Understand Yuva, the sovereign kernel
Why an agent platform builds its own kernel, what a fail-closed boot and formally verified leaves actually prove, and an honest account of Yuva's current status.
Units4
Duration16 min
Levelbeginner
By the end of this module, you'll be able to:
- Explain why an isolation guarantee is only as strong as the layer enforcing it.
- Describe how Yuva is built: no_std Rust, unsafe confined to one audited crate, formally verified leaves, dual-architecture boot.
- Explain what a fail-closed boot proves, and what it does not.
- State Yuva's current status accurately, including what is not live yet.
Prerequisites
- No prior kernel or Rust experience required.
- Helpful, but not required: the "Build your first agent with Namzu" module.
Units
Related
- Build your first agent with Namzu Install the Namzu kernel, register a provider, make your first model call, and declare a tool with a typed schema and an explicit authority - locally, with no account.
- Glossary The terms used across Cogitave documentation and training, defined once - agent kernel, capability grant, provider driver, sandbox, sovereign unikernel, MCP, evidence, and the words that are easy to assume.
- Agent identity and capabilities Every Cogitave agent acts under its own identity inside an explicit least-privilege capability grant, in a sandbox, with every action recorded as evidence. What that model guarantees, and where a human is still required.