Metadata-Version: 2.4
Name: kernell-os
Version: 2.0.0b0
Summary: First public release of an agentic runtime for M2M coordination. Machines coordinate, verify, and settle value autonomously.
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 :: 4 - Beta
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==42.0.5
Requires-Dist: httpx==0.27.0
Requires-Dist: prometheus-client==0.20.0
Requires-Dist: psutil==5.9.8
Requires-Dist: pydantic==2.9.2
Requires-Dist: redis==5.0.3
Requires-Dist: structlog==24.1.0
Requires-Dist: tenacity==8.2.3
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'
Provides-Extra: test
Requires-Dist: coverage>=7.4.0; extra == 'test'
Requires-Dist: fakeredis[lua]>=2.20.0; extra == 'test'
Requires-Dist: freezegun>=1.4.0; extra == 'test'
Requires-Dist: httpx>=0.27.0; extra == 'test'
Requires-Dist: hypothesis>=6.0.0; extra == 'test'
Requires-Dist: prometheus-client>=0.20.0; extra == 'test'
Requires-Dist: pytest-asyncio>=0.23.0; extra == 'test'
Requires-Dist: pytest-cov>=4.1.0; extra == 'test'
Requires-Dist: pytest-mock>=3.12.0; extra == 'test'
Requires-Dist: pytest>=8.0.0; extra == 'test'
Requires-Dist: responses>=0.25.0; extra == 'test'
Description-Content-Type: text/markdown

<div align="center">
  <img src="https://raw.githubusercontent.com/Greco-Italico/kernell-os-sdk/main/logo3d.png" alt="Kernell OS Logo" width="200" height="200">
  
  # Kernell OS
  ### Machines coordinate, verify, and settle value autonomously.

  <br>
  
  ![Kernell OS Demo](https://raw.githubusercontent.com/Greco-Italico/kernell-os-sdk/main/docs/assets/demo_60s.gif)

  <br>
</div>

Kernell OS is an agentic runtime where multiple AI systems collaborate, reuse accumulated knowledge, and transact value securely.

This is not another framework for LLM wrappers. This is **infrastructure for autonomous machine-to-machine economies**.

---

## The Landscape

| System | Generates Code | Remembers Architecture | Coordinates Agents | Settles M2M Value |
| :--- | :---: | :---: | :---: | :---: |
| **Copilots** | ✅ | ❌ | ❌ | ❌ |
| **Agent Frameworks** | ✅ | ⚠️ | ⚠️ | ❌ |
| **Kernell OS** | ✅ | ✅ | ✅ | ✅ |

---

## How It Works

Kernell OS fundamentally shifts how LLMs interact with code, infrastructure, and economics:

1. 🔀 **Cognitive Router v2**: Evaluates tasks contextually. If an architecture is unknown, it routes to premium reasoning models (e.g., DeepSeek-V3). If the architecture is known, it routes to hyper-cheap local models ($0) to just write the glue code.
2. 🧠 **Semantic Memory Graph**: Doesn't cache strings. It learns and traverses architectural paths, reusing proven dependencies and pruning toxic routes via the **Dual Confidence Model**.
3. 🛡️ **Intent Firewall**: Untrusted AI execution is halted. Every action (syscalls, file writes, outbound requests) is sandbox-verified before touching the host system.
4. 💰 **Escrow Engine**: Agents are financially bound. Kernell holds execution value in cryptographic escrow, releasing funds ($KERN) only upon verified, monotonic success.

---

## Quickstart

Stop building prototypes. Boot your first agentic economy in seconds.

```bash
# 1. Install the runtime
pip install kernell-os

# 2. Scaffold a new environment
kernell init

# 3. Boot the execution engine, Memory Graph, and Gateway
kernell start

# 4. Run the 60-second interactive investor demo
kernell demo
```

---

## Expected Output

Upon running `kernell demo`, your browser will launch the **Control Plane Dashboard**. 

You will visually trace:
* 🟣 **Path Intelligence Hit**: The system bypassing generation and retrieving an entire architectural sub-graph.
* 🔴 **Firewall Freeze**: The system halting a malicious external dependency request for human-in-the-loop approval.
* 🟢 **Escrow Settlement**: The smart contract releasing $KERN funds upon successful test execution.

*(See the placeholder GIF at the top for reference)*

---

<div align="center">
  <br>
  <i>This is not a copilot.</i><br>
  <b>This is infrastructure for autonomous systems.</b>
</div>
