Catalog PyPI
PACKAGE EXPLORERView in registry

agentmesh_runtime

PyPI

Public Preview — AgentMesh Runtime: Execution supervisor for multi-agent sessions with privilege rings, saga orchestration, and audit trails

agentsaiauditexecution-ringsgovernancehash-chainliabilitymulti-agentruntimesafetysagashared-sessionstrust
Versions collected1
Direct dependencies2From release 3.7.0
Last observed20 Oct, 22:43 UTC

README

Version 3.7.0 documentation

AgentMesh Runtime

Execution supervisor for multi-agent sessions — privilege rings, saga orchestration, and governance enforcement

Part of the Agent Governance Toolkit

CI License Python PyPI

[!IMPORTANT] Public Preview — The agentmesh-runtime package on PyPI is a Microsoft-signed public preview release. APIs may change before GA.


Note: This package was renamed from agent-runtime to agentmesh-runtime to avoid a PyPI name collision with the AutoGen team's package. The agent-hypervisor package remains the canonical upstream implementation; agentmesh-runtime is a thin re-export wrapper for incremental import migration.

What is Agent Runtime?

Agent Runtime provides execution-level supervision for autonomous AI agents. While Agent OS handles policy decisions and AgentMesh handles trust/identity, Agent Runtime enforces those decisions at the session level:

  • Execution Rings — 4-tier privilege model (Ring 0–3) controlling what agents can do at runtime
  • Shared Sessions — Multi-agent session management with consistency modes (strict, eventual, causal)
  • Saga Orchestration — Compensating transactions for multi-step agent workflows
  • Kill Switch — Immediate termination with audit trail and blast radius containment
  • Joint Liability — Attribution tracking across multi-agent collaborations
  • Audit Trails — Hash-chained, append-only execution logs

Quick Start

pip install agentmesh-runtime
from hypervisor import Hypervisor, SessionConfig, ConsistencyMode

# Create the runtime supervisor
hv = Hypervisor()

# Create a governed session
session = await hv.create_session(
    config=SessionConfig(consistency_mode=ConsistencyMode.EVENTUAL)
)

# Execute with privilege enforcement
result = await session.execute(
    agent_id="researcher-1",
    action="tool_call",
    tool="web_search",
    ring=2  # restricted privilege ring
)

Architecture

┌─────────────────────────────────────────────────────────────────────┐
│                        Agent Runtime                                 │
├─────────────┬──────────────────┬──────────────────┬─────────────────┤
│  Execution  │     Session      │      Saga        │    Liability    │
│   Rings     │   Management     │  Orchestration   │    Tracking     │
│             │                  │                  │                 │
│  Ring 0:    │  Create/join     │  Multi-step      │  Attribution    │
│   System    │  Consistency     │  Compensation    │  Vouching       │
│  Ring 1:    │  Checkpoints     │  Rollback        │  Slashing       │
│   Trusted   │  Merge/fork      │  Recovery        │  Quarantine     │
│  Ring 2:    │                  │                  │                 │
│   Standard  │                  │                  │                 │
│  Ring 3:    │                  │                  │                 │
│   Sandboxed │                  │                  │                 │
└─────────────┴──────────────────┴──────────────────┴─────────────────┘

Ecosystem

Agent Runtime is one of 7 packages in the Agent Governance Toolkit:

PackageRole
Agent OSPolicy engine — deterministic action evaluation
AgentMeshTrust infrastructure — identity, credentials, protocol bridges
AgentMesh RuntimeExecution supervisor — rings, sessions, sagas (this package)
Agent SREReliability — SLOs, circuit breakers, chaos testing
Agent ComplianceRegulatory compliance — GDPR, HIPAA, SOX frameworks
Agent MarketplacePlugin lifecycle — discover, install, verify, sign
Agent LightningRL training governance — governed runners, policy rewards

License

MIT — see LICENSE.

Downloads & popularity

Awaiting observations

No metric observations yet

Download counts and popularity will appear here as the collector receives them.

Versions 1

Collected releases
VersionPublishedDirect dependenciesOpen version
3.7.018 May 20262

Package advisories

0
No matching advisories collected

This describes our collected data; it is not a security assessment.

Repository

PENDING
microsoft/agent-governance-toolkit

Shared repository data · GitHub

License detected in repository
Not collected

Metadata history

Meaningful changes
Current collected state Current

Observed since 20 Oct, 22:43 UTC

No superseded metadata states collected. Unchanged observations do not create new revisions.

Record identity

package:b138f50b6965a6dd4254c85dc23dada92616b914e1b94a0327e7da512faf165f