v0.11.0 | Release notes →
V1.0 Launch Countdown
--Days
:
--Hours
:
--Minutes
:
--Seconds
March 25, 2026 · 20:00 PHT
We're live! Welcome to SIDJUA V1.

Your AI agents are out of control.
You just don't know it yet.

Can you tell me what they did yesterday? Exactly?

Right now, your AI agents are spending your money, accessing your data, and making decisions on your behalf. You have no spending limits, no audit trail, and no rules about what they can or can't do. When something goes wrong — and it will — you won't know until the damage is done.

SIDJUA is the governance layer for AI agents. One platform to see, control, and budget every agent in your organization. Rules are enforced before agents act — not after. Always-on daemons, 8-channel messaging, governed scheduling. Open source, self-hosted, works with any LLM.

This is happening right now.

If you're running multiple AI agents, one of these has already happened to you — or it will.

The Surprise Bill

An AI agent burned through $800 in API calls in a single afternoon. Nobody noticed until the invoice arrived at the end of the month.

"We thought it was a billing error. It wasn't."

The Rogue Email

An agent replied to a customer with completely hallucinated information. The client saw it before any human reviewed it. Trust: gone.

"We only found out because the client called us, confused."

The Compliance Question

Your compliance officer asks: "Who authorized this AI to access customer data?" You open a blank spreadsheet. You have no answer.

"We couldn't tell them which agents accessed what. Or when."
These aren't edge cases. They're Tuesday.

Stop babysitting. Start governing.

SIDJUA is a governance layer that sits between you and your AI agents. Every action gets checked before it runs.

💰

Control Spending

Per-agent and per-division budget caps, enforced automatically. Set a limit, forget about it. No more surprise API bills.

🛡

Block Bad Actions

5-step pre-action enforcement pipeline checks every action against your rules before it executes. Violations are blocked, not just logged.

Always-On Agents

Governed background daemons with mutual watchdog monitoring, scheduled tasks, and budget-limited cron jobs. Your agents run 24/7 — within your rules.

Works with any LLM Open source (AGPL-3.0) Self-hosted Runs on 4 GB RAM Full audit trail 8-channel messaging Desktop GUI (Tauri) Runs on Raspberry Pi

Four steps. Zero trust required.

SIDJUA intercepts every agent action and runs it through your rules before it ever executes.

1

Agent requests action

Any AI agent — Claude, GPT, Gemini, local models — wants to do something.

2

SIDJUA checks rules

5-step governance pipeline validates against your policies and budget limits.

3

Approve or block

Compliant actions proceed. Violations are stopped before they cause damage. Users can override with full audit trail.

4

Everything logged

Full audit trail. Every action, every decision, every cost — searchable and exportable.

Quick Start (Docker)

git clone https://github.com/GoetzKohlberg/sidjua.git
cd sidjua
docker compose up -d
docker exec -it sidjua sidjua init
docker exec -it sidjua sidjua chat guide

What you need before installing · Requires Docker and Docker Compose. See full docs on GitHub.

Why I built SIDJUA

2 minutes. No AI voiceover. Just the problem, the story, and the fix.

Founder video coming soon

Independently audited. Continuously tested.

v0.11.0
Latest Release
3
External Code Auditors
7+ Rounds
Audit Cycles Completed
2 Patents
USPTO Filed

"The architecture heavily isolates governance from execution. SQLite is an excellent choice for the air-gapped, self-hosted product promise."

— Gemini 3.1 Pro, Architecture Audit Round 2 (March 2026)

Besides extensive internal testing, three independent external auditors (DeepSeek V3, xAI Grok, Gemini) review our codebase continuously. All findings resolved.

Everyone is building agents. Nobody is governing them.

The biggest names in AI are validating the problem SIDJUA solves.

NVIDIA GTC · March 2026

Jensen Huang: "Every CEO needs an OpenClaw strategy."

NVIDIA built NemoClaw for runtime security on top of OpenClaw — sandbox isolation, privacy routing, network guardrails.

Missing: governance, budgets, compliance, audit trails. That's SIDJUA.
OpenClaw Ecosystem · 2026

800+ malicious skills. 30,000+ exposed instances.

CVEs, supply chain attacks, advisories from Microsoft, Cisco, Sophos, Bitdefender. The fastest-growing open source project has a governance crisis.

Governance-by-architecture is not optional. It's urgent.
Paperclip · March 2026

16,000+ GitHub stars in one week.

Paperclip wraps existing agents into company structures with org charts and approval gates. Proves massive demand for governed agent orchestration.

Wrapper layer with approval gates. No pre-action enforcement. No built-in runtime.

If you run AI agents, you need governance.

Solo Developer / AI Tinkerer

"I have 5 agents running but zero idea what they actually cost me."
SIDJUA: Budget caps per agent. Real-time cost tracking. Free to start.

Startup CTO

"We're scaling AI fast and I can't manually review every agent action."
SIDJUA: Automated policy enforcement. Always-on daemons with mutual watchdog monitoring. Rules that scale with you.

Enterprise / Regulated Industry

"Our auditors want to know exactly what our AI did and why."
SIDJUA: Complete audit trail. Compliance-ready. Self-hosted on your infrastructure. EU AI Act aware.

Privacy-Conscious Team

"We can't send our data to someone else's cloud."
SIDJUA: Air-gap capable. Runs on Raspberry Pi with local models. Your data stays yours.

Stop flying blind.

Three commands. Four gigs of RAM. Complete AI agent governance.

Enterprise inquiries? contact@sidjua.com