No live license call required
License keys are signed strings verified locally on server start. Once your key is configured, Palace can run without phoning home.
Air-gapped memory
Air-gapped AI memory without cloud dependencies
offline-ready
Palace Server supports teams that need memory for coding agents in locked-down, offline, or restricted network environments.
Runs on your infrastructure, not Palace's cloud.
Local ONNX embeddings: no third-party embedding API required.
Ed25519-signed licenses verify offline for air-gapped operation.
Local model path
Embeddings are computed locally, so prompts, memory snippets, and project context do not have to leave the deployment just to become searchable.
Operationally familiar
Palace stores data in Postgres with pgvector and can be deployed with Docker Compose or a static binary, so backups and access control stay boring in the best way.