See everything your AI coding agents do. Block what they shouldn't. Open-source observability for every agent action, secret scan, and compliance signal — deploy it on your infra, audit every line of code.
Claude Code hooks generate the telemetry. Tatu is the open-source brain that ingests, correlates, and acts on it — running on your own infrastructure.
Every blocked command, leaked secret, and PII detection surfaces instantly. Filter by severity, hook, developer, or repository.
Trigger counts, block rates, intervention patterns — know exactly which hooks are catching issues and which need tuning.
Automatic control mapping to SOC2, GDPR, LGPD, CPS234, and ISO 27001. Generate audit-ready evidence from every session.
Risk profiles per developer based on block frequency and session behavior. Spot patterns before they become incidents.
Every agent action logged as structured JSON. Export to CSV, JSON, or forward directly to your SIEM.
Deploy on your own infrastructure. Inspect every line of code. No data leaves your network. Apache 2.0 licensed — fork it, extend it, own it.
One self-hosted dashboard for CISOs, GRC analysts, and DevSecOps engineers to see what AI agents are doing across every repository. Your data stays on your infrastructure.
git clone, docker compose up. Tatu runs on your infrastructure — your data never leaves your network. One command to start.
Add Tatu's local ingestion endpoint to .claude/settings.json. Every PreToolUse, PostToolUse, and lifecycle event streams to your instance in real time.
Your dashboard lights up. Threats get blocked. Compliance evidence accumulates automatically. Export for auditors or forward to your SIEM.
Tatu automatically maps hook activity to compliance controls. Evidence generation isn't a quarterly scramble — it's continuous. And since it's open source, your auditors can verify the tooling itself.
CC6.1, CC7.2, CC7.3, CC8.1 — access controls, monitoring, change management
Articles 5, 25, 30, 32 — data protection by design, processing records, security of processing
Articles 37, 46 — processing records, technical security measures, DPO evidence
Information asset controls, logging requirements, change management obligations
A.9.4, A.12.4, A.12.6, A.14.2 — access, logging, vulnerability management
Free, open source, self-hosted. Built by Laboratório Hacker for teams that take AI security seriously. Deploy in minutes.