Skip to content

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

Fix test to expect VectorBackend.AUTO as default

chopratejas67d7db87ccd3
diff --git a/tests/test_memory/test_factory.py b/tests/test_memory/test_factory.py
index 33d403c34..73fcbea3e 100644
--- a/tests/test_memory/test_factory.py
+++ b/tests/test_memory/test_factory.py
@@ -49,7 +49,7 @@ class TestMemoryConfig:
config = MemoryConfig()
assert config.store_backend == StoreBackend.SQLITE
- assert config.vector_backend == VectorBackend.HNSW
+ assert config.vector_backend == VectorBackend.AUTO
assert config.text_backend == TextBackend.FTS5
assert config.embedder_backend == EmbedderBackend.LOCAL
assert config.cache_enabled is True