~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.
Find trending repositories by name or description.
~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.
Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.
[ACL 2026 KnowFM] Awesome Agentic Deep Research Resources
[ICML 2026] Multimodal deep-research MLLM and benchmark. The first long-horizon multimodal deep-research MLLM, extending the number of reasoning turns to dozens and the number of search-engine interactions to hundreds.
深度调研报告生成 Skill — 一条命令,十分钟出券商级深度调研报告 / Professional deep research report generation Skill · Supports 19 languages
Evaluation harness for Apodex-1.0 on public deep-research benchmarks.