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(ci): add sqlite-vec to dev deps to fix memory tests on CI

Long Ngo1df0b14ea0cb
diff --git a/pyproject.toml b/pyproject.toml
index 1f49da104..8e63ea3a5 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -156,6 +156,7 @@ dev = [
"ollama>=0.4.0", # For Ollama integration tests (local LLM, no API key needed)
"langchain-ollama>=0.2.0", # For LangChain+Ollama integration tests
"hnswlib>=0.8.0", # For memory system tests
+ "sqlite-vec>=0.1.6", # Fallback vector backend for CI runners without AVX support
]
# All optional dependencies
all = [