VIGIL is now VITNA

VITNA was previously known as VIGIL by COSTRINITY. The name changed. Nothing else did.

Vitna, from Old Norse: to bear witness. Pronounced VIT-nah.

Why

The name Vigil collides with several unrelated products in adjacent spaces, and with a research paper in our exact domain. For a product whose entire value is being findable and checkable by someone who does not trust us, an ambiguous name is a real problem. If you search for the thing that proves your agent was checked, you should not land on four other things first. Vitna is collision-free, and it says what the product does.

What changed

The name, the domain, and the package name. That is the whole list. The site is now vitna.costrinity.xyz, and the npm package is @costrinity/vitna-compliance-mcp.

What did not change

• The Ed25519 signing key and key_id. Still 01833acd46d06ab4. Evidence bundles issued under the VIGIL name remain valid and verify exactly as before, with the same verifier and the same published public key. We did not rotate anything.
• Old links. The old domain redirects to the new one, same path. The old GitHub repository URL redirects too.
• Old environment variables. VITNA_* is canonical now, but the VIGIL_* names keep working. We are not going to break a config that already works.
• Old tool names. The MCP tools are named vitna_* now, and the previous names still resolve, so an agent with a cached config does not break.
• The free tier, the pricing, and the limits. Unchanged.

What the product is

VITNA produces Ed25519-signed evidence records that anyone can verify offline with a published public key and an open-source verifier, with no need to trust VITNA's servers. It is a cooperative guardrail with heuristic detection, and those limits are documented publicly. Its purpose is not prevention. It is independently verifiable proof that an AI agent's actions were checked and allowed.

You can check that claim yourself in about a minute. See Verify evidence for the three commands.