AgentGovern Python SDK

Compliance-as-code for agentic AI workflows.

Beta — API may change before 1.0. Report issues.

AgentGovern intercepts AI agent actions, evaluates them against configurable compliance policies (EU AI Act, NIST AI RMF, ISO 42001), and generates audit-ready evidence — in near real-time (compliance verdicts within seconds; the SDK never blocks your agent). This SDK instruments your LangChain, CrewAI, or OpenAI Agents code with minimal changes.

Install

pip install "agentgovern[langchain]"

Quickstart — LangChain

import agentgovern
from langchain.agents import AgentExecutor, create_openai_tools_agent
from langchain_openai import ChatOpenAI

# 1. Initialize once at startup
agentgovern.init(
    api_key="ag_prod_...",           # from https://agentgovern.zirahn.com/settings/api-keys
    base_url="https://agentgovern.zirahn.com",
    environment="development",       # "production" | "staging" | "development"
)

# 2. Register your agent
agentgovern.register_agent(
    external_id="credit-scoring-v2",
    name="Credit Scoring Agent v2",
    framework="langchain",
)

# 3. Get the callback handler — binds to credit-scoring-v2 automatically
handler = agentgovern.instrument_langchain()

# 4. Pass it to your AgentExecutor — no other changes needed
llm = ChatOpenAI(model="gpt-4o")
agent = create_openai_tools_agent(llm, tools, prompt)
executor = AgentExecutor(agent=agent, tools=tools, callbacks=[handler])

result = executor.invoke({"input": "Evaluate loan application for customer #12345"})

instrument_langchain() binds to the most recently registered agent. Every tool call, LLM invocation, and agent step is captured, evaluated against your compliance policies, and visible in the dashboard.

Enforcement modes (current limitations)

AgentGovern supports four enforcement modes per policy:

Known limitation: enforce mode with LangChain (v0.1)

LangChain's callback machinery catches exceptions raised from callback handlers and logs them as warnings rather than propagating them to halt the agent chain. This means that when Gate 1 returns action_taken='block' for an enforce-mode rule, our SDK correctly raises PolicyViolation, but LangChain swallows the exception and the agent continues executing.

Today: enforce-mode rules log the violation to input_evaluations with full regulatory citation. The audit trail is complete, but the agent chain does not halt.

v0.2 (Q3 2026): We are releasing a ChatModel wrapper that invokes Gate 1 before the LLM call (not as a callback), enabling real hard-block behavior.

Workaround: For customers who need hard-block today, call agentgovern.evaluate_input() directly before invoking your agent, and check result.action_taken == 'block' yourself:

result = agentgovern.evaluate_input(agent_external_id="my-agent", prompt=user_prompt)
if result.action_taken == "block":
    raise HTTPException(status_code=403, detail="Prompt blocked by compliance policy")
agent.invoke({"input": user_prompt})

Multiple agents in one process

If you run more than one agent in the same process, pass the agent ID explicitly to avoid ambiguity:

agentgovern.register_agent("fraud-detector", name="Fraud Detector")
agentgovern.register_agent("kyc-agent", name="KYC Agent")

handler_fraud = agentgovern.instrument_langchain("fraud-detector")
handler_kyc   = agentgovern.instrument_langchain("kyc-agent")

fraud_executor = AgentExecutor(agent=..., tools=..., callbacks=[handler_fraud])
kyc_executor   = AgentExecutor(agent=..., tools=..., callbacks=[handler_kyc])

Manual instrumentation (all frameworks)

from agentgovern.types import ActionType, ActionStatus

agentgovern.track_action(
    agent_external_id="my-agent-id",
    action_type=ActionType.TOOL_CALL,
    action_name="fetch_credit_bureau_data",
    status=ActionStatus.COMPLETED,
    duration_ms=312,
    input_payload={"bureau": "experian", "customer_id": "..."},
    output_payload={"fico_score": 720},
)

Supported frameworks

Auto-instrumentation for CrewAI and OpenAI Agents is on the roadmap.

Compliance frameworks

Enable policy packs from the AgentGovern dashboard.

Configuration

Claude Code Hook

The SDK ships a built-in CLI for installing the AgentGovern hook into Claude Code. The hook intercepts PreToolUse events and enforces your tenant policies in real time — before any write-class tool (Bash, Write, Edit, MultiEdit, NotebookEdit) executes.

Install

agentgovern hook install

This deploys the hook script to ~/.agentgovern/hook.py, merges the correct entry into ~/.claude/settings.json (with an atomic backup), and prints instructions for any missing env vars.

Required env vars

export AGENTGOVERN_API_KEY="ag_prod_..."           # Settings → API Keys
export AGENTGOVERN_ACTOR_USER_ID="user_2xxxx..."   # Settings → Profile → User ID

Subcommands

Bypass

To skip governance for a session without removing the hook:

AGENTGOVERN_HOOK_MODE=off claude

See packages/claude-hook/README.md for the full option reference.

Design guarantees

• track_action() returns in < 5 ms — all I/O is async in a background thread
• Buffer cap: 10,000 actions; oldest dropped when full
• Retry: 3 attempts with exponential backoff (1 s → 30 s max)
• If AgentGovern is unreachable, your agent continues unaffected

Links

• Dashboard: https://agentgovern.zirahn.com
• Documentation: https://github.com/ahmedkhan-zirahn/agentgovern
• Issues: https://github.com/ahmedkhan-zirahn/agentgovern/issues

License

MIT — Copyright (c) 2026 Zirahn