LearningCircuit

local-deep-research. ~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.

Friendly-AI-Reviewer. Creates highly-customizable AI Reviews as PR comments. Installation: Just 2 files copied to your repo and an OpenRouter API Key in your secrets. Costs: $0.01 - $0.05 per review (even for large PRs with full context)

ldr-benchmarks. Community-submitted benchmark results for Local Deep Research (LDR) on SimpleQA, BrowseComp, and xbench-DeepSearch. Aggregated leaderboard CSVs are synced automatically to a companion Hugging Face dataset