AgentMesh — Community Edition

SSL for AI Agents

The trust, identity, and governance layer for production AI agent systems

Identity · Trust · Reward · Governance

⭐ If this project helps you, please star it! It helps others discover AgentMesh.

🔗 Part of the Agent Governance Ecosystem — Works with Agent OS (kernel), Agent Hypervisor (runtime), and Agent SRE (reliability)

📦 Install the full stack: pip install ai-agent-governance[full] — PyPI | GitHub

Quick Start • MCP Proxy • Examples • Agent OS • Agent Hypervisor

Trusted By

Featured In

1,300+

_{Tests Passing}

6

_{Framework Integrations}

170K+

_{Combined Stars of
Integrated Projects}

4

_{Protocol Bridges
(A2A · MCP · IATP · AI Card)}

<1ms p99

_{Full Governance Pipeline}

🏢 Production Integrations

Framework	Stars	Status	What We Ship
Dify	65K ⭐	✅ Merged	Trust verification plugin in Dify Marketplace
LlamaIndex	47K ⭐	✅ Merged	TrustedAgentWorker + TrustGatedQueryEngine
Microsoft Agent-Lightning	15K ⭐	✅ Merged	Governance kernel for RL training safety
LangGraph	24K ⭐	📦 PyPI	Trust-scored state transitions
OpenAI Agents SDK	—	📦 PyPI	Tool-level governance guardrails
Haystack	22K ⭐	🔄 In Review	GovernancePolicyChecker + TrustGate components

AgentMesh is "SSL for AI Agents" — the trust and identity layer that makes multi-agent systems enterprise-ready. Every agent gets a cryptographic identity. Every interaction is verified. Every action is audited.

Overview

AgentMesh is the first platform purpose-built for the Governed Agent Mesh — the cloud-native, multi-vendor network of AI agents that will define enterprise operations.

The protocols exist (A2A, MCP, IATP). The agents are shipping. The trust layer does not. AgentMesh fills that gap.

┌─────────────────────────────────────────────────────────────────────────────┐
│                           AGENTMESH ARCHITECTURE                            │
├─────────────────────────────────────────────────────────────────────────────┤
│  LAYER 4  │  Reward & Learning Engine                                       │
│           │  Per-agent trust scores · Behavioral rewards · Adaptive          │
├───────────┼─────────────────────────────────────────────────────────────────┤
│  LAYER 3  │  Governance & Compliance Plane                                  │
│           │  Policy engine · EU AI Act / SOC2 / HIPAA · Audit logs          │
├───────────┼─────────────────────────────────────────────────────────────────┤
│  LAYER 2  │  Trust & Protocol Bridge                                        │
│           │  A2A · MCP · IATP · Protocol translation · Capability scoping   │
├───────────┼─────────────────────────────────────────────────────────────────┤
│  LAYER 1  │  Identity & Zero-Trust Core                                     │
│           │  Agent CA · Ephemeral creds · SPIFFE/SVID · Human sponsors      │
└───────────┴─────────────────────────────────────────────────────────────────┘

Why AgentMesh?

The Problem

40:1 to 100:1 — Non-human identities now outnumber human identities in enterprises
AI agents are the fastest-growing, least-governed identity category
A2A gives agents a common language. MCP gives agents tools. Neither enforces trust.

The Solution

AgentMesh provides:

Capability	Description
Agent Identity	First-class identity with human sponsor accountability
Ephemeral Credentials	15-minute TTL by default, auto-rotation
Protocol Bridge	Native A2A, MCP, IATP with unified trust model
Reward Engine	Continuous behavioral scoring
Compliance Automation	EU AI Act, SOC 2, HIPAA, GDPR mapping

How It Works

1. Agent Registration & DID Issuance

sequenceDiagram
    participant Agent
    participant CLI as AgentMesh CLI
    participant CA as Certificate Authority
    participant Registry as Agent Registry

    Agent->>CLI: agentmesh init --name my-agent --sponsor alice@company.com
    CLI->>CA: Request Ed25519 keypair & DID
    CA-->>CLI: did:mesh:my-agent + signed certificate
    CLI->>Agent: Write identity to local config
    Agent->>CLI: agentmesh register
    CLI->>Registry: Register DID + capabilities + sponsor
    Registry-->>CLI: Registration confirmed
    CLI-->>Agent: Agent ready (status: registered)

2. Trust Handshake Between Two Agents

sequenceDiagram
    participant A as Agent A
    participant Bridge as TrustBridge
    participant B as Agent B

    A->>Bridge: verify_peer(did:mesh:agent-b, min_trust=700)
    Bridge->>B: IATP challenge (nonce + timestamp)
    B-->>Bridge: Signed response (Ed25519 signature)
    Bridge->>Bridge: Verify signature & check trust score
    alt Trust score ≥ 700
        Bridge-->>A: Verification succeeded (score: 850)
        A->>Bridge: send_message(did:mesh:agent-b, payload)
        Bridge->>B: Deliver message
        B-->>Bridge: Acknowledge
        Bridge-->>A: Message delivered
    else Trust score < 700
        Bridge-->>A: Verification failed (score: 620)
    end

3. MCP Proxy Request Flow

sequenceDiagram
    participant Client as MCP Client (e.g. Claude)
    participant Proxy as AgentMesh Proxy
    participant Policy as Policy Engine
    participant Server as MCP Server

    Client->>Proxy: Tool call request
    Proxy->>Policy: Evaluate action against policy rules
    alt Action allowed
        Policy-->>Proxy: Allow
        Proxy->>Server: Forward tool call
        Server-->>Proxy: Tool result
        Proxy->>Proxy: Sanitize output & append verification footer
        Proxy-->>Client: Governed tool result
    else Action denied
        Policy-->>Proxy: Deny (rule: no-pii-export)
        Proxy-->>Client: Action blocked + reason
    end
    Proxy->>Proxy: Write audit log entry

4. Credential Rotation Lifecycle

sequenceDiagram
    participant Agent
    participant CA as Certificate Authority
    participant Registry as Agent Registry

    CA->>Agent: Issue ephemeral credential (TTL: 15 min)
    Note over Agent: Credential active

    loop Every 15 minutes
        Agent->>CA: Request credential rotation
        CA->>CA: Verify agent DID & trust score
        CA-->>Agent: New ephemeral credential (TTL: 15 min)
        CA->>Registry: Update credential fingerprint
        Note over Agent: Old credential invalidated
    end

    alt Trust breach detected
        Registry->>CA: Revoke credential immediately
        CA-->>Agent: Credential revoked
        Note over Agent: Agent must re-register
    end

5. Trust Score Update After Task Completion

sequenceDiagram
    participant Agent
    participant Governance as Governance Layer
    participant Reward as Reward Engine
    participant Registry as Agent Registry

    Agent->>Governance: Complete task (action: data_export)
    Governance->>Governance: Check compliance (SOC2, HIPAA)
    Governance-->>Reward: Task result + compliance status
    Reward->>Reward: Calculate score delta
    Note over Reward: Policy compliance: +10<br/>Task success: +5<br/>No violations: +3
    Reward->>Registry: Update trust score (820 → 838)
    Registry-->>Agent: Updated trust score: 838
    Reward->>Governance: Write audit log

Quick Start

Option 1: Secure Claude Desktop (Recommended)

# 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

# Initialize a governed agent in 30 seconds
agentmesh init --name my-agent --sponsor alice@company.com

# Register with the mesh
agentmesh register

# Start with governance enabled
agentmesh run

Option 3: Wrap Any MCP Server

# 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

pip install agentmesh-platform

Or install with extra dependencies:

pip install agentmesh-platform[server]  # FastAPI server
pip install agentmesh-platform[dev]     # Development tools

Or from source:

git clone https://github.com/imran-siddique/agent-mesh.git
cd agent-mesh
pip install -e .

Examples & Integrations

Real-world examples to get started quickly:

Example	Use Case	Key Features
Registration Hello World	Agent registration walkthrough	Identity, DID, sponsor handshake
MCP Tool Server	Secure MCP server with governance	Rate limiting, output sanitization, audit logs
Multi-Agent Customer Service	Customer support automation	Trust handshakes, delegation, A2A
Healthcare HIPAA	HIPAA-compliant data analysis	Compliance automation, PHI protection, audit logs
DevOps Automation	Just-in-time DevOps credentials	Ephemeral creds, capability scoping
GitHub PR Review	Code review agent	Output policies, shadow mode, trust decay

Framework integrations:

Claude Desktop - Secure MCP tools with one command
LangChain Integration - Secure LangChain agents with policies
CrewAI Integration - Multi-agent crew governance
LangGraph - Trust checkpoints for graph workflows (built-in)
OpenAI Swarm - Trust-verified handoffs (built-in)
Dify - Trust middleware for Dify workflows

📚 Browse all examples →

Trust Visualization Dashboard

Interactive Streamlit dashboard:

cd examples/06-trust-score-dashboard
pip install -r requirements.txt
streamlit run trust_dashboard.py

Tabs: Trust Network | Trust Scores | Credential Lifecycle | Protocol Traffic | Compliance

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:

# 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 - Per-agent trust scoring (800-1000 scale)
📝 Audit Logs - Record of every action
✅ Verification Footers - Visual confirmation in outputs

Set it up in 10 seconds:

agentmesh init-integration --claude
# Restart Claude Desktop - done!

Learn more: Claude Desktop Integration Guide

Core Concepts

1. Agent Identity

Every agent gets a unique, cryptographically bound identity:

from agentmesh import AgentIdentity

identity = AgentIdentity.create(
    name="data-analyst-agent",
    sponsor="alice@company.com",  # Human accountability
    capabilities=["read:data", "write:reports"],
)

2. Scope Chains

Agents can delegate to sub-agents, but scope always narrows:

# Parent agent delegates to child
child_identity = parent_identity.delegate(
    name="summarizer-subagent",
    capabilities=["read:data"],  # Subset of parent's capabilities
)

3. Trust Handshakes (IATP)

Cross-agent communication requires trust verification:

from agentmesh import AgentIdentity, TrustBridge

# Create your identity first
identity = AgentIdentity.create(name="my-agent", sponsor="admin@company.com")

# Set up trust bridge
bridge = TrustBridge(agent_did=str(identity.did))

# Verify peer before communication
verification = await bridge.verify_peer(
    peer_did="did:mesh:other-agent",
    required_trust_score=700,
)

if verification.verified:
    print(f"Peer trusted: score={verification.trust_score}")

4. Reward Scoring

Every action is scored to maintain agent trust:

from agentmesh import RewardEngine

engine = RewardEngine()

# Actions are automatically scored
score = engine.get_agent_score("did:mesh:my-agent")
# Returns trust score on 0-1000 scale

5. Policy Engine

Declarative governance policies:

# policy.yaml
version: "1.0"
agent: "data-analyst-agent"

rules:
  - name: "no-pii-export"
    condition: "action.type == 'export' and data.contains_pii"
    action: "deny"
    
  - name: "rate-limit-api"
    condition: "action.type == 'api_call'"
    limit: "100/hour"
    
  - name: "require-approval-for-delete"
    condition: "action.type == 'delete'"
    action: "require_approval"
    approvers: ["security-team"]

Protocol Support

Protocol	Status	Description
AI Card	✅ Alpha	Cross-protocol identity standard (`src/agentmesh/integrations/ai_card/`)
A2A	✅ Alpha	Agent-to-agent coordination (full adapter in `src/agentmesh/integrations/a2a/`)
MCP	✅ Alpha	Tool and resource binding (trust-gated server/client in `src/agentmesh/integrations/mcp/`)
IATP	✅ Alpha	Trust handshakes (via agent-os, graceful fallback if unavailable)
ACP	🔜 Planned	Lightweight messaging (protocol bridge supports routing, adapter not yet implemented)
SPIFFE	✅ Alpha	Workload identity

Architecture

agentmesh/
├── identity/           # Layer 1: Identity & Zero-Trust
│   ├── agent_id.py     # Agent identity management (DIDs, Ed25519 keys)
│   ├── credentials.py  # Ephemeral credential issuance (15-min TTL)
│   ├── delegation.py   # Scope chains
│   ├── spiffe.py       # SPIFFE/SVID integration
│   ├── risk.py         # Continuous risk scoring
│   └── sponsor.py      # Human sponsor accountability
│
├── trust/              # Layer 2: Trust & Protocol Bridge
│   ├── bridge.py       # Multi-protocol trust bridge (A2A/MCP/IATP/ACP)
│   ├── handshake.py    # IATP trust handshakes
│   ├── cards.py        # Trusted agent cards
│   └── capability.py   # Capability scoping
│
├── governance/         # Layer 3: Governance & Compliance
│   ├── policy.py       # Declarative policy engine (YAML/JSON)
│   ├── compliance.py   # Compliance mapping (EU AI Act, SOC2, HIPAA, GDPR)
│   ├── audit.py        # Audit logs
│   └── shadow.py       # Shadow mode for policy testing
│
├── reward/             # Layer 4: Reward & Learning
│   ├── engine.py       # Multi-dimensional reward engine
│   ├── scoring.py      # Trust scoring
│   └── learning.py     # Adaptive learning
│
├── integrations/       # Protocol & framework adapters
│   ├── ai_card/        # AI Card standard (cross-protocol identity)
│   ├── a2a/            # Google A2A protocol support
│   ├── mcp/            # Anthropic MCP trust-gated server/client
│   ├── langgraph/      # LangGraph trust checkpoints
│   └── swarm/          # OpenAI Swarm trust-verified handoffs
│
├── cli/                # Command-line interface
│   ├── main.py         # agentmesh init/register/status/audit/policy
│   └── proxy.py        # MCP governance proxy
│
├── core/               # Low-level services
│   └── identity/ca.py  # Certificate Authority (SPIFFE/SVID)
│
├── storage/            # Storage abstraction (memory, Redis, PostgreSQL)
│
├── observability/      # OpenTelemetry tracing & Prometheus metrics
│
└── services/           # Service wrappers (registry, audit, reward)

Compliance

AgentMesh automates compliance mapping for:

EU AI Act — Risk classification, transparency requirements
SOC 2 — Security, availability, processing integrity
HIPAA — PHI handling, audit controls
GDPR — Data processing, consent, right to explanation

from agentmesh import ComplianceEngine, ComplianceFramework

compliance = ComplianceEngine(frameworks=[ComplianceFramework.SOC2, ComplianceFramework.HIPAA])

# Check an action for violations
violations = compliance.check_compliance(
    agent_did="did:mesh:healthcare-agent",
    action_type="data_access",
    context={"data_type": "phi", "encrypted": True},
)

# Generate compliance report
from datetime import datetime, timedelta
report = compliance.generate_report(
    framework=ComplianceFramework.SOC2,
    period_start=datetime.utcnow() - timedelta(days=30),
    period_end=datetime.utcnow(),
)

Threat Model

Threat	AgentMesh Defense
Prompt Injection	Tool output sanitized at Protocol Bridge
Credential Theft	15-min TTL, instant revocation on trust breach
Shadow Agents	Unregistered agents blocked at network layer
Delegation Escalation	Chains enforce scope narrowing
Cascade Failure	Per-agent trust scoring isolates blast radius

🗺️ Roadmap

Quarter	Milestone
Q1 2026	✅ Core trust layer, identity, governance engine, 6 framework integrations
Q2 2026	TypeScript SDK, Go SDK, Dashboard UI, Plugin Marketplace
Q3 2026	AI Card spec contribution, CNCF Sandbox application
Q4 2026	Managed cloud service (AgentMesh Cloud), SOC2 Type II

See our full roadmap for details.

Known Limitations & Open Work

Transparency about what's done and what isn't.

Not Yet Implemented

Item	Location	Notes
ACP protocol adapter	`trust/bridge.py`	Bridge routes ACP messages, but no dedicated `ACPAdapter` class yet
Service wrapper for audit	`services/audit/`	Core audit module (`governance/audit.py`) is complete; service layer wrapper is a TODO
Service wrapper for reward engine	`services/reward_engine/`	Core reward engine (`reward/engine.py`) is complete; service layer wrapper is a TODO
Mesh control plane	`services/mesh-control-plane/`	Placeholder directory; no implementation yet
Scope chain cryptographic verification	`packages/langchain-agentmesh/trust.py`	Simulated verification; full cryptographic chain validation not yet implemented

Integration Caveats (Dify)

The Dify integration has these documented limitations:

Request body signature verification (X-Agent-Signature header) is not yet verified by middleware
Trust score time decay is not yet implemented (scores don't decay over time)
Audit logs are in-memory only (not persistent across multi-worker deployments)
Environment variable configuration requires programmatic initialization (not auto-wired)

Infrastructure

Redis/PostgreSQL storage providers: Implemented but require real infrastructure for testing (unit tests use in-memory provider)
Kubernetes Operator: GovernedAgent CRD defined, but no controller/operator to reconcile it
SPIRE Integration: SPIFFE identity module exists; real SPIRE agent integration is stubbed
Performance targets: Latency overhead (<5ms) and throughput (10k reg/sec) are design targets, not yet benchmarked

Documentation

docs/rfcs/ — Directory exists, no RFCs written yet
docs/architecture/ — Directory exists, no architecture docs yet (see IMPLEMENTATION-NOTES.md for current notes)

Dependencies

AgentMesh builds on:

Agent OS — IATP protocol, Nexus trust exchange
Agent Hypervisor — Runtime session governance
Agent SRE — SLO monitoring, chaos testing
SPIFFE/SPIRE — Workload identity
OpenTelemetry — Observability

Frequently Asked Questions

What is an agent mesh? An agent mesh is a trust and communication infrastructure for multi-agent AI systems, analogous to a service mesh for microservices. AgentMesh provides identity (DID-based), per-agent trust scoring (0-1000 scale), ephemeral credentials, reward distribution, and automated compliance mapping.

How does AgentMesh handle trust between agents? Every agent gets a trust score from 0 to 1000 based on behavioral history, vouching from other agents, and compliance with governance policies. Trust scores gate what actions agents can perform and which sessions they can join. The score updates in real-time based on agent behavior.

What protocols does AgentMesh bridge? AgentMesh unifies three major protocols: Google's A2A (Agent-to-Agent) for inter-agent communication, Anthropic's MCP (Model Context Protocol) for tool integration, and IATP (Inter-Agent Trust Protocol) for cryptographic trust establishment. This means agents built on different frameworks can communicate through a single trust-verified channel.

Does AgentMesh help with regulatory compliance? Yes. AgentMesh provides automated compliance mapping for EU AI Act, SOC 2, HIPAA, and GDPR. Combined with audit trails and deterministic policy enforcement from Agent OS, it provides the documentation and safety guarantees needed for regulatory compliance.

Contributing

See CONTRIBUTING.md for guidelines.

License

Apache 2.0 — See LICENSE for details.

Agents shouldn't be islands. But they also shouldn't be ungoverned.

AgentMesh is the trust layer that makes the mesh safe enough to scale.

Name		Name	Last commit message	Last commit date
Latest commit History 160 Commits
.github		.github
assets		assets
charts/agentmesh		charts/agentmesh
dashboards/grafana		dashboards/grafana
deployments		deployments
docs		docs
examples		examples
integrations		integrations
notebooks		notebooks
packages		packages
proto		proto
schemas		schemas
sdks		sdks
services/api		services/api
src/agentmesh		src/agentmesh
tests		tests
tutorials/claude-desktop-mcp-proxy		tutorials/claude-desktop-mcp-proxy
.dockerignore		.dockerignore
.env.example		.env.example
.gitignore		.gitignore
.pre-commit-config.yaml		.pre-commit-config.yaml
ADOPTERS.md		ADOPTERS.md
AGENTS.md		AGENTS.md
ARCHITECTURE.md		ARCHITECTURE.md
CHANGELOG.md		CHANGELOG.md
CODE_OF_CONDUCT.md		CODE_OF_CONDUCT.md
CONTRIBUTING.md		CONTRIBUTING.md
DEPLOYMENT.md		DEPLOYMENT.md
Dockerfile.dev		Dockerfile.dev
Dockerfile.server		Dockerfile.server
Dockerfile.sidecar		Dockerfile.sidecar
GOVERNANCE.md		GOVERNANCE.md
IMPLEMENTATION-NOTES.md		IMPLEMENTATION-NOTES.md
LICENSE		LICENSE
README.md		README.md
SECURITY.md		SECURITY.md
docker-compose.dev.yml		docker-compose.dev.yml
docker-compose.yml		docker-compose.yml
pyproject.toml		pyproject.toml
requirements-dev.txt		requirements-dev.txt

Uh oh!

Folders and files

Latest commit

History

Repository files navigation

AgentMesh — Community Edition

Trusted By

Featured In

1,300+

6

170K+

4

<1ms p99

🏢 Production Integrations

Overview

Why AgentMesh?

The Problem

The Solution

How It Works

1. Agent Registration & DID Issuance

2. Trust Handshake Between Two Agents

3. MCP Proxy Request Flow

4. Credential Rotation Lifecycle

5. Trust Score Update After Task Completion

Quick Start

Option 1: Secure Claude Desktop (Recommended)

Option 2: Create a Governed Agent

Option 3: Wrap Any MCP Server

Installation

Examples & Integrations

Trust Visualization Dashboard

The AgentMesh Proxy: "SSL for AI Agents"

Core Concepts

1. Agent Identity

2. Scope Chains

3. Trust Handshakes (IATP)

4. Reward Scoring

5. Policy Engine

Protocol Support

Architecture

Compliance

Threat Model

🗺️ Roadmap

Known Limitations & Open Work

Not Yet Implemented

Integration Caveats (Dify)

Infrastructure

Documentation

Dependencies

Frequently Asked Questions

Contributing

License

About

Topics

Resources

License

Code of conduct

Contributing

Security policy

Uh oh!

Stars

Watchers

Forks

Releases 5

Sponsor this project

Uh oh!

Packages 0

Uh oh!

Contributors

Uh oh!

Languages

Packages