Provides persistent adaptive memory management with tools for storing, recalling, contextualizing, and consolidating memories, along with graph queries and feedback mechanisms.
Enables AI clients (Codex, Claude, OpenCode, ChatGPT-compatible) to securely administer a YunoHost server, run bounded read-only incident diagnostics, and develop _ynh packages, through Nostr-signed, policy-controlled, fully audited access. Also supports optional delegated short-lived agent identities and an authenticated local memory façade.
Enables AI assistants to invoke generated NostrHost operations over MCP, with read operations executed immediately and write operations gated on approval. Client authentication uses NIP-98, results are redacted, and the HTTP transport binds to loopback only.