Lictorate is a company building the runtime layer that sits between AI agents and the systems they touch — so a confident model never becomes a catastrophic one. We start with one product, deeply.
For thirty years, the line between human intent and system action sat at the keyboard. Models with tools removed the gap. The security model has not caught up.
Tool calls. Browser control. Code execution. The agent reads, decides, and reaches into real systems — the same loop, no person between the intent and the consequence.
Audit logs and evals record what already cost you something. An audit without enforcement is a confession, not a control. Agents need a firewall, not just an IDS.
Not the model. Not the prompt. Not the framework. The line must hold in the runtime — deterministic, auditable, and unable to be argued with by a long enough message.
Three rules we hold to. They shape every API, default, and release.
Policy precedes execution. No model output reaches a tool until the rules permit it. Not after. Not in parallel.
One prompt injection should not be catastrophic. Enforcement is the layer that contains the blast radius when alignment fails.
Every decision visible. Every rule reviewable. Security teams should read code, not hope.
Lictorate is the company. The products below are how the thesis reaches the world. We start narrow on purpose — and the core stays open, forever.
open-source runtime firewall for AI agents
Protect, rate-limit, and audit AI workloads with isolated tenant policies at 0.53 ms p99 latency. Drop in our LLM API Proxy or MCP Gateway, write your YAML rules, and get fully stateful enforcement powered by a write-behind embedded SQLite store.
fleet routing, central dashboard, team audit sync
For teams managing multiple agents in production. Shared policy libraries, global rate limits, live SSE action feeds for central human approposals, and exportable SOC-ready audit logs. The core proxy stays open; this is the control plane.
Lictorate is, today, one founder and a runtime. Mail goes to a person. Pull requests are read. We are deliberately focused on building the definitive routing layer for AI agents.
Cauã Ferraz· founder · backend & systems
Backend and systems engineer. Started Lictorate to build the enforcement layer the agent stack is missing — the boring, load-bearing kind of infrastructure, the kind you only notice when it isn’t there.
That’s the whole company in five words. If you’re building with agents and want centralized guardrails across your fleet, join the waitlist.