# Urizen Research Labs

Building machine intelligence we can trust.

We research machines that compute on encrypted data and prove their work.

Urizen advances verifiable private computation: machine-checked theory,
confidential execution, and proof-carrying systems. From that research we
build **Nibiru**, an engine for private execution with public proof of
correctness; **Baobab**, the verifiable control layer for AI agents; and
**Anansi**, the harness that joins them into governed agentic AI.

Core guarantees: confidentiality (FHE), integrity (ZK), mutual trust (MPC).
The proof theory is machine-checked in Lean 4; builds are reproducible and
signed. The Nibiru demo build cleared 100/100 transactions over a continuous
24-hour endurance run. The systems are experimental research previews and
are not yet generally available.

- [About the lab](https://urizen.ai/about/)
- [Nibiru engine notes](https://urizen.ai/nibiru/)
- [Interactive demo](https://urizen.ai/demo/) · [Anansi harness demo](https://urizen.ai/demo/anansi/)
- [Docs](https://urizen.ai/docs/) · [Developers](https://urizen.ai/developers/)
- [Contact](https://urizen.ai/contact/) — hello@urizen.ai · [Privacy](https://urizen.ai/privacy/)
- Machine surfaces: [site index JSON](https://urizen.ai/api/site.json) · [OpenAPI](https://urizen.ai/openapi.json) · [llms.txt](https://urizen.ai/llms.txt) · [agents.md](https://urizen.ai/agents.md)