering how builders use their terminals.

Builders can enhance code comprehension, pace up debugging, and automate tough coding duties by utilising these CLIs. Instruments like Codex CLI assist customers write, analyse, and enhance code extra effectively by bringing sturdy AI-driven options like code era, refactoring, and inline documentation straight into the command line. The market has turn out to be much more thrilling with the launch of Gemini CLI, a light-weight, open-source substitute from Google that’s gaining recognition rapidly.

Let’s now take a more in-depth take a look at how Gemini CLI and Codex CLI fare when put to the check.

What are Gemini CLI and Codex CLI?

Gemini CLI: An open-source AI agent by Google that integrates Gemini fashions (like Gemini 2.5 Professional) into the terminal for builders.

Codex CLI: An open-source command-line instrument forked from OpenAI’s authentic Codex CLI, now supporting a number of AI suppliers, together with Gemini 2.5 Professional. It allows builders to work together with massive language fashions within the terminal for duties like code era, refactoring, and script rationalization.

In the event you’re searching for detailed walkthroughs, try our guides on every CLI instrument:

Set up

Earlier than continuing with the set up, be certain that the system necessities are happy.

System Necessities

NodeJS is a typical prerequisite for each the CLIs. You possibly can set up Node.js by following the directions on its official web page: https://nodejs.org/

Set up Steps for Codex CLI

1. Examine Node.js model:

node --version

2. Guarantee it’s NodeJS model 22 or larger.
3. Set up Codex CLI globally:

npm set up -g @openai/codex

4. Or utilizing pnpm:

pnpm add -g @openai/codex

5. Set your OpenAI API key (if inside your undertaking listing’s .env file incorporates the OPEN AI API Key, then we don’t want to do that job):

export OPENAI_API_KEY="your-openai-api-key"

6. Add this line to your shell config file (e.g., ~/.bashrc, ~/.zshrc) for persistence.
7. Run Codex CLI:

codex

8. Or go a immediate straight:

codex "clarify this codebase to me"

Set up Steps for Gemini CLI

1. Examine Node.js model:

node --version

Guarantee it’s 18 or larger.

2. Set up Gemini CLI globally (beneficial):

npm set up -g @google/gemini-cli

3. Alternatively, run straight with out set up:

npx https://github.com/google-gemini/gemini-cli

4. Authenticate:
   1. Default: Register along with your Google account when prompted (browser window will open).
   2. API Key (for superior use):
      1. Get your API key from Google AI Studio.
      2. Set it in your setting utilizing the next entry:
         export GEMINI_API_KEY=”your-api-key”
5. Run Gemini CLI:

gemini

6. Or go a immediate straight:

gemini "Hi there, are you able to assist me with coding?"

Issues to Hold in Thoughts

• For each instruments, Node.js and npm (Node Bundle Supervisor) have to be put in and accessible in your system PATH.
• For Codex CLI, Node.js 22+ is required, whereas Gemini CLI works with Node.js 18+.
• Each require authentication through API keys or account login for full performance.
• On Home windows, Codex CLI is greatest run through WSL2 for full compatibility.
• Keep in mind, if you wish to use your CLI for a sure undertaking, be sure to have the present working listing set to the folder path the place your undertaking exists. 

Operating our CLI Situations

Let’s proceed to check the efficiency between the two fashions with 3 duties

• Constructing a working mannequin on a neighborhood host
• Studying a posh codebase and explaining the code
• Error debugging

Let’s first strive it out with Codex CLI:

Codex CLI

If all the necessities have been happy, then we will begin with the checks.

Job 1 – Explaining our Codebase

We are able to see that Codex can present an in depth abstract of our code base, which was, to be trustworthy, surprisingly good. Moreover, Codex CLI quickly asks us to grant entry to particular code segments, which we will grant or reject based mostly on our judgment. It supplies a decent report after taking an affordable period of time to replicate.

The report’s high-level objective, repository structure, key parts, front-end web sites, and belongings are all included, together with a abstract. Regardless that I had given the primary information slightly ambiguous names, I used to be nonetheless shocked to search out that it might decode the entire earlier iterations of the code information in chronological order.

Job 2 – Error Debugging

Since we permit the Codex CLI entry to our total database, whether or not or not it’s non-public or protected, it is going to ask for our authorization earlier than studying any code snippets. If we allow it, it is going to entry our snippet appropriately. 

General, it was in a position to recognise each minute mistake and sometimes provided fixes for some careless errors within the code, eradicating pointless parts that had an influence on among the latency barely.

Job 3 – Additions to Codebase

This concerned understanding how every module was outlined throughout varied directories and bridging the information between every dependency to make sure that a brand new listing was created to construct the brand new .py information for the additions we had requested after we requested entry.

Let’s now try to look at how the Gemini CLI capabilities.

Gemini CLI

I appreciated the Dracula theme.

In contrast to Codex CLI, the place we solely must export our OPENAI_API_KEY, we’ve three other ways to log in right here: utilizing our Gmail account, copying the GEMINI_API_KEY from AIStudio, or utilizing Vertex AI credentials.

Job 1 – Clarify our Codebase

The principle distinction I noticed was that, in contrast to Codex CLI, which asks for entry to particular directories, Gemini skips this step and as an alternative scans our total database. Nonetheless, in my expertise, it does provide an honest overview, however it’s on no account nearly as good as Codex by way of output.

Job 2 – Error Debugging

For my part, Gemini’s response was considerably higher defined than Codex’s, because it was in a position to determine the sorts of safety dangers, clarify them, and supply file names as references for additional investigation and prompt adjustments. Moreover, providing an intensive technique to deal with every of those errors would allow the code to be modified with out impairing its performance if the required directions have been adopted.

Job 3 – Additions to Codebase

Gemini CLI wasn’t working for this workload, so no output was produced.

Gemini CLI vs Codex CLI: Closing Verdict

Additionally Learn: 10 Methods College students Can Use Cursor AI for Free

Conclusion

When evaluating the options of those two CLIs, I discovered that Codex affords extra performance than Gemini CLI. In the intervening time, each the CLIs are open-sourced and can ultimately have higher performance in future releases. 

Since a GPT mannequin analyses our code, Codex additionally affords larger privateness by requesting entry to our codebases and modules in a manner that minimizes safety threat. Nevertheless, this doesn’t seem like a case of the Gemini CLI requesting entry commonly; as an alternative, it asks when it desires to run the appliance code. Moreover, we must always keep in mind that the context on the best facet of the terminal can also be tracked by Gemini CLI. 

When mixed with extra clever vibe coding IDEs like Cursor, Windsurf, and others, such CLIs would undoubtedly open up new potentialities for vibe coding workflow and software operation. Nevertheless, safety and privateness vulnerabilities should exist, so I’d advise being cautious about what and the place in our codebase we grant these CLIs entry.  

Often Requested Questions

GenAI Intern @ Analytics Vidhya | Closing Yr @ VIT Chennai
Captivated with AI and machine studying, I am desperate to dive into roles as an AI/ML Engineer or Information Scientist the place I could make an actual influence. With a knack for fast studying and a love for teamwork, I am excited to convey modern options and cutting-edge developments to the desk. My curiosity drives me to discover AI throughout varied fields and take the initiative to delve into information engineering, making certain I keep forward and ship impactful initiatives.