Issue Station
Sign In
Tools hereToolbox

crewai - ✅(Solved) Fix feat: DID-based agent identity and EU AI Act compliance credentials for crew agents [1 pull requests, 1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
crewAIInc/crewAI#5360•Fetched 2026-04-09 08:01:28
View on GitHub
Comments
0
Participants
1
Timeline
1
Reactions
0
Author
ascender1729ascender1729
Participants
ascender1729ascender1729
Timeline (top)
cross-referenced ×1

CrewAI assigns roles to agents that collaborate on tasks. When crews are deployed in EU-regulated industries, each agent role needs:

  1. A verifiable cryptographic identity (WHO is this agent?)
  2. Compliance documentation proving risk assessment was performed
  3. Delegation chains showing which agent authorized which action
  4. A tamper-evident audit trail of all crew task outputs

Root Cause

CrewAI assigns roles to agents that collaborate on tasks. When crews are deployed in EU-regulated industries, each agent role needs:

  1. A verifiable cryptographic identity (WHO is this agent?)
  2. Compliance documentation proving risk assessment was performed
  3. Delegation chains showing which agent authorized which action
  4. A tamper-evident audit trail of all crew task outputs

Fix Action

Fixed

PR fix notes

PR #41: feat: add 7 framework integration examples and 15 integration tests

Description (problem / solution / changelog)

Summary

Working integration examples for 7 major AI agent frameworks, each demonstrating the exact pattern proposed in the corresponding GitHub issue.

FrameworkExampleGitHub IssueTests
LangChainintegrations/examples/langchain_compliance.pylangchain-ai/langchain#366173
CrewAIintegrations/examples/crewai_compliance.pycrewAIInc/crewAI#53603
OpenAI Agentsintegrations/examples/openai_agents_compliance.pyopenai/openai-agents-python#28623
Semantic Kernelintegrations/examples/semantic_kernel_compliance.pymicrosoft/semantic-kernel#138531
Difyintegrations/examples/dify_compliance.pylanggenius/dify#347661
Google ADKintegrations/examples/google_adk_compliance.pygoogle/adk-python#52121
AWS Strandsintegrations/examples/strands_compliance.pystrands-agents/sdk-python#20963

All examples work without framework dependencies. 15 integration tests pass.

Test plan

  • All 7 examples run with exit code 0
  • 15 integration tests pass
  • 315 total tests pass (300 existing + 15 new)
  • No framework dependencies required
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->

Summary by CodeRabbit

  • New Features

    • Added example integrations demonstrating compliance workflows for CrewAI, Dify, Google ADK, LangChain, OpenAI Agents, Semantic Kernel, and Strands frameworks.
    • Introduced bulk HTML report generation for multi-agent compliance summaries.
    • Added digital signature verification section to compliance reports.
    • Enhanced credential reporting with proof type and verification method details.

  • Tests

    • Added comprehensive integration tests for all supported framework integrations.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

Changed files

  • integrations/examples/crewai_compliance.py (added, +561/-0)
  • integrations/examples/dify_compliance.py (added, +376/-0)
  • integrations/examples/google_adk_compliance.py (added, +527/-0)
  • integrations/examples/langchain_compliance.py (added, +502/-0)
  • integrations/examples/openai_agents_compliance.py (added, +496/-0)
  • integrations/examples/semantic_kernel_compliance.py (added, +619/-0)
  • integrations/examples/strands_compliance.py (added, +634/-0)
  • services/report_service.py (modified, +214/-2)
  • tests/integration/test_framework_integrations.py (added, +413/-0)
  • tests/unit/test_report.py (modified, +118/-0)

Code Example

from crewai import Agent, Task, Crew
from services.identity_service import IdentityService
from services.compliance_service import ComplianceService

identity_svc = IdentityService()
compliance_svc = ComplianceService()

# Each agent gets a DID-based cryptographic identity
researcher_identity = identity_svc.create_identity(
    display_name="ResearchAgent",
    capabilities=["web_search", "data_analysis"],
    issuer_name="AcmeCorp",
)

# Compliance profile with EU AI Act risk classification
compliance_svc.create_compliance_profile(
    agent_id=researcher_identity["agent_id"],
    risk_category="limited",  # Transparency obligations only
    provider_name="AcmeCorp",
    intended_purpose="Market research data collection",
)

# Every action logged to hash-chained audit trail
# Compliance credential auto-issued on conformity declaration
RAW_BUFFERClick to expand / collapse

Context

CrewAI assigns roles to agents that collaborate on tasks. When crews are deployed in EU-regulated industries, each agent role needs:

  1. A verifiable cryptographic identity (WHO is this agent?)
  2. Compliance documentation proving risk assessment was performed
  3. Delegation chains showing which agent authorized which action
  4. A tamper-evident audit trail of all crew task outputs

Problem

Currently a CrewAI agent's identity is a string (role name). There is no:

  • Cryptographic proof of agent identity
  • EU AI Act risk classification per agent role
  • Verifiable compliance credential attached to crew outputs
  • Hash-chained audit trail of task delegation and execution

Proposed Solution

A compliance layer using W3C Decentralized Identifiers (DIDs) and Verifiable Credentials:

from crewai import Agent, Task, Crew
from services.identity_service import IdentityService
from services.compliance_service import ComplianceService

identity_svc = IdentityService()
compliance_svc = ComplianceService()

# Each agent gets a DID-based cryptographic identity
researcher_identity = identity_svc.create_identity(
    display_name="ResearchAgent",
    capabilities=["web_search", "data_analysis"],
    issuer_name="AcmeCorp",
)

# Compliance profile with EU AI Act risk classification
compliance_svc.create_compliance_profile(
    agent_id=researcher_identity["agent_id"],
    risk_category="limited",  # Transparency obligations only
    provider_name="AcmeCorp",
    intended_purpose="Market research data collection",
)

# Every action logged to hash-chained audit trail
# Compliance credential auto-issued on conformity declaration

Each crew member carries a verifiable identity (DID) and compliance credential (W3C VC) that any counterparty can verify independently.

Available Implementation

Open-source MCP server: pip install attestix

  • 47 MCP tools across 9 modules (identity, compliance, credentials, delegation, reputation, provenance, DIDs, agent cards, blockchain)
  • CrewAI's native MCP support (mcps field) means this works out of the box
  • 13 EU AI Act articles automated, 291 tests
  • Apache 2.0

GitHub: https://github.com/VibeTensor/attestix Docs: https://attestix.io/docs

extent analysis

TL;DR

Implementing a compliance layer using W3C Decentralized Identifiers (DIDs) and Verifiable Credentials can address the lack of cryptographic proof of agent identity and compliance documentation.

Guidance

  • Integrate the attestix library using pip install attestix to leverage its 47 MCP tools for identity, compliance, and credentials management.
  • Utilize the IdentityService and ComplianceService classes to create DID-based cryptographic identities for agents and compliance profiles with EU AI Act risk classification.
  • Configure the mcps field in CrewAI to enable native MCP support and automate 13 EU AI Act articles.
  • Verify the implementation by checking the hash-chained audit trail and compliance credentials issued to crew members.

Example

researcher_identity = identity_svc.create_identity(
    display_name="ResearchAgent",
    capabilities=["web_search", "data_analysis"],
    issuer_name="AcmeCorp",
)

This code snippet demonstrates how to create a DID-based cryptographic identity for an agent using the IdentityService.

Notes

The proposed solution relies on the attestix library, which is open-source and available under the Apache 2.0 license. However, the implementation details may vary depending on the specific requirements of the CrewAI system and the EU-regulated industries it operates in.

Recommendation

Apply the proposed workaround by integrating the attestix library and implementing the compliance layer using W3C Decentralized Identifiers (DIDs) and Verifiable Credentials, as it provides a comprehensive solution to address the lack of cryptographic proof of agent identity and compliance documentation.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#retriever error#indexing error#inference speed#output truncation#response parsing

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING