useagentmesh 0.5.0

The Python Governance Platform for AI Agents — compliance middleware for LangGraph, CrewAI, AutoGen

AgentMesh SDK

The Trust Layer for AI Agents — Scan for governance gaps offline. Enforce policies in production via the AgentMesh platform.

---

Quick Start

1. Install

pip install useagentmesh

With framework-specific extras:

pip install useagentmesh[crewai]      # CrewAI support
pip install useagentmesh[langgraph]   # LangGraph support
pip install useagentmesh[autogen]     # AutoGen support
pip install useagentmesh[all]         # All frameworks

2. Scan Your Project (free, offline, no account needed)

agentmesh scan .
# → Governance Score: 35/100 | 8 findings | Agent BOM: 3 agents, 12 tools
# → Run `agentmesh auth login` to enable runtime governance

3. Connect to Platform (optional, enables runtime governance)

agentmesh init

This will:

• Validate your API key
• Generate .agentmesh.yaml config
• Create a framework-specific middleware file
• Enable runtime policy enforcement

4. Integrate Runtime Middleware

CrewAI

from agentmesh import with_compliance
from my_crew import MyCrew

crew = with_compliance(MyCrew())
result = crew.kickoff()

LangGraph

from agentmesh import with_langgraph_compliance

graph = with_langgraph_compliance(my_graph.compile())
result = graph.invoke(input)

AutoGen

from agentmesh import with_autogen_compliance

chat = with_autogen_compliance(my_group_chat)

Direct Client

from agentmesh import AgentMeshClient

client = AgentMeshClient.from_env()
result = client.verify_agent_identity_sync("my-agent", "researcher")

---

CLI Commands

Command	Description	Requires Account
agentmesh scan .	Scan project for governance gaps	No
agentmesh init	Initialize runtime SDK in your project	Yes
agentmesh status	Check connection and quota status	Yes
agentmesh verify	Verify audit hash chain integrity	Yes
agentmesh serve	Start a local MCP compliance server	Yes

---

Configuration

.agentmesh.yaml:

version: "1.0"
tenant_id: your_tenant_id
api_key_env: AGENTMESH_API_KEY
endpoint: https://api.useagentmesh.com
framework: crewai

tools:
  audit_log_action: true
  verify_agent_identity: true
  evaluate_policy: true

guardrails:
  prompt_injection_detection: true
  dlp_scanning: false

trust:
  enabled: true
  decay_half_life_hours: 168
  circuit_breaker_threshold: 3

---

Capabilities

Scan CLI (free, offline)

Capability	Status	Details
Governance Score	✅ Built-in	25 rules, 4 categories, deterministic evaluation
Agent BOM	✅ Built-in	AST-based discovery, 6 frameworks
EU AI Act Gap Detection	✅ Built-in	Art. 9, 11, 12, 14 mapping with fix snippets
SARIF 2.1.0	✅ Built-in	GitHub Code Scanning compatible
SVG Badge	✅ Built-in	Embeddable governance badge

Runtime Platform (requires account)

Capability	Status	Details
Policy Enforcement	✅ Production	Real-time evaluation on tool calls
DLP/PII Detection	✅ Production	Presidio-based, 8+ entity types, anonymization
Circuit Breaker	✅ Production	State machine + EigenTrust scoring
Audit Trail	✅ Production	SHA-256/BLAKE3 hash chain + digital signatures
Trust Score	✅ Production	0-100 dynamic score per agent
OTEL Export	🔜 Next Sprint	OpenTelemetry semantic conventions

---

Environment Variables

Variable	Description	Required
AGENTMESH_API_KEY	Your API key (for runtime features)	For platform
AGENTMESH_ENDPOINT	Custom backend URL	No
AGENTMESH_TENANT_ID	Override tenant ID	No

---

Development

git clone https://github.com/agentmesh/agentmesh-python.git
cd agentmesh-python
pip install -e ".[dev]"
pytest

---

License

MIT