A flight recorder for AI agents. Every tool call, every LLM call, every error — captured as replayable evidence.
pip install centinela
No agent is a black box once Centinela is recording. The SDK is fail-open by design: if the backend is slow or down, your agent never blocks, slows, or crashes.
Wrap your agent or drop in c.trace(...). Every action becomes a structured event: type, name, input, output, timing, status.
When an agent fails expensively, the context is usually already gone. Centinela keeps an auditable record you can replay, prove, and debug.
Turn on field-level redaction and sensitive payloads never leave your process — only structure, timing, and status ship. Compliance-safe by construction.
Real-time blocking · on the roadmapfrom centinela import Centinela c = Centinela(api_key="ctl_...", project="my-agent") # Option A — automatic wrapper agent = c.wrap(agent) # Option B — works with any framework with c.trace("process_order") as t: t.log_action(type="tool_call", name="send_email", blocked=True, human_review="approved") t.log_action(type="llm_call", model="claude-sonnet-4", tokens=1234)
The same trace that shows you what happened also doubles as your compliance layer. Centinela maps each recorded agent to a library of controls aligned with the frameworks your enterprise customers are starting to ask about.
Build agents for clients? Ship the evidence with the product. Hand a customer a bilingual audit report and a Centinela Verified badge for their agent — a differentiator you can sell, not a fire drill you survive.
Centinela generates evidence from your real traces; it doesn't certify your company. 8 of 10 controls are measurable today from SDK signals. One transparency deadline is already close: under the EU AI Act, disclosure obligations for deployers apply from 2 Aug 2026, and provider watermarking from 2 Dec 2026 — the kind of thing it's cheaper to instrument now than to retrofit later.
An agent running 24/7 with the Centinela SDK — synthetic data, identical evaluation to production. What you see here is exactly what you'd see with one of your real agents.
Demo agent · live synthetic data
Traces live in Centinela's vault, beyond the reach of the agent owner — not in their own database. A third party can query and verify them. Cryptographic sealing tamper-proof: on the roadmap.
The SDK is open source and works on your machine in two minutes — no signup, no backend required. Hosted dashboards and the Verified seal are in early access.