DEV Community

Cover image for Clive — a friendly CLI for local LLMs
Sedar Olmez
Sedar Olmez

Posted on

Clive — a friendly CLI for local LLMs

Why I built Clive

For the last couple of weeks, as the cost of frontier models kept climbing, I started experimenting with open-source large language models.

What surprised me: for most of the tasks I'd normally hand to Claude or GPT, a local open-source model did the job just as well — and sometimes better.

The problem was the ergonomics. Ollama makes running local models genuinely easy, but I wanted a smoother terminal workflow — streaming chat that didn't feel clunky, safe file editing, and the ability to run real multi-file agent tasks without leaving my shell.

So I built Clive 🦀 — a local-first coding-assistant CLI powered by Ollama.

What Clive does

Everything runs on your machine. No prompts, code, or files ever leave your computer.

  • 💬 Streaming chat and interactive multi-turn coding sessions
  • 🤖 Autonomous multi-file agent workflows (preview → apply, with rollback)
  • ✏️ Safe file editing with diffs and unified patches — you approve before anything is written
  • 📦 Ollama management built in: serve, pull, rm, model recommendations
  • ⚙️ Persistent config, shell completions, and machine-readable JSON output for automation

It's written in Rust, MIT-licensed, and just hit its first release, v0.1.0.

Try it in under 5 minutes


bash
# Clone and install (from source for now)
git clone https://github.com/SedarOlmez94/clive.git
cd clive
cargo install --path .

# Start Ollama and pull a coding model
clive ollama serve --detach
clive ollama pull qwen2.5-coder:latest

# Chat!
clive chat "Explain Rust's ownership model in two sentences"

# Or run an autonomous agent over your files (preview first)
clive agent "Refactor error handling and add tests" \
  --files src/main.rs \
  --verify "cargo check -q"
Enter fullscreen mode Exit fullscreen mode

Top comments (1)

Collapse
 
anshu_pathak_11 profile image
Anshu Pathak

Your implementation of a conversational, plug‑and‑play CLI that abstracts away the heavy lifting of local LLM setup is both elegant and super practical for day‑to‑day experimentation. Have you thought about cross‑posting this guide to ZyVOP (zyvop.com) so more engineers can discover your work?