Attestix

AI 与智能体

by vibetensor

提供AI agent identity、W3C credentials和EU AI Act合规支持,内置47个MCP工具。

什么是 Attestix

提供AI agent identity、W3C credentials和EU AI Act合规支持,内置47个MCP工具。

README

<!-- mcp-name: io.github.VibeTensor/attestix --> <p align="center"> <img src="https://raw.githubusercontent.com/VibeTensor/attestix/main/docs/assets/atx_icon.png" alt="Attestix" width="120" height="120" /> </p> <h1 align="center">Attestix</h1> <p align="center"> <strong>Compliance Automation for AI Agents</strong> </p> <p align="center"> <a href="https://github.com/VibeTensor/attestix/actions/workflows/test.yml"><img src="https://img.shields.io/github/actions/workflow/status/VibeTensor/attestix/test.yml?branch=main&label=tests&style=flat-square" alt="CI"></a> <a href="https://github.com/VibeTensor/attestix/actions/workflows/lint.yml"><img src="https://img.shields.io/github/actions/workflow/status/VibeTensor/attestix/lint.yml?branch=main&label=lint&style=flat-square" alt="Lint"></a> <a href="https://github.com/VibeTensor/attestix/actions/workflows/security.yml"><img src="https://img.shields.io/github/actions/workflow/status/VibeTensor/attestix/security.yml?branch=main&label=security&style=flat-square" alt="Security"></a> <a href="https://codecov.io/gh/VibeTensor/attestix"><img src="https://img.shields.io/codecov/c/github/VibeTensor/attestix?style=flat-square" alt="Coverage"></a> <a href="https://pypi.org/project/attestix/"><img src="https://img.shields.io/pypi/v/attestix?color=4f46e5&style=flat-square" alt="PyPI"></a> <a href="https://pypi.org/project/attestix/"><img src="https://img.shields.io/pypi/pyversions/attestix?color=4f46e5&style=flat-square" alt="Python"></a> <a href="https://pypi.org/project/attestix/"><img src="https://img.shields.io/pypi/dm/attestix?color=4f46e5&style=flat-square" alt="Downloads"></a> <a href="https://github.com/VibeTensor/attestix/blob/main/LICENSE"><img src="https://img.shields.io/github/license/VibeTensor/attestix?color=4f46e5&style=flat-square" alt="License"></a> <a href="https://attestix.io/docs"><img src="https://img.shields.io/badge/docs-attestix.io%2Fdocs-4f46e5?style=flat-square" alt="Docs"></a> <a href="https://attestix.io"><img src="https://img.shields.io/badge/website-attestix.io-4f46e5?style=flat-square" alt="Website"></a> </p> <p align="center"> Make your AI agents EU AI Act compliant with cryptographically verifiable proof.<br/> Open-source identity, credentials, compliance automation, and trust scoring.<br/> 47 MCP tools across 9 modules, 44 REST API endpoints, 531-test suite (440 functional + 91 RFC / W3C conformance benchmarks).<br/> Real integrations with LangChain, OpenAI Agents SDK, and CrewAI. </p> <p align="center"> <em>Status: v0.4.0 stable (pre-release 0.4.1rc1 available via the --pre channel). Single-maintainer project, community contributions welcome. No independent third-party security audit has been performed yet; deploy with the same diligence you would apply to any pre-1.0 open-source crypto stack.</em> </p>

Install

bash
# Stable 0.4.0:
pip install attestix

# Pre-release 0.4.1rc1 (opt in with --pre):
pip install --pre attestix

Stable 0.4.0 ships only the canonical attestix.* namespace. The older flat layout (from services... import, from auth... import, ...) keeps working via thin deprecation shims that emit a DeprecationWarning on first import and are scheduled for removal in v0.5.0. Update imports to from attestix.services... import at your earliest convenience.

CLI

bash
attestix status                          # System overview
attestix init --name MyBot               # Create agent identity
attestix compliance <agent-id>           # Check EU AI Act compliance
attestix verify <agent-id>               # Verify identity cryptographically
attestix audit <agent-id>                # View hash-chained audit trail
attestix credential --list               # List W3C Verifiable Credentials

REST API

bash
pip install fastapi uvicorn
uvicorn attestix.api.main:app --reload   # Swagger docs at http://localhost:8000/docs

Web Dashboard

bash
pip install streamlit
streamlit run demo/webapp/app.py         # Opens at http://localhost:8501

Quick Demo

bash
python examples/quickstart.py            # Full 9-module workflow in 0.1 seconds

Verify in any language

Attestix credentials are issued once (Python core or cloud) and verify anywhere. Six independent verifier implementations share one conformance suite (spec/verify/v1): verify offline, no Python runtime, zero trust in the issuer. The verifiers are verifier-only: issuance stays in the Python core.

LanguageInstallStatus
Pythonpip install attestixlive (full lib: issue + verify)
JS / TSnpm install attestixlive (attestix-js)
Gogo get github.com/VibeTensor/attestix-golive (attestix-go)
Rustcargo add attestixlive (attestix-rs)
Javacom.vibetensor:attestix:0.4.0publishing soon (attestix-java)
Rinstall.packages("attestix")coming to CRAN (attestix-r)

Every verifier checks the same canonical-JSON form (RFC 8785) and Ed25519 signatures (RFC 8032) against the shared spec/verify/v1 vectors. Verify in the browser at https://attestix.io/verify, or read the bundle wire-format at https://attestix.io/spec/bundle/v1.

Why Attestix

On August 2, 2026, the EU AI Act enforcement begins. Fines reach EUR 35M or 7% of global revenue.

Existing compliance tools (Credo AI, Holistic AI, Vanta) are organizational dashboards. None produce machine-readable, cryptographically verifiable proof that an AI agent can present to another agent, regulator, or system.

Agent identity is fragmenting across walled gardens (Microsoft Entra, AWS AgentCore, Google A2A, ERC-8004). No single tool combines agent identity + EU AI Act compliance + verifiable credentials in one protocol.

Attestix fills this gap.


Modules

ModuleToolsWhat it does
Identity8Unified Agent Identity Tokens (UAITs) bridging MCP OAuth, A2A, DIDs, and API keys. GDPR Article 17 erasure
Agent Cards3Parse, generate, and discover A2A-compatible agent cards
DID3Create and resolve W3C Decentralized Identifiers (did:key, did:web)
Delegation4UCAN-style capability delegation with EdDSA-signed JWT tokens
Reputation3Recency-weighted trust scoring (0.0 - 1.0) with category breakdown
Compliance7EU AI Act risk profiles, conformity assessments (Article 43), Annex V declarations
Credentials8W3C Verifiable Credentials with Ed25519Signature2020 proofs, presentations
Provenance5Training data provenance (Article 10), model lineage (Article 11), hash-chained audit trail (Article 12)
Blockchain6Anchor artifact hashes to Base L2 via Ethereum Attestation Service, Merkle batching

Quick Start

As an MCP Server (Claude Code)

Add to your Claude Code config (~/.claude.json):

json
{
  "mcpServers": {
    "attestix": {
      "type": "stdio",
      "command": "python",
      "args": ["-m", "attestix.main"]
    }
  }
}

Then ask Claude:

"Create an identity for my data analysis agent with capabilities: data_analysis, reporting"

As a Python Library

python
from attestix.services.identity_service import IdentityService
from attestix.services.compliance_service import ComplianceService
from attestix.services.credential_service import CredentialService

identity_svc = IdentityService()
compliance_svc = ComplianceService()
credential_svc = CredentialService()

# 1. Create an agent identity
agent = identity_svc.create_identity(
    display_name="MyAgent",
    source_protocol="manual",
    capabilities=["data_analysis", "reporting"],
    description="Analyzes quarterly financial data",
    issuer_name="VibeTensor",
    expiry_days=365,
)
agent_id = agent["agent_id"]      # attestix:f9bdb7a94ccb40f1
agent_did = agent["issuer"]["did"]  # did:key:z6Mk...

# 2. Create a compliance profile
profile = compliance_svc.create_compliance_profile(
    agent_id=agent_id,
    risk_category="limited",
    provider_name="VibeTensor",
    intended_purpose="Analyzes quarterly financial data",
)

# 3. Issue a verifiable credential
credential = credential_svc.issue_credential(
    subject_id=agent_id,
    credential_type="AgentIdentityCredential",
    issuer_name="VibeTensor",
    claims={"capabilities": ["data_analysis", "reporting"]},
    expiry_days=365,
)
print(credential["proof"]["type"])  # Ed25519Signature2020

For a complete end-to-end walkthrough covering all 9 modules, run the quickstart:

bash
python examples/quickstart.py

From Source

bash
git clone https://github.com/VibeTensor/attestix.git
cd attestix
pip install -r requirements.txt
python -m attestix.main

EU AI Act Compliance Workflow

Take a high-risk AI agent from zero to fully compliant:

code
1. create_agent_identity        --> UAIT with DID (Ed25519 signed)
2. record_training_data         --> Article 10 data governance
3. record_model_lineage         --> Article 11 technical documentation
4. create_compliance_profile    --> Risk categorization + obligations
5. record_conformity_assessment --> Article 43 third-party assessment
6. generate_declaration_of_conformity --> Annex V declaration + W3C VC
7. create_verifiable_presentation     --> Signed VP for regulator

High-risk systems are blocked from self-assessment:

code
record_conformity_assessment(assessment_type="self", ...)
--> ERROR: "High-risk AI systems require third_party conformity assessment"

Full walkthrough: EU AI Act Compliance Guide


How It Works

Every artifact Attestix produces is cryptographically signed with Ed25519:

ArtifactStandardSigned
Agent Identity (UAIT)Custom + DIDEd25519
Verifiable CredentialW3C VC Data Model 1.1Ed25519Signature2020
Verifiable PresentationW3C VPEd25519Signature2020
Delegation TokenUCAN-style JWTEdDSA
Compliance RecordsEU AI Act Annex VEd25519
Audit TrailHash-chained logSHA-256 chain
Blockchain AnchorEAS on Base L2On-chain

No cloud dependency. All core operations work offline with local JSON storage.


Architecture

code
attestix/                  # Canonical Python package (v0.4.0)
  main.py                  # MCP server entry point (47 tools)
  cli.py                   # `attestix` console script
  config.py                # Environment-based configuration
  errors.py                # Error handling with JSON logging
  api/                     # FastAPI REST surface
    main.py                # uvicorn entry: `attestix.api.main:app`
    routers/               # one router per service (44 endpoints)
  auth/
    crypto.py              # Ed25519 key management
    ssrf.py                # SSRF protection for outbound HTTP
  services/
    identity_service.py    # UAIT lifecycle, GDPR erasure
    agent_card_service.py  # A2A agent card operations
    did_service.py         # DID creation and resolution
    delegation_service.py  # UCAN delegation tokens
    reputation_service.py  # Trust scoring
    compliance_service.py  # EU AI Act profiles and assessments
    credential_service.py  # W3C VCs and VPs
    provenance_service.py  # Training data, lineage, audit trail
    blockchain_service.py  # Base L2 anchoring via EAS
  storage/                 # Repository seam (file / memory / pg)
  signing/                 # Signer seam (in-process / kms)
  audit/                   # Tamper-evident event chain
  tenancy/                 # Tenant context
  idempotency/             # Stripe-style idempotency keys + middleware
  blockchain/
    merkle.py              # Merkle tree for batch anchoring
  tools/                   # MCP tool definitions (one file per module)

The pre-v0.4.0 flat layout (services/, auth/, storage/, ...) is preserved as deprecation shims at the same paths. They re-export from the canonical attestix.* namespace and emit a DeprecationWarning on first import. The shims are scheduled for removal in v0.5.0.


All 47 Tools

<details> <summary><strong>Identity</strong> (8 tools)</summary>
ToolDescription
create_agent_identityCreate a UAIT from any identity source
resolve_identityAuto-detect token type and register
verify_identityCheck existence, revocation, expiry, signature
translate_identityConvert to A2A, DID Document, OAuth, or summary
list_identitiesList UAITs with protocol/revocation filters
get_identityGet full UAIT details
revoke_identityMark a UAIT as revoked
purge_agent_dataGDPR Article 17 right to erasure across all stores
</details> <details> <summary><strong>Agent Cards</strong> (3 tools)</summary>
ToolDescription
parse_agent_cardParse an A2A Agent Card JSON
generate_agent_cardGenerate agent.json for hosting
discover_agentFetch /.well-known/agent.json from a URL
</details> <details> <summary><strong>DID</strong> (3 tools)</summary>
ToolDescription
create_did_keyGenerate ephemeral did:key with Ed25519 keypair
create_did_webGenerate did:web DID Document for self-hosting
resolve_didResolve any DID to its DID Document
</details> <details> <summary><strong>Delegation</strong> (4 tools)</summary>
ToolDescription
create_delegationUCAN-style capability delegation token
verify_delegationVerify JWT signature, expiry, structure
list_delegationsList delegations by agent and role
revoke_delegationRevoke a delegation token
</details> <details> <summary><strong>Reputation</strong> (3 tools)</summary>
ToolDescription
record_interactionRecord outcome and update trust score
get_reputationGet score with category breakdown
query_reputationSearch agents by reputation criteria
</details> <details> <summary><strong>Compliance</strong> (7 tools)</summary>
ToolDescription
create_compliance_profileCreate EU AI Act profile with risk categorization
get_compliance_profileRetrieve full compliance profile
update_compliance_profileUpdate an existing compliance profile
get_compliance_statusGap analysis: completed vs missing requirements
record_conformity_assessmentRecord self or third-party assessment (Article 43)
generate_declaration_of_conformityGenerate Annex V declaration + auto-issue VC
list_compliance_profilesFilter by risk category and compliance status
</details> <details> <summary><strong>Credentials</strong> (8 tools)</summary>
ToolDescription
issue_credentialIssue W3C VC with Ed25519Signature2020 proof
verify_credentialCheck signature, expiry, revocation
verify_credential_externalVerify any VC JSON from an external source
revoke_credentialRevoke a Verifiable Credential
get_credentialGet full VC details
list_credentialsFilter by agent, type, validity
create_verifiable_presentationBundle VCs into a signed VP for a verifier
verify_presentationVerify a VP with embedded credentials
</details> <details> <summary><strong>Provenance</strong> (5 tools)</summary>
ToolDescription
record_training_dataRecord training data source (Article 10)
record_model_lineageRecord model chain and metrics (Article 11)
log_actionLog agent action with hash-chained audit trail (Article 12)
get_provenanceGet full provenance record
get_audit_trailQuery audit log with filters
</details> <details> <summary><strong>Blockchain</strong> (6 tools)</summary>
ToolDescription
anchor_identityAnchor identity hash to Base L2 via EAS
anchor_credentialAnchor credential hash to Base L2 via EAS
anchor_audit_batchMerkle batch anchor of audit log entries
verify_anchorVerify an on-chain anchor against local data
get_anchor_statusGet anchoring status for an artifact
estimate_anchor_costEstimate gas cost for anchoring
</details>

Standards Conformance

Every standards claim is validated by 91 automated conformance benchmarks that run alongside the rest of the suite for a total of 531 tests passing (1 skipped on Windows). These benchmarks demonstrate cryptographic conformance with the listed standards; they are not a substitute for a legal compliance audit. Run them yourself:

bash
docker build -f Dockerfile.test -t attestix-bench . && docker run --rm attestix-bench
StandardWhat is testedTests
RFC 8032 (Ed25519)4 IETF canonical vectors: key derivation, signature generation (exact match), verification, tamper rejection18
W3C VC Data Model 1.1Credential structure, Ed25519Signature2020 proof, mutable field exclusion, VP structure, replay protection25
W3C DID Core 1.0did:key and did:web document structure, roundtrip resolution, Ed25519VerificationKey202018
UCAN v0.9.0JWT header (alg/typ/ucv), all payload fields, capability attenuation, expiry enforcement, revocation18
MCP Protocol47 tools registered, 9 modules, async convention, snake_case naming5
PerformanceEd25519 key gen, JSON canonicalization, sign/verify, identity creation, credential ops7

Performance (median latency, 1000 runs)

OperationLatency
Ed25519 key generation0.08 ms
JSON canonicalization0.02 ms
Ed25519 sign + verify0.28 ms
Identity creation~14 ms
Credential issuance~17 ms
Credential verification~2 ms
UCAN token creation~9 ms

Security

  • Ed25519 signatures on all UAITs, VCs, assessments, declarations, and audit entries
  • Hash-chained audit trail with SHA-256 for tamper-evident logging
  • SSRF protection blocks private IPs, metadata endpoints, and DNS rebinding
  • Encrypted key storage with AES-256-GCM when ATTESTIX_KEY_PASSWORD is set
  • Private keys never exposed in tool responses
  • No external API calls required for core operations

Research Paper

Attestix is described in a research paper covering system architecture, cryptographic pipeline, EU AI Act compliance automation, and evaluation with 531 automated tests (440 functional + 91 RFC / W3C conformance benchmarks).

Attestix: A Unified Attestation Infrastructure for Autonomous AI Agents Pavan Kumar Dubasi, VibeTensor Private Limited, 2026.

Citing Attestix

If you use Attestix in your research, please cite:

bibtex
@article{dubasi2026attestix,
  title     = {Attestix: A Unified Attestation Infrastructure for Autonomous AI Agents},
  author    = {Dubasi, Pavan Kumar},
  year      = {2026},
  url       = {https://github.com/VibeTensor/attestix},
  note      = {Open-source. Apache License 2.0}
}

Documentation

Full documentation at attestix.io/docs

GuideDescription
Getting StartedInstallation and first identity in 5 minutes
EU AI Act ComplianceStep-by-step compliance workflow
Risk ClassificationHow to determine your AI system's risk category
ArchitectureSystem design and data flows
API ReferenceAll 47 tools with parameter tables
Integration GuideLangChain, OpenAI Agents SDK, CrewAI, MCP client
ConfigurationEnvironment variables, storage, Docker
Research PaperPaper, citation formats, evaluation highlights
Reputation ScoringRecency-weighted trust scoring and categories
ExamplesEnd-to-end code examples for common workflows

Disclaimer

Attestix generates machine-readable, cryptographically signed compliance documentation. It is a documentation and evidence tooling system. It does not replace legal counsel, notified body assessments, or official regulatory submissions. Always consult qualified legal professionals for compliance decisions.


Sponsors

Attestix is free and open-source. If you or your organization benefit from it, please consider sponsoring to support continued development, security audits, and infrastructure.

<a href="https://github.com/sponsors/VibeTensor"><img src="https://img.shields.io/badge/Sponsor-GitHub%20Sponsors-ea4aaa?style=flat-square&logo=github" alt="GitHub Sponsors" /></a>


Contributing

See CONTRIBUTING.md for development setup and guidelines.

License

Apache License 2.0. See LICENSE.


<p align="center"> <a href="https://vibetensor.com"> <img src="https://raw.githubusercontent.com/VibeTensor/attestix/main/docs/assets/atx_gold.svg" alt="Attestix" width="48" /> </a> </p> <p align="center"> Built by <a href="https://vibetensor.com">VibeTensor</a> </p>

常见问题

Attestix 是什么?

提供AI agent identity、W3C credentials和EU AI Act合规支持,内置47个MCP工具。

相关 Skills

Claude接口

by anthropics

Universal
热门

面向接入 Claude API、Anthropic SDK 或 Agent SDK 的开发场景,自动识别项目语言并给出对应示例与默认配置,快速搭建 LLM 应用。

想把Claude能力接进应用或智能体,用claude-api上手快、兼容Anthropic与Agent SDK,集成路径清晰又省心

AI 与智能体
未扫描164.6k

RAG架构师

by alirezarezvani

Universal
热门

聚焦生产级RAG系统设计与优化,覆盖文档切块、检索链路、索引构建、召回评估等关键环节,适合搭建可扩展、高准确率的知识库问答与检索增强应用。

面向RAG落地,把知识库、向量检索和生成链路系统串联起来,做架构设计时更清晰,也更少踩坑。

AI 与智能体
未扫描23.3k

多智能体架构

by alirezarezvani

Universal
热门

聚焦多智能体系统架构设计,梳理 Supervisor、Swarm、分层和 Pipeline 等模式,覆盖角色定义、通信协作与性能评估,适合规划稳健可扩展的 AI agent 编排方案。

帮你系统解决多智能体应用的架构设计与协同编排难题,适合构建复杂 AI 工作流,成熟度高、社区认可也很亮眼。

AI 与智能体
未扫描23.3k

相关 MCP Server

知识图谱记忆

编辑精选

by Anthropic

热门

Memory 是一个基于本地知识图谱的持久化记忆系统,让 AI 记住长期上下文。

帮 AI 和智能体补上“记不住”的短板,用本地知识图谱沉淀长期上下文,连续对话更聪明,数据也更可控。

AI 与智能体
89.0k

顺序思维

编辑精选

by Anthropic

热门

Sequential Thinking 是让 AI 通过动态思维链解决复杂问题的参考服务器。

这个服务器展示了如何让 Claude 像人类一样逐步推理,适合开发者学习 MCP 的思维链实现。但注意它只是个参考示例,别指望直接用在生产环境里。

AI 与智能体
88.1k

by deusdata

热门

持久化的代码库知识图谱,可跨会话保留上下文,在 session 重启或上下文压缩后仍能继续使用。

专治 AI 编程助手“会话失忆”,把代码库沉淀为持久知识图谱,重启或压缩上下文后也能无缝续上开发状态。

AI 与智能体
26.9k

评论