PkgFoundry
Catalog PyPI
Back to packageRELEASE DETAILS

0.6.1

PyPI

agent-failsafe

FailSafe governance adapter for Microsoft Agent Governance Toolkit

agentfailsafegovernancesecuritytrust
Published3 Jun 2026
Direct dependencies7
Transitive dependenciesNot calculated

README

Version 0.6.1 documentation

agent-failsafe

PyPI Downloads Python License VS Code

FailSafe governance adapter for the Microsoft Agent Governance Toolkit.

agent-failsafe is a Python adapter that connects the FailSafe runtime governance engine to the Microsoft Agent Governance Toolkit.

• Adds runtime behavioral governance to the toolkit • Detects failure patterns such as tool recursion and reasoning collapse • Integrates through interceptors, validators, and policy providers • Install with pip install agent-failsafe

Core runtime: https://github.com/MythologIQ/Failsafe

Installation

# Core only (types, clients, patterns, trust scoring)
pip install agent-failsafe

# With specific toolkit packages
pip install agent-failsafe[agent-os]          # Interceptor + Integration + Webhook events
pip install agent-failsafe[agent-sre]         # SLI + Signal generation
pip install agent-failsafe[agent-mesh]        # Audit sink
pip install agent-failsafe[agent-hypervisor]  # ExecutionRing + KillSwitch

# Everything
pip install agent-failsafe[full]

The public extras above keep their names, but resolve to the consolidated Microsoft Agent Governance Toolkit 4.x packages: agent-os, agent-mesh, and agent-hypervisor pull agent-governance-toolkit-core (>=4.0.0,<5.0), while agent-sre pulls agent-governance-toolkit-cli (>=4.0.0,<5.0). full (and dev) install the union of both consolidated packages.

Extension Points

AdapterToolkit Extension PointModule
FailSafeInterceptorToolCallInterceptorinterceptor.py
FailSafeKernelBaseIntegration + @register_adapterintegration.py
GovernancePipelineFull lifecycle orchestrationpipeline.py
FailSafeRingAdapterExecutionRing + KillSwitchring_adapter.py
FailSafeTrustValidatorValidatorInterface (control plane)trust_validator.py
ShadowGenomePolicyProviderPolicyProviderInterfacepolicy_provider.py
FailSafeComplianceSLISLI (agent-sre)sli.py
FailSafeAuditSinkAuditSinkaudit_sink.py
FailSafeApprovalBackendApprovalBackendescalation.py
FailSafeTrustMapperDID translation (did:myth <> did:mesh)trust_mapper.py
decision_to_webhook_eventWebhookEvent translationwebhook_events.py

Architecture Diagram

AI Agent
↓
Agent Governance Toolkit
↓
agent-failsafe adapter
↓
FailSafe runtime engine
↓
Tool execution

Basic Usage Example

Basic interceptor example

from agent_failsafe import FailSafeInterceptor

interceptor = FailSafeInterceptor()
result = interceptor.intercept(request)

from agent_failsafe import FailSafeInterceptor

interceptor = FailSafeInterceptor()
result = interceptor.intercept(request)

See docs/ADAPTER_ARCHITECTURE.md for full API reference.

Ecosystem

FailSafe runtime engine https://github.com/MythologIQ/Failsafe

Developer extension https://marketplace.visualstudio.com/items?itemName=MythologIQ.mythologiq-failsafe https://open-vsx.org/extension/MythologIQ/mythologiq-failsafe

Recommended GitHub Topics

  • ai-agents
  • agent-governance
  • agentic-ai
  • ai-runtime
  • ai-reliability
  • llm-agents
  • ai-infrastructure
  • open-source

License

MIT

Downloads & popularity

Awaiting observations

No metric observations yet

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

Declared dependencies 13

Native requirements
7 direct targetsNot calculated transitive count
Package / targetRequirementRelationship
fastapi
Environment
{
  "extras": "",
  "marker": "extra == \"server\"",
  "requires_python": ">=3.11",
  "evaluation": "NOT_EVALUATED"
}
fastapi>=0.100.0; extra == "server"runtime
uvicorn
Environment
{
  "extras": "",
  "marker": "extra == \"server\"",
  "requires_python": ">=3.11",
  "evaluation": "NOT_EVALUATED"
}
uvicorn>=0.20.0; extra == "server"runtime
pyyaml
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.11",
  "evaluation": "NOT_EVALUATED"
}
pyyaml>=6.0runtime
agent-governance-toolkit-core
Environment
{
  "extras": "",
  "marker": "extra == \"agent-hypervisor\"",
  "requires_python": ">=3.11",
  "evaluation": "NOT_EVALUATED"
}
agent-governance-toolkit-core<5.0,>=4.0.0; extra == "agent-hypervisor"runtime
agent-governance-toolkit-core
Environment
{
  "extras": "",
  "marker": "extra == \"agent-mesh\"",
  "requires_python": ">=3.11",
  "evaluation": "NOT_EVALUATED"
}
agent-governance-toolkit-core<5.0,>=4.0.0; extra == "agent-mesh"runtime
agent-governance-toolkit-core
Environment
{
  "extras": "",
  "marker": "extra == \"agent-os\"",
  "requires_python": ">=3.11",
  "evaluation": "NOT_EVALUATED"
}
agent-governance-toolkit-core<5.0,>=4.0.0; extra == "agent-os"runtime
agent-governance-toolkit-cli
Environment
{
  "extras": "",
  "marker": "extra == \"agent-sre\"",
  "requires_python": ">=3.11",
  "evaluation": "NOT_EVALUATED"
}
agent-governance-toolkit-cli<5.0,>=4.0.0; extra == "agent-sre"runtime
agent-governance-toolkit-cli
Environment
{
  "extras": "",
  "marker": "extra == \"dev\"",
  "requires_python": ">=3.11",
  "evaluation": "NOT_EVALUATED"
}
agent-governance-toolkit-cli<5.0,>=4.0.0; extra == "dev"runtime
agent-governance-toolkit-core
Environment
{
  "extras": "",
  "marker": "extra == \"dev\"",
  "requires_python": ">=3.11",
  "evaluation": "NOT_EVALUATED"
}
agent-governance-toolkit-core<5.0,>=4.0.0; extra == "dev"runtime
pytest
Environment
{
  "extras": "",
  "marker": "extra == \"dev\"",
  "requires_python": ">=3.11",
  "evaluation": "NOT_EVALUATED"
}
pytest>=7.0; extra == "dev"runtime
ruff
Environment
{
  "extras": "",
  "marker": "extra == \"dev\"",
  "requires_python": ">=3.11",
  "evaluation": "NOT_EVALUATED"
}
ruff>=0.1.0; extra == "dev"runtime
agent-governance-toolkit-cli
Environment
{
  "extras": "",
  "marker": "extra == \"full\"",
  "requires_python": ">=3.11",
  "evaluation": "NOT_EVALUATED"
}
agent-governance-toolkit-cli<5.0,>=4.0.0; extra == "full"runtime
agent-governance-toolkit-core
Environment
{
  "extras": "",
  "marker": "extra == \"full\"",
  "requires_python": ">=3.11",
  "evaluation": "NOT_EVALUATED"
}
agent-governance-toolkit-core<5.0,>=4.0.0; extra == "full"runtime

Distribution files

2 collected
agent_failsafe-0.6.1-py3-none-any.whl

bdist_wheel · 47.86 KB · Python py3

Source file
agent_failsafe-0.6.1.tar.gz

sdist · 96.87 KB · Python source

Source file

Repository

PENDING
mythologiq/agent-failsafe

Shared repository data · GitHub

License detected in repository
Not collected

Metadata history

Meaningful changes
Current collected state Current

Observed since 20 Oct, 21:54 UTC

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

Record identity

package_version:8d7d216a0e4f1df38ae3d93235cc8bb063ea6f3d9ee71f2f28db65d11ad8b225

Other collected versions

View all collected versions →