AIActGuard

Drop-in EU AI Act compliance for any agent framework — audit trails, risk classification, and human-approval gates in one decorator.

AIActGuard is a lightweight middleware layer that any existing agent stack can adopt without ripping out its framework. It is not another agent orchestrator — it makes the one you already use (LangChain, CrewAI, AutoGen, ...) compliant.

Each module logs, drafts, tests, or flags something concrete. None of them certify compliance on their own — that's a legal determination. See Scope below.

Install

pip install aiactguard[langchain]

Other extras: crewai, claude-agent-sdk, langgraph, autogen, openai-agents, postgres (for PostgresAuditStore) — mix and match, e.g. pip install aiactguard[langgraph,postgres].

Quickstart

from aiactguard.adapters.langchain_adapter import AIActGuardCallbackHandler
from aiactguard.core.approval import ApprovalContext, ApprovalDecision


def compliance_officer(ctx: ApprovalContext) -> ApprovalDecision:
    approved = input(f"Approve {ctx.action} ({ctx.risk_tier.value})? [y/N] ").lower() == "y"
    return ApprovalDecision(approved=approved, approver_id="compliance_officer")


guard = AIActGuardCallbackHandler(
    category="essential_services",
    approvers=[compliance_officer],  # an escalation chain — add more to route to a fallback
)

agent_executor.invoke({"input": "..."}, config={"callbacks": [guard]})

See examples/ for full runnable examples: LangChain, CrewAI, Claude Agent SDK, LangGraph (using LangGraph's own interrupt() for human-in-the-loop), AutoGen, OpenAI Agents SDK, the framework-agnostic @watch decorator with an escalation chain + override, generating all five Phase 2 compliance reports from an audit trail, running the red-team scenario harness, a fairness scan, drafting an incident report + GPAI transparency card, composite-system risk aggregation, NIST/ISO mappings, using the Postgres storage backend, and a worked community plugin.

Module roadmap

All 19 modules from the original project plan are built — see Scope for what's deliberately excluded.

Core (Phase 1)

Documentation & assessment tooling (Phase 2)

Robustness & incident tooling (Phase 3)

Multi-agent & multi-standard extensions (Phase 4 — differentiators)

Scope

Explicitly out of scope, and why:

• Prohibited-practice determination (Title II) — legal judgment call, not a runtime check
• Conformity assessment / CE marking itself — requires formal procedures, sometimes a notified body; the toolkit preps evidence, it doesn't perform the assessment
• Quality management system (Art. 17) — an organizational process, not code
• GPAI systemic-risk evaluation (Art. 55) — applies to frontier model providers, not agent builders
• Actual legal filing/registration submission — data prep is automated, submission is not

Contributing

Contributions are welcome, especially jurisdiction- or industry-specific modules. Open an issue to discuss before submitting a large PR.

Writing a plugin: implement aiactguard.plugins.Plugin — a name, a description, and a generate(logger, *, questionnaire=None, **kwargs) -> str method (the same shape every built-in report/mapping already has). See examples/plugins/example_gxp_plugin.py for a worked example. To publish one for others to auto-discover, register it under the aiactguard.plugins entry-point group in your own package's pyproject.toml:

[project.entry-points."aiactguard.plugins"]
gxp = "aiactguard_gxp_plugin:plugin"

Callers pick it up with aiactguard.plugins.discover_entry_points().

License

MIT — see LICENSE.