Bash-based AI coding assistant uses local Gemma model, outperforms Copilot

A developer has created a command-line coding assistant using a combination of standard Linux tools like bash, sed, and grep, along with curl. This project, named "canitbedone," utilizes a local instance of Google's Gemma 4 model running through llama.cpp for its AI capabilities. The developer reports that this tool performs surprisingly well, even outperforming GitHub Copilot on certain tasks, and has minimal dependencies beyond the core Linux utilities and the AI model. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Demonstrates how local LLMs can be integrated with traditional command-line tools for practical coding assistance.

RANK_REASON This is a user-created tool that leverages existing AI models and standard software utilities.

Read on Mastodon — mastodon.social →

• Mastodon
• canitbedone
• bash
• Gemma 4
• llama.cpp
• GitHub Copilot
• Linux

• product
• model release