auditant

Compliance system-of-record for AI agents: every action your agents take, hash-chained, policy-checked, externally countersigned — and verifiable offline by someone who doesn't trust you.

Two lines

import auditant
auditant.init(api_key="ak_…", log_id="t_…/prod", agent_id="underwriter")

With OpenTelemetry present, init() registers a span processor and activates whichever OpenInference instrumentors are installed (LangChain, OpenAI, Anthropic) — LLM calls and tool executions become chained audit events automatically: hashes, never payloads; token counts reported as observed-not-priced, never as $0. Install the extras for full capture:

pip install "auditant[openinference]"

Without OpenTelemetry, init() still gives you a session on the chain (lifecycle + heartbeats, so a quiet agent is distinguishable from a dead emitter), the manual record() API, and the synchronous policy check:

handle = auditant.init(api_key="ak_…", log_id="t_…/prod", agent_id="underwriter")
verdict = await handle.client.decide({
    "logId": "t_…/prod", "agentId": "underwriter",
    "action": "wire_transfer", "amount": 50_000, "sessionId": handle.session_id,
})
# {'effect': 'pending_approval', ...} → a human approves in the dashboard
# or from Slack, and the same call then returns 'allow'.

Evidence writes never block your agent (queued, batched, spilled to disk on outage), and the policy service failing means a recorded enforcement gap, never a silent allow.

The examiner's side

Every exported bundle is self-verifying: it embeds a dependency-free verifier (node verify.mjs bundle.json) that recomputes the chain and validates every countersignature — no account, no network, nothing from us.

Docs: https://auditant.insightron.ai/docs