warpos 0.1.0

The open-source platform for AI agents. Write logic, deploy everything.

 ██╗    ██╗ █████╗ ██████╗ ██████╗  ██████╗ ███████╗
 ██║    ██║██╔══██╗██╔══██╗██╔══██╗██╔═══██╗██╔════╝
 ██║ █╗ ██║███████║██████╔╝██████╔╝██║   ██║███████╗
 ██║███╗██║██╔══██║██╔══██╗██╔══██╗██║   ██║╚════██║
 ╚███╔███╔╝██║  ██║██║  ██║██████╔╝╚██████╔╝███████║
  ╚══╝╚══╝ ╚═╝  ╚═╝╚═╝  ╚═╝╚═════╝  ╚═════╝ ╚══════╝
  

The open-source platform for AI agents.
Write logic, deploy everything.

Website · GitHub · PyPI

---

What is WarpOS?

WarpOS is a lightweight framework for building AI agents that actually work in production. It handles the messy parts — provider routing, tool orchestration, memory management, and server deployment — so you can focus on writing agent logic. Ship a working agent in minutes, not days.

from warpos import Agent, tool

@tool
def get_weather(city: str) -> str:
    """Get the current weather for a city."""
    return f"Sunny, 72°F in {city}"

agent = Agent(
    name="WeatherBot",
    model="gpt-4o",
    tools=[get_weather],
    instructions="You are a helpful weather assistant."
)

response = agent.run("What's the weather in San Francisco?")
print(response)

⚡ Quick Start

pip install warpos

Set your API key:

export OPENAI_API_KEY=sk-...

Run your first agent:

from warpos import Agent

agent = Agent(name="MyAgent", model="gpt-4o")
print(agent.run("Hello! What can you do?"))

🚀 Features

• Multi-provider support — OpenAI, Anthropic, Groq, DeepSeek, Ollama, Cerebras, and more
• Tool calling — Decorate any Python function as a tool with @tool
• Memory — Built-in conversation memory with persistent storage options
• CLI — warp init scaffolds a project, warp serve starts an API server
• Streaming — Real-time token streaming for all providers
• Type-safe — Full type hints and Pydantic model support
• Lightweight — Minimal dependencies, fast startup, production-ready

🔌 Providers

WarpOS supports multiple LLM providers out of the box. Swap providers with one line:

Provider	Models	Streaming	Tool Calling
OpenAI	GPT-4o, GPT-4, GPT-3.5	✅	✅
Anthropic	Claude 3.5 Sonnet, Claude 3 Opus	✅	✅
Groq	Llama 3, Mixtral	✅	✅
DeepSeek	DeepSeek-V2, DeepSeek Coder	✅	✅
Ollama	Llama 3, Mistral, any local model	✅	✅
Cerebras	Llama 3, custom models	✅	✅

# Switch providers easily
agent = Agent(name="Bot", model="anthropic/claude-3-5-sonnet-20241022")
agent = Agent(name="Bot", model="groq/llama3-70b-8192")
agent = Agent(name="Bot", model="ollama/llama3")

🖥️ CLI

WarpOS includes a CLI for scaffolding and running agents:

# Create a new project
warp init my-agent

# Start the development server
warp serve

# Run with hot reload
warp serve --reload

🏗️ Architecture

WarpOS is built around five core components:

• Agent — The orchestrator. Takes instructions, manages context, calls tools, returns responses.
• Tools — Python functions exposed to the agent via the @tool decorator. Type-hinted, self-documenting.
• Memory — Conversation history and long-term storage. Pluggable backends (in-memory, SQLite, Redis).
• Provider — Abstraction layer over LLM APIs. Handles routing, retries, rate limits, and streaming.
• Server — HTTP server with REST API and WebSocket support for real-time agent interactions.

┌─────────────────────────────────────────────┐
│                   Agent                      │
│  ┌──────────┐  ┌──────────┐  ┌──────────┐  │
│  │  Memory   │  │  Tools   │  │ Provider │  │
│  └──────────┘  └──────────┘  └──────────┘  │
└─────────────────────────────────────────────┘
                      │
               ┌──────┴──────┐
               │   Server    │
               └─────────────┘

📖 Examples

Check out the examples/ directory:

• Advanced Agent — Multiple tools, custom provider, memory
• Discord Bot — Build a Discord bot with WarpOS
• Telegram Bot — Build a Telegram bot with WarpOS

🤝 Contributing

We welcome contributions of all kinds. See CONTRIBUTING.md for setup instructions, coding standards, and how to submit a PR.

git clone https://github.com/warp-os/warpos.git
cd warpos
pip install -e ".[dev]"
pytest

📄 License

WarpOS is released under the MIT License.

⭐ Star History

If you find WarpOS useful, consider giving it a star on GitHub!