LIBRAOS // v0.9
Runs in your environment The engine · one Go binary

One 59MB binary. Your whole AI operating layer.

The engine underneath every LibraOS digital employee is a single Go binary that runs inside your own environment — air-gapped if you need it. Multi-agent orchestration, grounded retrieval, a 3-tier firewall, and 100+ models behind one OpenAI-compatible endpoint. No vendor cloud. No data egress.

01

The cascade: the LLM runs only when it's needed.

Most requests never reach a frontier model. A three-tier cascade resolves the routine in milliseconds and escalates only what genuinely needs reasoning — so latency and cost track the work, not the model.

Tier 1 — deterministic. Regex, cache, and policy resolve known-shape requests instantly, with zero token spend.

Tier 2 — small-model routing. A fast local model classifies, retrieves, and answers the grounded majority.

Tier 3 — frontier reasoning. The heavy model runs only when the first two tiers defer — the exception, not the default.

02

Four systems, one binary.

The engine ships as a single artifact. Every digital employee, every function, every pack runs on the same four systems — nothing to assemble, nothing that phones home.

KERNEL

Cascade routing

Three-tier orchestration plans the work and routes it. Most requests resolve in milliseconds; the LLM runs only when the cascade defers to it.

KNOWLEDGE DB

Grounded retrieval

Graph + vector + keyword retrieval with cross-session memory. Every answer traces back to your source documents — grounding, not guessing.

AI FIREWALL

3-tier screening

Regex → ML risk scoring → LLM judge, on both inbound and outbound traffic, for prompt injection, jailbreaks, and PII. Utility holds at 90.7% with defenses on.

MULTI-PROVIDER

100+ models

Frontier and open-source models behind one OpenAI-compatible endpoint with intelligent failover. Point your existing clients at it — zero lock-in.

03

Numbers that survive diligence.

Controlled same-model A/B, every figure certified across three runs. Full methodology and per-run data available on request.

SYSTEM LIFT

+18.9 pts

GAIA (public agentic benchmark, all levels). Same brain, with vs. without the engine. Replicates on-prem: +17.2 apples-to-apples on the shipped local brain.

GROUNDED SCALE

256 / node

Grounded digital employees per 8×H100 node. 98.3% grounded success across ×3 runs — we measure grounded success, not HTTP 200.

SECURITY DELTA

−35%

Attack success rate on AgentDojo — 26.8% → 17.3% with defenses on, while benign utility holds at 90.7%.

04

Deploy where your data already lives.

One binary, your infrastructure. About two weeks to production — and your existing OpenAI-compatible clients keep working unchanged.

ON-PREM Data never leaves your network AIR-GAPPED No egress required SOC2 / HIPAA Compliance support ~2 WEEKS To production deployment OPENAI-COMPATIBLE Point your existing clients at it

Built with Go. Runs anywhere. Compatibility identifiers from earlier releases (env vars, client IDs, image tags) are honored indefinitely.

SEE IT ON YOUR STACK

Put the engine to work.

A 30-minute call with our engineering team — we'll run it against your documents, your compliance rules, and your security requirements.

libraos · engine/eval

Read the integration guide, or open the console to point an existing client at the endpoint.