~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
🐛 Bug Fixes
- Citation handlers and the report structure generator now route LLM responses through
get_llm_response_text, stripping<think>reasoning blocks from synthesized answers and reports (previously leaked verbatim with reasoning models) and normalizing string/message responses in one place. - Cross-engine filtering now deduplicates repeated LLM-ranked result indices so the same source does not appear multiple times with different citation numbers.
- Fix
AttributeErrorin citation handlers during follow-up research when LLMs return string responses instead of message objects. - Restore
str()coercion in the precision citation handler's key-fact extraction so it always returns a string (fixes a mypyno-any-returnfailure introduced in #3884).