Observed since 20 Oct, 21:31 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
agentavow-agt
AgentAvow (formerly agentgraph-agt) trust provider for Microsoft Agent Governance Toolkit
Formerly
agentgraph-agt. This distribution is now published asagentavow-agt. The import module is unchanged —import agentmesh_agentgraphstill works.
AgentAvow trust provider for the Microsoft Agent Governance Toolkit (AGT).
pip install agentavow-agt
AgentGraphTrustProvider implements the duck-typed external-provider interface
AGT's TrustEngine expects. Hand it to the engine and AgentAvow becomes one of
its trust signals:
from agentmesh_agentgraph import AgentGraphTrustProvider
provider = AgentGraphTrustProvider(
api_url="https://agentavow.com/api/v1", # this is the built-in default; pass your own host to override
api_key=None, # optional bearer token for authenticated reads
timeout=10.0,
)
engine = TrustEngine(external_providers=[provider]) # AGT's engine
score = await engine.get_trust_score("agent-id-here")
Or call it directly:
# Normalized 0.0-1.0 trust score (0.5 when the agent is unknown or the API is unreachable)
score = await provider.get_trust_score("agent-id-here")
# Sybil-risk estimate from identity verification + external accounts + community signals
sybil = await provider.check_sybil("agent-id-here")
# -> {"risk": "low" | "medium" | "high" | "unknown", "confidence": 0.0-1.0, ...}
# Direct trust connections (depth-1 ego graph)
circle = await provider.get_trust_circle("agent-id-here") # list[str] of entity ids
# True when the entity exists and its identity is verified (email, operator link, or OAuth)
ok = await provider.verify_identity("agent-id-here")
await provider.close()
| Method | Returns | AgentAvow endpoint |
|---|---|---|
get_trust_score(agent_id) | float 0.0-1.0 | GET /entities/{id}/trust |
check_sybil(agent_id) | dict (risk, confidence, identity_verified, external_accounts, community_attestations) | GET /entities/{id}/trust |
get_trust_circle(agent_id) | list[str] | GET /graph/ego/{id}?depth=1 |
verify_identity(agent_id, credentials=None) | bool | GET /entities/{id}/trust |
close() | — | closes the HTTP client |
Every method fails soft (default score, "unknown" risk, empty circle, False)
and logs a warning rather than raising, so a network error never blocks AGT.
This adapter implements the AGT external trust-provider interface, allowing AgentAvow's trust scores to be used as a governance signal in Microsoft's Agent Governance Toolkit. It queries the AgentAvow API for trust scores, their component breakdown, the social graph, and identity-verification status.
MIT
Download counts and popularity will appear here as the collector receives them.
| Package / target | Requirement | Relationship |
|---|---|---|
httpxEnvironment{
"extras": "",
"marker": null,
"requires_python": ">=3.9",
"evaluation": "NOT_EVALUATED"
} | httpx>=0.25 | runtime |
pytest-asyncioEnvironment{
"extras": "",
"marker": "extra == \"dev\"",
"requires_python": ">=3.9",
"evaluation": "NOT_EVALUATED"
} | pytest-asyncio>=0.21; extra == "dev" | runtime |
pytestEnvironment{
"extras": "",
"marker": "extra == \"dev\"",
"requires_python": ">=3.9",
"evaluation": "NOT_EVALUATED"
} | pytest>=7.0; extra == "dev" | runtime |
bdist_wheel · 4.45 KB · Python py3
sdist · 4.3 KB · Python source
Observed since 20 Oct, 21:31 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
package_version:6faf2d17b059d1384a6188ce9cbfc95d9600c76aa1fc774d43aea1e4958e1cab