chore: finalize repo audit hygiene (#257)

src/everos/component/rerank/deepinfra_provider.py

@@ -39,7 +39,7 @@ from .protocol import RerankError, RerankResult
 
 # Qwen3-Reranker chat template. The DeepInfra inference API treats the reranker
 # as a yes/no generator, so the prompt scaffolding must be supplied client-side
-# (verbatim mirror of the EverCore benchmark's reranker client). Without it the
+# (verbatim mirror of the benchmark reranker client). Without it the
 # model scores raw text off-template and returns uncalibrated relevance.
 _QWEN3_PREFIX = (
     "<|im_start|>system\n"

src/everos/entrypoints/cli/commands/init_cmd.py

@@ -180,4 +180,6 @@ def register(parent: typer.Typer) -> None:
         typer.echo("Next steps:")
         typer.echo("  1. Edit the file and fill in the API keys (see comments inside).")
         typer.echo("  2. Run `everos server start`.")
-        typer.echo("Docs: https://github.com/evermind/everos/blob/master/QUICKSTART.md")
+        typer.echo(
+            "Docs: https://github.com/EverMind-AI/EverOS/blob/main/QUICKSTART.md"
+        )

src/everos/memory/search/manager.py

@@ -518,7 +518,7 @@ class SearchManager:
         ``atomic_fact`` table) for finer-grained semantic match — long
         episodes whose single mean-pooled vector dilutes a specific topic
         recover via the matching atomic fact's own embedding. Mirrors
-        EverOS/EverCore's MaxSim retrieval pattern.
+        the EverOS MaxSim retrieval pattern.
         """
         vector = await self._embed_query(req.query)
         if not vector: