DeepCLI

Run, chat, and control LLM agents from one powerful command-line tool

Installation

Download DeepCLI from GitHub Releases, then unzip and add the folder to your PATH.

Download from GitHub Releases
1
Download and unzip

Click the button above to open GitHub Releases, download the Windows build (e.g. deepcli-x.x.x-x86_64-pc-windows-msvc.zip), and unzip it to a folder (e.g. C:\deepcli).

2
Add the folder to PATH (Windows)

Add the unzipped folder to your PATH using environment variables so you can run deepcli from any terminal:

  • Press Win + R, type sysdm.cpl, press Enter.
  • Open the Advanced tab → Environment Variables.
  • Under User variables (or System), select Path → Edit.
  • Click New and add the full path to the folder (e.g. C:\deepcli).
  • Click OK to close all dialogs. Open a new terminal for the change to apply.

Or via Command Prompt (run as Administrator if needed):

setx PATH "%PATH%;C:\deepcli"

Replace C:\deepcli with the path where you unzipped DeepCLI.

3
Verify installation

Open a new terminal and run: 

deepcli --version

Setup

Run deepcli init once to configure DeepCLI. You'll be prompted for:

  • API key — Get one at openrouter.ai/keys. Copy it and press Enter at the prompt to use clipboard if paste doesn't work.
  • Model — Pick from the list or type a custom model name.
  • Agent name — Name your first agent (e.g., assistant).
deepcli init

Core Commands

deepcli init Set up DeepCLI (API key, model, first agent). Run this first.
deepcli chat [agent] [--project NAME] Interactive chat with an agent. Use --project to save chat history and context.
deepcli multichat [--count N] [--project NAME] Split-screen chat with multiple agents. Use --project <name> to load and save chat history. Tab to switch lanes, Enter to send.
deepcli ask <agent> "<message>" Send a single message and print the response.
deepcli model Interactively change the model for an agent.

Agent Commands

deepcli agent new Create a new agent interactively (prompts for name, model, workdir).
deepcli agent create <name> [--model M] [--workdir W] [--prompt P] Create a new agent with arguments.
deepcli agent set <name> [--model M] [--workdir W] [--prompt P] Update an existing agent.
deepcli agent remove <name> Remove an agent.
deepcli agent list List all agents.
deepcli agent show <name> Show agent details.

Projects

Projects allow you to maintain chat history and context across multiple sessions. When you create a project, all conversations are saved automatically, letting you reference previous discussions with AI.

deepcli project new Create a new project interactively (prompts for name, description, agent).
deepcli project create <name> Create a new project with a name.
deepcli project list List all projects.
deepcli project show <name> Show project details and chat history count.
deepcli project remove <name> Remove a project (also deletes chat history).

Using Projects

Start a project-based chat session:

deepcli chat --project my-project

This will:

  • Load previous chat history from the project
  • Save all new messages to the project's history
  • Allow the AI to reference earlier conversations in the same project

Regular chat (without --project) doesn't save history and starts fresh each time.

Multichat

Multichat opens a split-screen terminal where each agent has its own lane. Perfect for comparing outputs or brainstorming with multiple AI perspectives simultaneously.

Project mode

Use --project <name> (or -p <name>) to attach multichat to a project. You must provide the project name; --project alone is invalid.

  • Chat history for the project is loaded into all agent lanes at start.
  • Conversations are saved to the project for use in future sessions.

Keyboard Shortcuts

  • Tab — Switch to next agent lane
  • Shift+Tab — Switch to previous agent lane
  • Enter — Send message to the focused agent
  • ↑↓ — Scroll chat history
  • Esc — Quit

You can switch tabs while an agent is generating a response. Type and send messages in other lanes while one is loading.

Examples

deepcli multichat
deepcli multichat --count 3
deepcli multichat --project my-project
deepcli multichat -p my-project --count 2