~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
Python academiaanthropicarxivbravedeep-researchencryptionhome-automationhomeserverlocallocal-deep-researchlocal-llmmistralollamaopenaipubmedresearchresearch-toolretrieval-augmented-generationsearxngself-hosted
chore: drop stale benchmarks/cli.py mention from pyproject comment (#3667)
LearningCircuit3c7ccbbb5da2
diff --git a/pyproject.toml b/pyproject.tomlindex 2ba42a7a9e..ebc807da9c 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -305,7 +305,7 @@ dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"".github/scripts/**" = ["T201"]# CLI modules: print is the interface"src/local_deep_research/cli/**" = ["T201"]-# Benchmarks: print is used for output/reporting (includes benchmarks/cli.py)+# Benchmarks: print is used for output/reporting"src/local_deep_research/benchmarks/**" = ["T201"]# Web/settings files with intentional print for startup/debug"src/local_deep_research/settings/logger.py" = ["T201"]