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