A coding agent for the models you run yourself

OpenCLI reads your code, runs your commands and edits your files — through any OpenAI-compatible API. A hosted provider, your own gateway, or a model on the machine in front of you. It ships with no accounts and no keys.

Download Install the CLI

What it is

The same agent in three shapes: a terminal program, a desktop app, and a local web UI. All three run on your machine and talk to whichever model you point them at.

Bring your own model

Ollama, LM Studio, vLLM, llama.cpp, or any hosted endpoint that speaks the OpenAI API. Declare it in one config file and it appears in the picker.

Nothing phones home

No built-in gateway, no telemetry account, no key baked into the binary. What it talks to is what you configured.

It asks before it acts

Commands and file writes are shown before they run, with a sandbox underneath. You choose how much it may do unattended.

Projects, memory, schedules

Group work by directory with standing instructions, keep facts across conversations, and put a recurring prompt on a timer.

The CLI

One binary. macOS and Linux:

curl -fsSL https://opencli.ai/install.sh | sh

Or with npm, on any platform Node runs on:

npm install -g @ai-dashboad/opencli

Then point it at a model. A local Ollama, for example, needs nothing but this in ~/.opencli/config.toml:

[model_providers.ollama]
name = "Ollama"
base_url = "http://localhost:11434/v1"
wire_api = "chat"

[[models]]
slug = "qwen3-coder"
model = "qwen3-coder:30b"
provider = "ollama"
context_window = 32768

How it compares

	OpenCLI	Hosted agents
Where the model runs	Wherever you point it, including your own hardware	The vendor's servers
Where your code goes	To the endpoint you configured, and nowhere else	To the vendor
Cost	Free; you pay for inference, or nothing if it is local	Per seat or per token
Works offline	Yes, with a local model	No

One thing worth saying plainly: a small local model is not as good at this as a frontier one. The interface is the same; the reasoning is not. OpenCLI is built so that choice is yours to make per task, not made for you.