coderunner VS gemini-cli

I have actually been working on something similar but instead of Docker, I am using Apple’s builtin container support to run shell commands and code with real OS-level isolation. It’s fast (spawns in milliseconds) and integrates nicely with things like Claude Code and the Gemini CLI. I open sourced it as CodeRunner[1]. Would love to hear what people think or chat about how it compares.

1. https://github.com/BandarLabs/coderunner

We looked at Pyodide and WASM along with other options like firecracker for our need of multi-step tasks that require running LLM generated code locally via Ollama etc. with some form of isolation than running it directly on our dev machines and figured it would be too much work with the various external libraries we have to install. The idea was to get code generated by a powerful remote LLM for general purpose stuff like video editing via ffmpeg, beautiful graphs generation via JS + chromium and stuff and execute it locally with all dependencies being installed before execution.

We built CodeRunner (https://github.com/BandarLabs/coderunner) on top of Apple Containers recently and have been using it for sometime. This works fine but still needs some improvement to work across very arbitrary prompts.

Gemini CLI supports code execution itself but via shell, which can be a security issue. CodeRunner solves this by running it in a safe isolated container.

Hi - I integrated Apple Container on M1 to run[1] the code executed by Gemini CLI. It works great!

1. CodeRunner - https://github.com/BandarLabs/coderunner/tree/main?tab=readm...

Interesting that I posted this few hours ago - https://github.com/BandarLabs/coderunner

The major difference would be Gemini CLI running code directly on you mac vs in a Apple container (in my tool).

They do have MCP support so I can probably add apple container support to it. Let's see once they make the repo public.

Unfortunately, the "protocol" doesn't have any emphasis on security so far, its all a repeat of HTTP -> HTTPS.

However I feel the tooling built around MCP has been a lot and makes your work easier.

The perfect use today would be using a locally running MCP servers for execution of code[1], manipulation of local files etc.

1. CodeRunner - Generate and run LLM code locally on Apple containers (https://github.com/BandarLabs/coderunner) (I am one of the authors)

Gemini CLI

With that mission in mind, I put the three major contenders of the moment to the test: Anthropic's Claude Code, the model-agnostic OpenCode, and Google's official Gemini CLI.

For example, Gemini CLI [1] can use native sandboxing on macOS. It's just a matter of time before every major coding agent will run inside of an operating system's native sandbox/container/jail/VM.

[1]: https://github.com/google-gemini/gemini-cli/blob/main/docs/c...

Also, if you are on Google Workspace, then everything changes there too. Activating the Gemini CLI is a smile while crying emoji kind of activity if you are trying to provide this to an entire organization [1]

[1]: https://github.com/google-gemini/gemini-cli/blob/main/docs/c...

Before people let their confirmation biases go wild about how terrible Gemini is, the original author was completely wrong. His files were never deleted: https://github.com/google-gemini/gemini-cli/issues/4586. He is a technically incompetent PM "vibe coding" who created a false story:

```

It’s a rough time to be doing this here in July 2025 because Cursor just nerfed its paid plans and all the first-party coding tools (Codex, Gemini CLI, Claude Code) don’t have feature parity with each other, but do what you can.

I was surprised recently to see that gemini-cli[0] and codex[1] each have way more GitHub stars than Claude Code[3]. Currently 62k, 31k, and 25k respectively.

Stars are only a proxy for use, of course, but I'm not sure what a closer public indicator might be.

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

2. https://github.com/openai/codex

3. https://github.com/anthropics/claude-code

Google has gemini-cli that is pretty close to Claude Code in terms of experience https://github.com/google-gemini/gemini-cli and has a generous free tier