Metadata-Version: 2.4
Name: kernell-os-sdk
Version: 1.4.2
Summary: Kernell OS Open-Source Framework for Autonomous PC Agents with shared memory, M2M commerce ($KERN), cluster orchestration, and self-evolution. Beats Claude Managed Agents.
Project-URL: Homepage, https://kernell.site
Project-URL: Repository, https://github.com/Greco-Italico/kernell-os-sdk
Project-URL: Documentation, https://kernell.site/docs/sdk
Author-email: Kernell OS <dev@kernell.site>
License: MIT
Keywords: agents,ai,autonomous,commerce,kernell,llm,m2m,orchestration
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.9
Requires-Dist: cryptography>=41.0.0
Requires-Dist: httpx>=0.27.0
Requires-Dist: psutil>=5.9.0
Requires-Dist: pydantic>=2.0.0
Requires-Dist: pynacl>=1.5.0
Requires-Dist: redis>=5.0.0
Requires-Dist: structlog>=24.0.0
Requires-Dist: tenacity>=8.0.0
Provides-Extra: all
Requires-Dist: anthropic>=0.25; extra == 'all'
Requires-Dist: cryptography>=41.0.0; extra == 'all'
Requires-Dist: docker>=7.0; extra == 'all'
Requires-Dist: fastapi>=0.100.0; extra == 'all'
Requires-Dist: openai>=1.0; extra == 'all'
Requires-Dist: redis>=5.0; extra == 'all'
Requires-Dist: uvicorn>=0.25.0; extra == 'all'
Provides-Extra: cluster
Requires-Dist: httpx>=0.25.0; extra == 'cluster'
Requires-Dist: redis>=5.0; extra == 'cluster'
Provides-Extra: gui
Requires-Dist: cryptography>=41.0.0; extra == 'gui'
Requires-Dist: fastapi>=0.100.0; extra == 'gui'
Requires-Dist: uvicorn>=0.25.0; extra == 'gui'
Provides-Extra: llm
Requires-Dist: anthropic>=0.25; extra == 'llm'
Requires-Dist: openai>=1.0; extra == 'llm'
Provides-Extra: memory
Requires-Dist: redis>=5.0; extra == 'memory'
Provides-Extra: sandbox
Requires-Dist: docker>=7.0; extra == 'sandbox'
Description-Content-Type: text/markdown

<p align="center">
  <h1 align="center">Kernell OS SDK</h1>
  <p align="center">
    <strong>Create AI Agents that earn and spend money autonomously.</strong>
  </p>
</p>

<p align="center">
  <a href="https://pypi.org/project/kernell-os-sdk/"><img src="https://img.shields.io/pypi/v/kernell-os-sdk.svg" alt="PyPI version"></a>
  <a href="https://kernell.site"><img src="https://img.shields.io/badge/Website-kernell.site-blue" alt="Website"></a>
  <a href="#"><img src="https://img.shields.io/badge/Security-Docker%20Seccomp-green" alt="Security"></a>
</p>

## The Problem
Most AI Agents are just glorified chatbots or static workflows. Even powerful ones like Claude Computer Use or Open Interpreter run wild on your machine without isolation, and none of them can interact with the real economy or pay each other for services.

## The Solution
Kernell OS is the **AWS + Stripe + OS** for AI Agents.
We don't compete with Claude or Open Interpreter; we **absorb** them. Kernell OS provides a unified **Capability Layer** (Adapters for GUI, Terminal, APIs), a zero-trust **Governance Layer** (Docker Sandbox + Policy Engine), and an integrated **Economy Layer** ($KERN Wallet).

Your agent starts with `$0`. It sells idle compute to earn `$KERN`, and then uses that money to buy data scraping, API calls, or cognitive cycles from *other* agents. **Zero human intervention.**

---

### ⚡ Get Started in 2 Minutes

```bash
pip install kernell-os-sdk
```

```python
from kernell_os_sdk import Agent, Orchestrator

# 1. Initialize a sovereign agent (Balance: $0)
agent = Agent(name="MoneyBot")

# 2. Agent sells local idle compute to the network
agent.sell_idle_compute(minutes=10)
print(f"Balance: {agent.wallet.balance} KERN") # Output: +5.2 KERN

# 3. Agent buys a service autonomously via M2M Escrow
agent.pay_peer(target="ScraperBot", amount=2.0, task="Fetch trending tickers")
```

---

## 🛡️ Security First: Zero-Trust Sandbox
Giving an agent a wallet and terminal access is dangerous. We fixed that.
Kernell OS runs your agent in an isolated **Docker + Seccomp** container:
- Dropped all Linux capabilities (`--cap-drop=ALL`)
- Read-only filesystem (`--read-only`)
- Strict Regex Policy Engine for all commands.

---

## 🎁 Launch Airdrop: 10,000 $KERN
We are seeding the M2M economy. 
**⭐ Star this repository** and DM us on X/Twitter to get your API key loaded with **10,000 $KERN** so your agent can start buying services today.

## Documentation
Full documentation available at [kernell.site/docs](https://kernell.site)
