Agent Veil Protocol integration for AgentMesh trust engine
Project description
Agent Veil Protocol Integration for AgentMesh
Trust scoring for AgentMesh agents using Agent Veil Protocol — EigenTrust reputation, sybil resistance, and DID-based identity.
Features
- EigenTrust Scores — Map AVP reputation scores to AgentMesh trust engine
- Identity Verification — Verify agents via AVP's DID registry
- Full Reputation Profile — Access confidence, risk factors, attestation history
- Graceful Fallback — Returns safe defaults when AVP API is unreachable
Installation
pip install agentmesh-avp
Usage
from agentmesh.trust import TrustEngine
from agentmesh_avp import AVPProvider
# Create provider pointing to AVP API
provider = AVPProvider(
base_url="https://agentveil.dev",
# Optional: map agent IDs to AVP DIDs
did_resolver=my_resolver,
)
# Register with AgentMesh trust engine
engine = TrustEngine(external_providers=[provider])
# Get composite trust score (AgentMesh + AVP EigenTrust)
score = await engine.get_trust_score("did:key:z6MkAgent...")
API Reference
AVPProvider
| Method | Description |
|---|---|
get_trust_score(agent_id) |
Returns EigenTrust score (0.0-1.0) |
get_reputation(agent_id) |
Returns full profile (score, confidence, tier, risk) |
verify_identity(agent_id, credentials) |
Verifies agent via AVP DID registry |
Constructor Arguments
| Argument | Default | Description |
|---|---|---|
base_url |
https://agentveil.dev |
AVP server URL |
did_resolver |
None |
Maps agent_id to AVP DID string |
name_resolver |
None |
Maps agent_id to AVP agent name |
timeout |
10.0 |
HTTP timeout in seconds |
min_score_threshold |
0.3 |
Minimum score for score-based verification |
Limitations
- DID method: Only
did:keyidentifiers are supported. Other DID methods (did:web,did:ion, etc.) will be rejected by the DID format validator. - Fallback behavior: When the AVP verification endpoint is unreachable,
verify_identityfalls back to score-based verification usingmin_score_threshold. This is logged as a warning.
About Agent Veil Protocol
AVP is an open reputation layer for AI agents. 110+ agents in production, daily IPFS anchors, MIT-licensed SDK.
- agentveil.dev
- SDK on PyPI —
pip install agentveil - GitHub
Contributing
See the main CONTRIBUTING.md for guidelines.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file agentmesh_avp-0.1.1.tar.gz.
File metadata
- Download URL: agentmesh_avp-0.1.1.tar.gz
- Upload date:
- Size: 6.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
97c30c3ec7546055527af20a3915b5bf87efe435becbb96eee3d68f49f0f51cb
|
|
| MD5 |
2475db68b8d5e0b6748cc580acece001
|
|
| BLAKE2b-256 |
3edc99d4155dde819132a3a5d35b9d08f98e48e434c8bcd4923c52ef72083715
|
File details
Details for the file agentmesh_avp-0.1.1-py3-none-any.whl.
File metadata
- Download URL: agentmesh_avp-0.1.1-py3-none-any.whl
- Upload date:
- Size: 4.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d4c68db13f393fa7f79e9f781ec735c1bfbef2e63d49c42b0498fe0d5e920643
|
|
| MD5 |
1cdb90b9f448b3f680d8c8142821941d
|
|
| BLAKE2b-256 |
4318ccce335d953fb927b7f2d86575d2782a40a6807fcffc19c80185bd8afbfa
|