❯ owo --about

owo = Observe · Warn · Offend(gated)  # detect · alert · gated red-team

security that explains itself. an analyst in a container:

prevents in the PR · detects at runtime · investigates on its own.

deterministic bot + on-prem AI agent — your data never leaves.

# the critical decision is always deterministic; the AI only enriches.

❯ owo problem

• ! nobody watches the logs — early-to-mid team with no security analyst
• ! data-leaking LLMs — "AI SOC" SaaS ships your logs (and PII) out
• ! alerts without context — someone investigates each one by hand
• ! rising incident cost — and nobody on call

❯ owo how-it-works

• [01] prevent → CI gate blocks the vuln before merge (auditable rule packs)
• [02] detect → runtime: brute-force, enumeration, cross-tenant authz, geo, rate-spike
• [03] investigate → read-only PII-free agent correlates and writes the report

# 🔒 data-residency by default — on-prem model (Ollama) or hosted.

❯ owo plans

❯ owo status

✓ 6 repos with the gate green   ✓ 5 detectors (100% tested)   ✓ on-prem agent

❯ owo trusted-by

# teams & design partners running owo

❯ owo contact --design-partner

closing 3-5 design partners (free, in exchange for feedback + a case study).