docs(readme): drop the stale operation count, mention data control

README.md

@@ -43,6 +43,9 @@ Add a conversation; EverOS turns it into structured, retrievable memory you can
 - **Knowledge bases** — ingest documents into a searchable topic library alongside
   conversational memory; ingest is async and reports progress through the task API.
 - **Multimodal** — attach images, audio, and documents to any message.
+- **You stay in control** — correct or delete single memories (scoped to one user when an
+  agent acts on their behalf), clear a user or session, or purge a whole memory space in
+  two confirmed steps.
 - **Built for production** — fully managed (no vector DB or extraction pipeline to run),
   with low-latency retrieval and high-concurrency throughput. The engineering guarantees
   you don't get from self-hosting.
@@ -99,9 +102,9 @@ Memory methods are bare verbs named after their route (`add`, `search`, `get`, `
 `<resource>_<verb>` (`kb_create`, `doc_ingest`, `task_wait`, `tag_bind`), so typing
 `client.kb` lists the knowledge-base surface.
 
-Everything the API offers — all 37 operations, including knowledge-base categories and
-document topics — is on the generated typed clients, reachable as `client.memory`,
-`client.storage`, `client.knowledge`, `client.tasks`. Those take and return the full
+Everything the API offers — every operation, including knowledge-base categories,
+document topics and memory-space purge — is on the generated typed clients, reachable
+as `client.memory`, `client.storage`, `client.knowledge`, `client.tasks`. Those take and return the full
 typed models, so responses arrive as an envelope you read `.data` from. The
 per-endpoint reference for them is under
 [`docs/`](https://github.com/EverMind-AI/everos-cloud-sdk-python/tree/v1/docs).