agentmesh-platform 1.0.0a1__tar.gz → 1.0.0a2__tar.gz

{agentmesh_platform-1.0.0a1 → agentmesh_platform-1.0.0a2}/.gitignore

@@ -84,3 +84,5 @@ secrets.json
 # Local config
 .agentmesh/
 config.local.yaml
+
+node_modules/

{agentmesh_platform-1.0.0a1 → agentmesh_platform-1.0.0a2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentmesh-platform
-Version: 1.0.0a1
+Version: 1.0.0a2
 Summary: The Secure Nervous System for Cloud-Native Agent Ecosystems - Identity, Trust, Reward, Governance
 Project-URL: Homepage, https://github.com/imran-siddique/agent-mesh
 Project-URL: Documentation, https://github.com/imran-siddique/agent-mesh#readme
@@ -23,16 +23,28 @@ Classifier: Topic :: Security :: Cryptography
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Topic :: System :: Systems Administration :: Authentication/Directory
 Requires-Python: >=3.11
-Requires-Dist: agent-os-kernel[iatp,nexus]>=1.2.0
 Requires-Dist: aiohttp>=3.9.0
 Requires-Dist: click>=8.1.0
 Requires-Dist: cryptography>=42.0.0
 Requires-Dist: httpx>=0.26.0
-Requires-Dist: pydantic>=2.5.0
+Requires-Dist: pydantic[email]>=2.5.0
 Requires-Dist: pynacl>=1.5.0
 Requires-Dist: pyyaml>=6.0
 Requires-Dist: rich>=13.0.0
 Requires-Dist: structlog>=24.1.0
+Provides-Extra: agent-os
+Requires-Dist: agent-os-kernel[iatp,nexus]>=1.2.0; extra == 'agent-os'
+Provides-Extra: all
+Requires-Dist: asyncpg>=0.29.0; extra == 'all'
+Requires-Dist: fastapi>=0.109.0; extra == 'all'
+Requires-Dist: opentelemetry-api>=1.20.0; extra == 'all'
+Requires-Dist: opentelemetry-exporter-otlp>=1.20.0; extra == 'all'
+Requires-Dist: opentelemetry-instrumentation-fastapi>=0.41b0; extra == 'all'
+Requires-Dist: opentelemetry-sdk>=1.20.0; extra == 'all'
+Requires-Dist: prometheus-client>=0.19.0; extra == 'all'
+Requires-Dist: redis[asyncio]>=5.0.0; extra == 'all'
+Requires-Dist: sqlalchemy[asyncio]>=2.0.0; extra == 'all'
+Requires-Dist: uvicorn[standard]>=0.27.0; extra == 'all'
 Provides-Extra: dev
 Requires-Dist: black>=24.1.0; extra == 'dev'
 Requires-Dist: mypy>=1.8.0; extra == 'dev'
@@ -40,9 +52,19 @@ Requires-Dist: pytest-asyncio>=0.23.0; extra == 'dev'
 Requires-Dist: pytest-cov>=4.1.0; extra == 'dev'
 Requires-Dist: pytest>=7.4.0; extra == 'dev'
 Requires-Dist: ruff>=0.1.0; extra == 'dev'
+Provides-Extra: observability
+Requires-Dist: opentelemetry-api>=1.20.0; extra == 'observability'
+Requires-Dist: opentelemetry-exporter-otlp>=1.20.0; extra == 'observability'
+Requires-Dist: opentelemetry-instrumentation-fastapi>=0.41b0; extra == 'observability'
+Requires-Dist: opentelemetry-sdk>=1.20.0; extra == 'observability'
+Requires-Dist: prometheus-client>=0.19.0; extra == 'observability'
 Provides-Extra: server
 Requires-Dist: fastapi>=0.109.0; extra == 'server'
 Requires-Dist: uvicorn[standard]>=0.27.0; extra == 'server'
+Provides-Extra: storage
+Requires-Dist: asyncpg>=0.29.0; extra == 'storage'
+Requires-Dist: redis[asyncio]>=5.0.0; extra == 'storage'
+Requires-Dist: sqlalchemy[asyncio]>=2.0.0; extra == 'storage'
 Description-Content-Type: text/markdown
 
 # AgentMesh
@@ -51,8 +73,15 @@ Description-Content-Type: text/markdown
 
 *Identity · Trust · Reward · Governance*
 
+[![GitHub Stars](https://img.shields.io/github/stars/imran-siddique/agent-mesh?style=social)](https://github.com/imran-siddique/agent-mesh/stargazers)
+[![CI](https://github.com/imran-siddique/agent-mesh/actions/workflows/ci.yml/badge.svg)](https://github.com/imran-siddique/agent-mesh/actions/workflows/ci.yml)
 [![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](LICENSE)
 [![Python](https://img.shields.io/badge/python-3.11+-blue.svg)](https://python.org)
+[![Agent-OS Compatible](https://img.shields.io/badge/agent--os-compatible-green.svg)](https://github.com/imran-siddique/agent-os)
+
+> ⭐ **If this project helps you, please star it!** It helps others discover AgentMesh.
+
+> 🔗 **Part of the Agent Ecosystem** — Works seamlessly with [Agent-OS](https://github.com/imran-siddique/agent-os) for IATP trust protocol
 
 ---
 
@@ -102,10 +131,23 @@ AgentMesh provides:
 
 ## Quick Start
 
+### Option 1: Secure Claude Desktop (Recommended)
+
 ```bash
-# Install AgentMesh CLI
-pip install agentmesh
+# Install AgentMesh
+pip install agentmesh-platform
 
+# Set up Claude Desktop to use AgentMesh governance
+agentmesh init-integration --claude
+
+# Restart Claude Desktop - all MCP tools are now secured!
+```
+
+Claude will now route tool calls through AgentMesh for policy enforcement and trust scoring.
+
+### Option 2: Create a Governed Agent
+
+```bash
 # Initialize a governed agent in 30 seconds
 agentmesh init --name my-agent --sponsor alice@company.com
 
@@ -116,10 +158,29 @@ agentmesh register
 agentmesh run
 ```
 
+### Option 3: Wrap Any MCP Server
+
+```bash
+# Proxy any MCP server with governance
+agentmesh proxy --target npx --target -y \
+  --target @modelcontextprotocol/server-filesystem \
+  --target /path/to/directory
+
+# Use strict policy (blocks writes/deletes)
+agentmesh proxy --policy strict --target <your-mcp-server>
+```
+
 ## Installation
 
 ```bash
-pip install agentmesh
+pip install agentmesh-platform
+```
+
+Or install with extra dependencies:
+
+```bash
+pip install agentmesh-platform[server]  # FastAPI server
+pip install agentmesh-platform[dev]     # Development tools
 ```
 
 Or from source:
@@ -130,6 +191,71 @@ cd agent-mesh
 pip install -e .
 ```
 
+## Examples & Integrations
+
+**Real-world examples** to get started quickly:
+
+| Example | Use Case | Key Features |
+|---------|----------|--------------|
+| [MCP Tool Server](./examples/01-mcp-tool-server/) | Secure MCP server with governance | Rate limiting, output sanitization, audit logs |
+| [Multi-Agent Customer Service](./examples/02-customer-service/) | Customer support automation | Delegation chains, trust handshakes, A2A |
+| [Healthcare HIPAA](./examples/03-healthcare-hipaa/) | HIPAA-compliant data analysis | Compliance automation, PHI protection, Merkle audit |
+| [GitHub PR Review](./examples/05-github-integration/) | Code review agent | Output policies, shadow mode, trust decay |
+
+**Framework integrations:**
+- **[Claude Desktop](./docs/integrations/claude-desktop.md)** - Secure MCP tools with one command
+- [LangChain Integration](./examples/integrations/langchain.md) - Secure LangChain agents with policies
+- [CrewAI Integration](./examples/integrations/crewai.md) - Multi-agent crew governance
+
+📚 **[Browse all examples →](./examples/)**
+
+## The AgentMesh Proxy: "SSL for AI Agents"
+
+**Problem:** AI agents like Claude Desktop have unfettered access to your filesystem, database, and APIs through MCP servers. One hallucination could be catastrophic.
+
+**Solution:** AgentMesh acts as a transparent governance proxy:
+
+```bash
+# Before: Unsafe direct access
+{
+  "mcpServers": {
+    "filesystem": {
+      "command": "npx",
+      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/Users/me"]
+    }
+  }
+}
+
+# After: Protected by AgentMesh
+{
+  "mcpServers": {
+    "filesystem": {
+      "command": "agentmesh",
+      "args": [
+        "proxy", "--policy", "strict",
+        "--target", "npx", "--target", "-y",
+        "--target", "@modelcontextprotocol/server-filesystem",
+        "--target", "/Users/me"
+      ]
+    }
+  }
+}
+```
+
+**What you get:**
+- 🔒 **Policy Enforcement** - Block dangerous operations before they execute
+- 📊 **Trust Scoring** - Behavioral monitoring (800-1000 scale)  
+- 📝 **Audit Logs** - Tamper-evident record of every action
+- ✅ **Verification Footers** - Visual confirmation in outputs
+
+**Set it up in 10 seconds:**
+```bash
+agentmesh init-integration --claude
+# Restart Claude Desktop - done!
+```
+
+Learn more: **[Claude Desktop Integration Guide](./docs/integrations/claude-desktop.md)**
+
 ## Core Concepts
 
 ### 1. Agent Identity

{agentmesh_platform-1.0.0a1 → agentmesh_platform-1.0.0a2}/README.md

@@ -4,8 +4,15 @@
 
 *Identity · Trust · Reward · Governance*
 
+[![GitHub Stars](https://img.shields.io/github/stars/imran-siddique/agent-mesh?style=social)](https://github.com/imran-siddique/agent-mesh/stargazers)
+[![CI](https://github.com/imran-siddique/agent-mesh/actions/workflows/ci.yml/badge.svg)](https://github.com/imran-siddique/agent-mesh/actions/workflows/ci.yml)
 [![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](LICENSE)
 [![Python](https://img.shields.io/badge/python-3.11+-blue.svg)](https://python.org)
+[![Agent-OS Compatible](https://img.shields.io/badge/agent--os-compatible-green.svg)](https://github.com/imran-siddique/agent-os)
+
+> ⭐ **If this project helps you, please star it!** It helps others discover AgentMesh.
+
+> 🔗 **Part of the Agent Ecosystem** — Works seamlessly with [Agent-OS](https://github.com/imran-siddique/agent-os) for IATP trust protocol
 
 ---
 
@@ -55,10 +62,23 @@ AgentMesh provides:
 
 ## Quick Start
 
+### Option 1: Secure Claude Desktop (Recommended)
+
 ```bash
-# Install AgentMesh CLI
-pip install agentmesh
+# Install AgentMesh
+pip install agentmesh-platform
 
+# Set up Claude Desktop to use AgentMesh governance
+agentmesh init-integration --claude
+
+# Restart Claude Desktop - all MCP tools are now secured!
+```
+
+Claude will now route tool calls through AgentMesh for policy enforcement and trust scoring.
+
+### Option 2: Create a Governed Agent
+
+```bash
 # Initialize a governed agent in 30 seconds
 agentmesh init --name my-agent --sponsor alice@company.com
 
@@ -69,10 +89,29 @@ agentmesh register
 agentmesh run
 ```
 
+### Option 3: Wrap Any MCP Server
+
+```bash
+# Proxy any MCP server with governance
+agentmesh proxy --target npx --target -y \
+  --target @modelcontextprotocol/server-filesystem \
+  --target /path/to/directory
+
+# Use strict policy (blocks writes/deletes)
+agentmesh proxy --policy strict --target <your-mcp-server>
+```
+
 ## Installation
 
 ```bash
-pip install agentmesh
+pip install agentmesh-platform
+```
+
+Or install with extra dependencies:
+
+```bash
+pip install agentmesh-platform[server]  # FastAPI server
+pip install agentmesh-platform[dev]     # Development tools
 ```
 
 Or from source:
@@ -83,6 +122,71 @@ cd agent-mesh
 pip install -e .
 ```
 
+## Examples & Integrations
+
+**Real-world examples** to get started quickly:
+
+| Example | Use Case | Key Features |
+|---------|----------|--------------|
+| [MCP Tool Server](./examples/01-mcp-tool-server/) | Secure MCP server with governance | Rate limiting, output sanitization, audit logs |
+| [Multi-Agent Customer Service](./examples/02-customer-service/) | Customer support automation | Delegation chains, trust handshakes, A2A |
+| [Healthcare HIPAA](./examples/03-healthcare-hipaa/) | HIPAA-compliant data analysis | Compliance automation, PHI protection, Merkle audit |
+| [GitHub PR Review](./examples/05-github-integration/) | Code review agent | Output policies, shadow mode, trust decay |
+
+**Framework integrations:**
+- **[Claude Desktop](./docs/integrations/claude-desktop.md)** - Secure MCP tools with one command
+- [LangChain Integration](./examples/integrations/langchain.md) - Secure LangChain agents with policies
+- [CrewAI Integration](./examples/integrations/crewai.md) - Multi-agent crew governance
+
+📚 **[Browse all examples →](./examples/)**
+
+## The AgentMesh Proxy: "SSL for AI Agents"
+
+**Problem:** AI agents like Claude Desktop have unfettered access to your filesystem, database, and APIs through MCP servers. One hallucination could be catastrophic.
+
+**Solution:** AgentMesh acts as a transparent governance proxy:
+
+```bash
+# Before: Unsafe direct access
+{
+  "mcpServers": {
+    "filesystem": {
+      "command": "npx",
+      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/Users/me"]
+    }
+  }
+}
+
+# After: Protected by AgentMesh
+{
+  "mcpServers": {
+    "filesystem": {
+      "command": "agentmesh",
+      "args": [
+        "proxy", "--policy", "strict",
+        "--target", "npx", "--target", "-y",
+        "--target", "@modelcontextprotocol/server-filesystem",
+        "--target", "/Users/me"
+      ]
+    }
+  }
+}
+```
+
+**What you get:**
+- 🔒 **Policy Enforcement** - Block dangerous operations before they execute
+- 📊 **Trust Scoring** - Behavioral monitoring (800-1000 scale)  
+- 📝 **Audit Logs** - Tamper-evident record of every action
+- ✅ **Verification Footers** - Visual confirmation in outputs
+
+**Set it up in 10 seconds:**
+```bash
+agentmesh init-integration --claude
+# Restart Claude Desktop - done!
+```
+
+Learn more: **[Claude Desktop Integration Guide](./docs/integrations/claude-desktop.md)**
+
 ## Core Concepts
 
 ### 1. Agent Identity

agentmesh_platform-1.0.0a2/docs/CLOUDEVENTS_SCHEMA.md

@@ -0,0 +1,281 @@
+# CloudEvents Audit Log Schema
+
+AgentMesh audit logs follow the [CloudEvents v1.0](https://cloudevents.io/) specification for interoperability with enterprise event systems.
+
+## Overview
+
+CloudEvents is a specification for describing event data in a common way. By adopting CloudEvents, AgentMesh audit logs can be natively ingested by:
+
+- **Azure Event Grid**
+- **AWS EventBridge**
+- **Google Cloud Eventarc**
+- **Apache Kafka**
+- **Splunk**
+- **Datadog**
+- **Any CloudEvents-compatible system**
+
+## Event Types
+
+| Event Type | Description |
+|------------|-------------|
+| `ai.agentmesh.agent.registered` | New agent registered |
+| `ai.agentmesh.agent.verified` | Agent identity verified |
+| `ai.agentmesh.policy.evaluation` | Policy was evaluated |
+| `ai.agentmesh.policy.violation` | Policy violation detected |
+| `ai.agentmesh.tool.invoked` | Tool was invoked |
+| `ai.agentmesh.tool.blocked` | Tool invocation blocked |
+| `ai.agentmesh.trust.handshake` | Trust handshake performed |
+| `ai.agentmesh.trust.score.updated` | Trust score changed |
+| `ai.agentmesh.audit.integrity.verified` | Audit log integrity checked |
+
+## Schema
+
+### Base CloudEvent Structure
+
+```json
+{
+  "specversion": "1.0",
+  "id": "550e8400-e29b-41d4-a716-446655440000",
+  "type": "ai.agentmesh.policy.violation",
+  "source": "did:mesh:agent123",
+  "time": "2026-02-03T12:00:00.000Z",
+  "datacontenttype": "application/json",
+  "subject": "tool:filesystem:read",
+  "data": {
+    // Event-specific payload
+  }
+}
+```
+
+### Required Fields
+
+| Field | Type | Description |
+|-------|------|-------------|
+| `specversion` | String | Always "1.0" |
+| `id` | String | Unique event ID (UUID) |
+| `type` | String | Event type from list above |
+| `source` | URI | Agent DID or service identifier |
+| `time` | Timestamp | ISO 8601 timestamp |
+
+### Optional Fields
+
+| Field | Type | Description |
+|-------|------|-------------|
+| `subject` | String | Specific subject (tool name, resource) |
+| `datacontenttype` | String | Always "application/json" |
+| `dataschema` | URI | Link to JSON schema |
+
+## Event Payloads
+
+### Policy Violation
+
+```json
+{
+  "specversion": "1.0",
+  "id": "event-uuid-here",
+  "type": "ai.agentmesh.policy.violation",
+  "source": "did:mesh:agent-abc123",
+  "time": "2026-02-03T12:00:00.000Z",
+  "datacontenttype": "application/json",
+  "subject": "tool:shell:execute",
+  "data": {
+    "trace_id": "trace-uuid-here",
+    "agent_id": "agent-abc123",
+    "agent_name": "CustomerServiceBot",
+    "tool_name": "shell:execute",
+    "tool_args": {
+      "command": "rm -rf /",
+      "args_hash": "sha256:abc123..."
+    },
+    "policy_id": "policy-no-destructive-commands",
+    "policy_name": "No Destructive Commands",
+    "violation_reason": "Command matches destructive pattern",
+    "severity": "critical",
+    "action_taken": "blocked",
+    "merkle_proof": {
+      "entry_hash": "sha256:...",
+      "previous_hash": "sha256:...",
+      "chain_position": 1542
+    }
+  }
+}
+```
+
+### Tool Invoked (Success)
+
+```json
+{
+  "specversion": "1.0",
+  "id": "event-uuid-here",
+  "type": "ai.agentmesh.tool.invoked",
+  "source": "did:mesh:agent-abc123",
+  "time": "2026-02-03T12:00:00.000Z",
+  "subject": "tool:database:query",
+  "data": {
+    "trace_id": "trace-uuid-here",
+    "agent_id": "agent-abc123",
+    "tool_name": "database:query",
+    "tool_args_hash": "sha256:...",
+    "execution_time_ms": 45.2,
+    "result_hash": "sha256:...",
+    "policy_verdict": "allowed",
+    "policies_evaluated": ["policy-read-only", "policy-no-pii"],
+    "merkle_proof": {
+      "entry_hash": "sha256:...",
+      "previous_hash": "sha256:..."
+    }
+  }
+}
+```
+
+### Trust Handshake
+
+```json
+{
+  "specversion": "1.0",
+  "id": "event-uuid-here",
+  "type": "ai.agentmesh.trust.handshake",
+  "source": "did:mesh:agent-requester",
+  "time": "2026-02-03T12:00:00.000Z",
+  "subject": "did:mesh:agent-provider",
+  "data": {
+    "requester_did": "did:mesh:agent-requester",
+    "provider_did": "did:mesh:agent-provider",
+    "capabilities_requested": ["database:read", "api:call"],
+    "capabilities_granted": ["database:read"],
+    "capabilities_denied": ["api:call"],
+    "requester_trust_score": 847,
+    "provider_trust_score": 920,
+    "handshake_result": "partial",
+    "signature": "base64:..."
+  }
+}
+```
+
+### Trust Score Updated
+
+```json
+{
+  "specversion": "1.0",
+  "id": "event-uuid-here",
+  "type": "ai.agentmesh.trust.score.updated",
+  "source": "did:mesh:agent-abc123",
+  "time": "2026-02-03T12:00:00.000Z",
+  "data": {
+    "agent_did": "did:mesh:agent-abc123",
+    "previous_score": 850,
+    "new_score": 835,
+    "change": -15,
+    "reason": "policy_violation",
+    "dimensions": {
+      "policy_compliance": 75,
+      "resource_efficiency": 90,
+      "output_quality": 85,
+      "security_posture": 80,
+      "collaboration_health": 88
+    },
+    "tier_change": {
+      "from": "Trusted",
+      "to": "Trusted"
+    }
+  }
+}
+```
+
+## Extension Attributes
+
+AgentMesh defines these extension attributes:
+
+| Attribute | Type | Description |
+|-----------|------|-------------|
+| `agentmeshmerkleroot` | String | Current Merkle tree root hash |
+| `agentmeshtrustscope` | String | Trust scope (local, federated) |
+| `agentmeshpolicyversion` | String | Policy engine version |
+
+## JSON Schema
+
+Full JSON Schema for validation:
+
+```json
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://agentmesh.dev/schemas/cloudevents/v1/policy-violation.json",
+  "title": "AgentMesh Policy Violation Event",
+  "type": "object",
+  "required": ["specversion", "id", "type", "source", "time", "data"],
+  "properties": {
+    "specversion": { "const": "1.0" },
+    "id": { "type": "string", "format": "uuid" },
+    "type": { "const": "ai.agentmesh.policy.violation" },
+    "source": { "type": "string", "format": "uri" },
+    "time": { "type": "string", "format": "date-time" },
+    "data": {
+      "type": "object",
+      "required": ["trace_id", "agent_id", "tool_name", "violation_reason"],
+      "properties": {
+        "trace_id": { "type": "string" },
+        "agent_id": { "type": "string" },
+        "tool_name": { "type": "string" },
+        "violation_reason": { "type": "string" },
+        "severity": { "enum": ["low", "medium", "high", "critical"] }
+      }
+    }
+  }
+}
+```
+
+## Integration Examples
+
+### Azure Event Grid
+
+```python
+from azure.eventgrid import EventGridPublisherClient
+from azure.core.credentials import AzureKeyCredential
+
+client = EventGridPublisherClient(endpoint, AzureKeyCredential(key))
+client.send([cloud_event])  # AgentMesh CloudEvent
+```
+
+### AWS EventBridge
+
+```python
+import boto3
+
+client = boto3.client('events')
+client.put_events(Entries=[{
+    'Source': cloud_event['source'],
+    'DetailType': cloud_event['type'],
+    'Detail': json.dumps(cloud_event['data']),
+    'EventBusName': 'agentmesh-audit'
+}])
+```
+
+### Splunk HEC
+
+```bash
+curl -X POST https://splunk:8088/services/collector/event \
+  -H "Authorization: Splunk $TOKEN" \
+  -d '{"event": <cloudevent-json>}'
+```
+
+## Migration from Legacy Format
+
+If upgrading from pre-CloudEvents audit logs:
+
+```python
+def migrate_to_cloudevent(legacy_log):
+    return {
+        "specversion": "1.0",
+        "id": legacy_log["trace_id"],
+        "type": f"ai.agentmesh.tool.{legacy_log['policy_verdict']}",
+        "source": f"did:mesh:{legacy_log['agent_id']}",
+        "time": legacy_log["timestamp"],
+        "datacontenttype": "application/json",
+        "data": legacy_log
+    }
+```
+
+---
+
+*Schema Version: 1.0*
+*Last Updated: February 2026*

{agentmesh_platform-1.0.0a1 → agentmesh_platform-1.0.0a2}/docs/GTM-PLAN.md

@@ -10,20 +10,30 @@ AgentMesh is the first platform purpose-built for the **Governed Agent Mesh** -
 
 ```
 PyPI Packages:
-├── agent-os (1.2.0)
+├── agent-os-kernel (1.2.0) ✅ PUBLISHED
 │   ├── Core kernel
 │   ├── [nexus] - Trust Exchange
 │   ├── [iatp] - Inter-Agent Trust Protocol
 │   └── [full] - All components
 │
-└── agentmesh (1.0.0-alpha)
-    ├── Depends on: agent-os[nexus,iatp]
+└── agentmesh-platform (1.0.0a1) ✅ PUBLISHED
+    ├── Depends on: agent-os-kernel[nexus,iatp]
     ├── Layer 1: Identity
     ├── Layer 2: Trust
     ├── Layer 3: Governance
     └── Layer 4: Reward
 ```
 
+## Installation
+
+```bash
+# Install the complete governance platform
+pip install agentmesh-platform
+
+# Or install just the kernel
+pip install agent-os-kernel[nexus,iatp]
+```
+
 ## GTM Timeline
 
 ### Week 1-2: Open Source Launch