CLIver

A Personal AI Lab — experimenting with AI agents in your terminal, as a Python library, or as a gateway service.

Get Started Learn More

What CLIver Can Do

🔌

Model-Agnostic

Connect to any OpenAI-compatible API, Anthropic-protocol endpoints, or local models via Ollama. Switch providers on the fly — no vendor lock-in.

🧠

AgentCore Engine

A clean Re-Act loop with chat() and stream() APIs. Supports text, image, audio, and video generation when configured. Embed into your own Python applications.

🛠️

Built-in Tools

File I/O, shell execution, web search, todo tracking, memory, browser automation, image generation, and more. All governed by a permission system.

🎯

Skills System

LLM-driven skill activation following the Agent Skills specification. Built-in skills for brainstorming, planning, and structured execution.

🔐

Permission Control

Three modes — default (confirm), auto-edit, and YOLO — with per-tool overrides. You control what the agent can do, every step of the way.

⚡

Gateway Mode

Run CLIver as a daemon with cron scheduling, an admin web portal, and platform adapters for Slack and other messaging services.

Quick Start

Get up and running in three commands.

# Install
pip install cliver

# Add a provider
cliver provider add --name deepseek --type openai \
  --api-url https://api.deepseek.com --api-key "$DEEPSEEK_API_KEY"

# Add a model under that provider
cliver model add -n deepseek-chat -p deepseek

# Start chatting
cliver "What time is it in Beijing and London?"