halyn 0.3.0__tar.gz → 0.3.1__tar.gz

halyn-0.3.1/PKG-INFO

@@ -0,0 +1,178 @@
+Metadata-Version: 2.4
+Name: halyn
+Version: 0.3.1
+Summary: Halyn — NRP control plane with domain-scoped authorization.
+Author-email: Elmadani SALKA <contact@halyn.dev>
+License: MIT
+Project-URL: Homepage, https://github.com/ElmadaniS/halyn
+Project-URL: Repository, https://github.com/ElmadaniS/halyn
+Project-URL: Issues, https://github.com/ElmadaniS/halyn/issues
+Keywords: ai,browser,robotics,iot,mcp,nrp,llm,infrastructure,devops
+Classifier: Development Status :: 3 - Alpha
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: System :: Systems Administration
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: nrprotocol>=0.1.0
+Requires-Dist: aiohttp>=3.9
+Provides-Extra: enterprise
+Requires-Dist: grpcio>=1.60; extra == "enterprise"
+Requires-Dist: psycopg2-binary; extra == "enterprise"
+Requires-Dist: redis; extra == "enterprise"
+Provides-Extra: robotics
+Requires-Dist: rclpy; extra == "robotics"
+Requires-Dist: unitree-sdk2py; extra == "robotics"
+Provides-Extra: iot
+Requires-Dist: paho-mqtt; extra == "iot"
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-asyncio; extra == "dev"
+Requires-Dist: mypy; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+Dynamic: license-file
+
+<div align="center">
+
+# Halyn
+
+**Connect any device to any AI.**
+
+[![PyPI](https://img.shields.io/pypi/v/halyn?style=flat-square&color=0a6e3f)](https://pypi.org/project/halyn/)
+[![License](https://img.shields.io/badge/license-MIT-0a6e3f?style=flat-square)](LICENSE)
+[![Python](https://img.shields.io/badge/python-3.10+-0a6e3f?style=flat-square)](https://pypi.org/project/halyn/)
+
+MCP Server · 12 drivers · Shield rules · Audit chain · 5 autonomy levels
+
+[Website](https://halyn.dev) · [Quickstart](#quickstart) · [MCP Server](#mcp-server) · [Tutorials](https://halyn.dev#tutorials)
+
+</div>
+
+---
+
+## The Problem
+
+MCP connects AI to software. But AI is entering the physical world — robots, drones, factories, farms, hospitals. There's no universal standard for how AI safely controls hardware.
+
+**Halyn connects AI to everything else.** Servers, sensors, robots, industrial machines, smart homes — with safety rules the AI cannot break.
+
+## Quickstart
+
+```bash
+pip install halyn
+```
+
+```python
+from halyn import ControlPlane, SSHDriver
+
+cp = ControlPlane()
+cp.connect(SSHDriver("192.168.1.10", "admin"))
+
+# Safety rules — the AI physically cannot bypass these
+cp.shield("deny * delete *")
+cp.shield("deny * write /etc/*")
+
+# Observe
+state = cp.observe()
+print(state)  # {"cpu": 23.4, "mem": 67.2, ...}
+
+# Act (within shield rules)
+cp.act("restart nginx")     # ✓ allowed
+cp.act("rm -rf /etc")       # ✗ blocked by shield
+```
+
+## MCP Server
+
+Connect Claude.ai, ChatGPT, Cursor, or any MCP client directly to your devices:
+
+```bash
+# Start the MCP Server
+halyn-mcp --port 8935
+
+# In Claude.ai → Settings → MCP → Add Server
+# URL: http://your-server:8935/mcp
+```
+
+Then just talk:
+- *"Show me the status of all connected devices"*
+- *"What's the temperature in the greenhouse?"*
+- *"Restart nginx on server-01"*
+- *"Show me the audit trail"*
+
+The AI sees your devices as tools. Shield rules still apply. Every action is audited.
+
+## 12 Drivers
+
+| Driver | Target | Protocol |
+|--------|--------|----------|
+| `SSHDriver` | Linux/Mac servers | SSH |
+| `HTTPDriver` | REST APIs, webhooks | HTTP |
+| `WebSocketDriver` | Real-time streams | WebSocket |
+| `SerialDriver` | Arduino, Pi, PLCs | Serial |
+| `MQTTDriver` | IoT sensors | MQTT |
+| `OPCUADriver` | Industrial machines | OPC-UA |
+| `ROS2Driver` | Robots, drones | ROS2/DDS |
+| `DDSDriver` | Real-time systems | DDS |
+| `DockerDriver` | Containers | Docker API |
+| `BrowserDriver` | Web automation | Chrome CDP |
+| `UnitreeDriver` | Unitree robots | UDP |
+| `SocketDriver` | Raw TCP/UDP | Socket |
+
+## Safety
+
+**Shield Rules** — Constraints enforced at protocol level. The AI has no power to override them.
+
+```python
+cp.shield("deny * delete *")                    # no deletions
+cp.shield("deny * write temperature > 180")     # thermal limit
+cp.shield("deny lock unlock between 23:00-06:00")  # doors locked at night
+```
+
+**Audit Chain** — Every action recorded in SHA-256 hash chain. Tamper-evident. Append-only.
+
+**Consent Protocol** — Devices and AI negotiate permissions before any interaction.
+
+**5 Autonomy Levels** — From fully manual to fully autonomous. You choose.
+
+| Level | Name | Who Decides |
+|-------|------|-------------|
+| 0 | Manual | Human does everything |
+| 1 | Advisory | AI suggests, human acts |
+| 2 | Supervised | AI acts, human approves |
+| 3 | Monitored | AI acts freely, human watches |
+| 4 | Autonomous | AI decides within shield rules |
+
+## Works with Every LLM
+
+```python
+# Claude
+import anthropic
+client = anthropic.Anthropic()
+response = client.messages.create(model="claude-sonnet-4-6", ...)
+cp.act(response.content[0].text)
+
+# GPT
+from openai import OpenAI
+client = OpenAI()
+response = client.chat.completions.create(model="gpt-5", ...)
+
+# Local (Ollama — no internet needed)
+import ollama
+response = ollama.chat(model="llama4", ...)
+
+# All use the same shield rules. Same audit chain.
+```
+
+## Built on NRP
+
+Halyn implements [NRP (Node Reach Protocol)](https://nrprotocol.dev) — the open standard for AI-to-device communication. 6 primitives: Manifest, Observe, Act, Shield, Audit, Consent.
+
+## Free. Open Source. Forever.
+
+MIT licensed. Use it for anything. Modify it. Build a company on it. No fees, no limits, no lock-in.
+
+---
+
+[halyn.dev](https://halyn.dev) · [nrprotocol.dev](https://nrprotocol.dev) · [PyPI](https://pypi.org/project/halyn/) · [contact@halyn.dev](mailto:contact@halyn.dev)

halyn-0.3.1/README.md

@@ -0,0 +1,142 @@
+<div align="center">
+
+# Halyn
+
+**Connect any device to any AI.**
+
+[![PyPI](https://img.shields.io/pypi/v/halyn?style=flat-square&color=0a6e3f)](https://pypi.org/project/halyn/)
+[![License](https://img.shields.io/badge/license-MIT-0a6e3f?style=flat-square)](LICENSE)
+[![Python](https://img.shields.io/badge/python-3.10+-0a6e3f?style=flat-square)](https://pypi.org/project/halyn/)
+
+MCP Server · 12 drivers · Shield rules · Audit chain · 5 autonomy levels
+
+[Website](https://halyn.dev) · [Quickstart](#quickstart) · [MCP Server](#mcp-server) · [Tutorials](https://halyn.dev#tutorials)
+
+</div>
+
+---
+
+## The Problem
+
+MCP connects AI to software. But AI is entering the physical world — robots, drones, factories, farms, hospitals. There's no universal standard for how AI safely controls hardware.
+
+**Halyn connects AI to everything else.** Servers, sensors, robots, industrial machines, smart homes — with safety rules the AI cannot break.
+
+## Quickstart
+
+```bash
+pip install halyn
+```
+
+```python
+from halyn import ControlPlane, SSHDriver
+
+cp = ControlPlane()
+cp.connect(SSHDriver("192.168.1.10", "admin"))
+
+# Safety rules — the AI physically cannot bypass these
+cp.shield("deny * delete *")
+cp.shield("deny * write /etc/*")
+
+# Observe
+state = cp.observe()
+print(state)  # {"cpu": 23.4, "mem": 67.2, ...}
+
+# Act (within shield rules)
+cp.act("restart nginx")     # ✓ allowed
+cp.act("rm -rf /etc")       # ✗ blocked by shield
+```
+
+## MCP Server
+
+Connect Claude.ai, ChatGPT, Cursor, or any MCP client directly to your devices:
+
+```bash
+# Start the MCP Server
+halyn-mcp --port 8935
+
+# In Claude.ai → Settings → MCP → Add Server
+# URL: http://your-server:8935/mcp
+```
+
+Then just talk:
+- *"Show me the status of all connected devices"*
+- *"What's the temperature in the greenhouse?"*
+- *"Restart nginx on server-01"*
+- *"Show me the audit trail"*
+
+The AI sees your devices as tools. Shield rules still apply. Every action is audited.
+
+## 12 Drivers
+
+| Driver | Target | Protocol |
+|--------|--------|----------|
+| `SSHDriver` | Linux/Mac servers | SSH |
+| `HTTPDriver` | REST APIs, webhooks | HTTP |
+| `WebSocketDriver` | Real-time streams | WebSocket |
+| `SerialDriver` | Arduino, Pi, PLCs | Serial |
+| `MQTTDriver` | IoT sensors | MQTT |
+| `OPCUADriver` | Industrial machines | OPC-UA |
+| `ROS2Driver` | Robots, drones | ROS2/DDS |
+| `DDSDriver` | Real-time systems | DDS |
+| `DockerDriver` | Containers | Docker API |
+| `BrowserDriver` | Web automation | Chrome CDP |
+| `UnitreeDriver` | Unitree robots | UDP |
+| `SocketDriver` | Raw TCP/UDP | Socket |
+
+## Safety
+
+**Shield Rules** — Constraints enforced at protocol level. The AI has no power to override them.
+
+```python
+cp.shield("deny * delete *")                    # no deletions
+cp.shield("deny * write temperature > 180")     # thermal limit
+cp.shield("deny lock unlock between 23:00-06:00")  # doors locked at night
+```
+
+**Audit Chain** — Every action recorded in SHA-256 hash chain. Tamper-evident. Append-only.
+
+**Consent Protocol** — Devices and AI negotiate permissions before any interaction.
+
+**5 Autonomy Levels** — From fully manual to fully autonomous. You choose.
+
+| Level | Name | Who Decides |
+|-------|------|-------------|
+| 0 | Manual | Human does everything |
+| 1 | Advisory | AI suggests, human acts |
+| 2 | Supervised | AI acts, human approves |
+| 3 | Monitored | AI acts freely, human watches |
+| 4 | Autonomous | AI decides within shield rules |
+
+## Works with Every LLM
+
+```python
+# Claude
+import anthropic
+client = anthropic.Anthropic()
+response = client.messages.create(model="claude-sonnet-4-6", ...)
+cp.act(response.content[0].text)
+
+# GPT
+from openai import OpenAI
+client = OpenAI()
+response = client.chat.completions.create(model="gpt-5", ...)
+
+# Local (Ollama — no internet needed)
+import ollama
+response = ollama.chat(model="llama4", ...)
+
+# All use the same shield rules. Same audit chain.
+```
+
+## Built on NRP
+
+Halyn implements [NRP (Node Reach Protocol)](https://nrprotocol.dev) — the open standard for AI-to-device communication. 6 primitives: Manifest, Observe, Act, Shield, Audit, Consent.
+
+## Free. Open Source. Forever.
+
+MIT licensed. Use it for anything. Modify it. Build a company on it. No fees, no limits, no lock-in.
+
+---
+
+[halyn.dev](https://halyn.dev) · [nrprotocol.dev](https://nrprotocol.dev) · [PyPI](https://pypi.org/project/halyn/) · [contact@halyn.dev](mailto:contact@halyn.dev)

{halyn-0.3.0 → halyn-0.3.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "halyn"
-version = "0.3.0"
+version = "0.3.1"
 description = "Halyn — NRP control plane with domain-scoped authorization."
 requires-python = ">=3.10"
 license = {text = "MIT"}

{halyn-0.3.0 → halyn-0.3.1}/src/halyn/mcp_serve.py

@@ -41,7 +41,7 @@ except ImportError:
 
 SERVER_INFO = {
     "name": "halyn",
-    "version": "0.3.0",
+    "version": "0.3.1",
 }
 
 PROTOCOL_VERSION = "2024-11-05"
@@ -195,7 +195,7 @@ class HalynMCPServer:
             # Check action match
             if action == "*" or action in cmd_lower:
                 condition = " ".join(parts[3:]) if len(parts) > 3 else ""
-                if not condition or condition in cmd_lower:
+                if not condition or condition == "*" or condition in cmd_lower:
                     return f"Shield rule: {rule}"
         return None
 

halyn-0.3.1/src/halyn.egg-info/PKG-INFO

@@ -0,0 +1,178 @@
+Metadata-Version: 2.4
+Name: halyn
+Version: 0.3.1
+Summary: Halyn — NRP control plane with domain-scoped authorization.
+Author-email: Elmadani SALKA <contact@halyn.dev>
+License: MIT
+Project-URL: Homepage, https://github.com/ElmadaniS/halyn
+Project-URL: Repository, https://github.com/ElmadaniS/halyn
+Project-URL: Issues, https://github.com/ElmadaniS/halyn/issues
+Keywords: ai,browser,robotics,iot,mcp,nrp,llm,infrastructure,devops
+Classifier: Development Status :: 3 - Alpha
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: System :: Systems Administration
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: nrprotocol>=0.1.0
+Requires-Dist: aiohttp>=3.9
+Provides-Extra: enterprise
+Requires-Dist: grpcio>=1.60; extra == "enterprise"
+Requires-Dist: psycopg2-binary; extra == "enterprise"
+Requires-Dist: redis; extra == "enterprise"
+Provides-Extra: robotics
+Requires-Dist: rclpy; extra == "robotics"
+Requires-Dist: unitree-sdk2py; extra == "robotics"
+Provides-Extra: iot
+Requires-Dist: paho-mqtt; extra == "iot"
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-asyncio; extra == "dev"
+Requires-Dist: mypy; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+Dynamic: license-file
+
+<div align="center">
+
+# Halyn
+
+**Connect any device to any AI.**
+
+[![PyPI](https://img.shields.io/pypi/v/halyn?style=flat-square&color=0a6e3f)](https://pypi.org/project/halyn/)
+[![License](https://img.shields.io/badge/license-MIT-0a6e3f?style=flat-square)](LICENSE)
+[![Python](https://img.shields.io/badge/python-3.10+-0a6e3f?style=flat-square)](https://pypi.org/project/halyn/)
+
+MCP Server · 12 drivers · Shield rules · Audit chain · 5 autonomy levels
+
+[Website](https://halyn.dev) · [Quickstart](#quickstart) · [MCP Server](#mcp-server) · [Tutorials](https://halyn.dev#tutorials)
+
+</div>
+
+---
+
+## The Problem
+
+MCP connects AI to software. But AI is entering the physical world — robots, drones, factories, farms, hospitals. There's no universal standard for how AI safely controls hardware.
+
+**Halyn connects AI to everything else.** Servers, sensors, robots, industrial machines, smart homes — with safety rules the AI cannot break.
+
+## Quickstart
+
+```bash
+pip install halyn
+```
+
+```python
+from halyn import ControlPlane, SSHDriver
+
+cp = ControlPlane()
+cp.connect(SSHDriver("192.168.1.10", "admin"))
+
+# Safety rules — the AI physically cannot bypass these
+cp.shield("deny * delete *")
+cp.shield("deny * write /etc/*")
+
+# Observe
+state = cp.observe()
+print(state)  # {"cpu": 23.4, "mem": 67.2, ...}
+
+# Act (within shield rules)
+cp.act("restart nginx")     # ✓ allowed
+cp.act("rm -rf /etc")       # ✗ blocked by shield
+```
+
+## MCP Server
+
+Connect Claude.ai, ChatGPT, Cursor, or any MCP client directly to your devices:
+
+```bash
+# Start the MCP Server
+halyn-mcp --port 8935
+
+# In Claude.ai → Settings → MCP → Add Server
+# URL: http://your-server:8935/mcp
+```
+
+Then just talk:
+- *"Show me the status of all connected devices"*
+- *"What's the temperature in the greenhouse?"*
+- *"Restart nginx on server-01"*
+- *"Show me the audit trail"*
+
+The AI sees your devices as tools. Shield rules still apply. Every action is audited.
+
+## 12 Drivers
+
+| Driver | Target | Protocol |
+|--------|--------|----------|
+| `SSHDriver` | Linux/Mac servers | SSH |
+| `HTTPDriver` | REST APIs, webhooks | HTTP |
+| `WebSocketDriver` | Real-time streams | WebSocket |
+| `SerialDriver` | Arduino, Pi, PLCs | Serial |
+| `MQTTDriver` | IoT sensors | MQTT |
+| `OPCUADriver` | Industrial machines | OPC-UA |
+| `ROS2Driver` | Robots, drones | ROS2/DDS |
+| `DDSDriver` | Real-time systems | DDS |
+| `DockerDriver` | Containers | Docker API |
+| `BrowserDriver` | Web automation | Chrome CDP |
+| `UnitreeDriver` | Unitree robots | UDP |
+| `SocketDriver` | Raw TCP/UDP | Socket |
+
+## Safety
+
+**Shield Rules** — Constraints enforced at protocol level. The AI has no power to override them.
+
+```python
+cp.shield("deny * delete *")                    # no deletions
+cp.shield("deny * write temperature > 180")     # thermal limit
+cp.shield("deny lock unlock between 23:00-06:00")  # doors locked at night
+```
+
+**Audit Chain** — Every action recorded in SHA-256 hash chain. Tamper-evident. Append-only.
+
+**Consent Protocol** — Devices and AI negotiate permissions before any interaction.
+
+**5 Autonomy Levels** — From fully manual to fully autonomous. You choose.
+
+| Level | Name | Who Decides |
+|-------|------|-------------|
+| 0 | Manual | Human does everything |
+| 1 | Advisory | AI suggests, human acts |
+| 2 | Supervised | AI acts, human approves |
+| 3 | Monitored | AI acts freely, human watches |
+| 4 | Autonomous | AI decides within shield rules |
+
+## Works with Every LLM
+
+```python
+# Claude
+import anthropic
+client = anthropic.Anthropic()
+response = client.messages.create(model="claude-sonnet-4-6", ...)
+cp.act(response.content[0].text)
+
+# GPT
+from openai import OpenAI
+client = OpenAI()
+response = client.chat.completions.create(model="gpt-5", ...)
+
+# Local (Ollama — no internet needed)
+import ollama
+response = ollama.chat(model="llama4", ...)
+
+# All use the same shield rules. Same audit chain.
+```
+
+## Built on NRP
+
+Halyn implements [NRP (Node Reach Protocol)](https://nrprotocol.dev) — the open standard for AI-to-device communication. 6 primitives: Manifest, Observe, Act, Shield, Audit, Consent.
+
+## Free. Open Source. Forever.
+
+MIT licensed. Use it for anything. Modify it. Build a company on it. No fees, no limits, no lock-in.
+
+---
+
+[halyn.dev](https://halyn.dev) · [nrprotocol.dev](https://nrprotocol.dev) · [PyPI](https://pypi.org/project/halyn/) · [contact@halyn.dev](mailto:contact@halyn.dev)