~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
{
"name": "ldr-api-tests-with-login",
"version": "1.0.0",
"description": "API tests with authentication for Local Deep Research",
"scripts": {
"test": "mocha 'test_*.js' --exclude 'test_helpers.js'",
"test:report": "mocha test_report_api.js",
"test:settings": "mocha test_settings_api.js",
"test:history": "mocha test_history_api.js",
"test:models": "mocha test_models_api.js",
"test:search": "mocha test_search_engines_api.js",
"test:research": "mocha test_research_api.js",
"test:auth": "mocha test_auth_api.js",
"test:metrics": "mocha test_metrics_api.js",
"test:benchmark": "mocha test_benchmark_api.js",
"test:queue": "mocha test_queue_api.js",
"test:apiv1": "mocha test_apiv1_api.js",
"test:debug": "mocha 'test_*.js' --exclude 'test_helpers.js' --inspect-brk",
"test:watch": "mocha 'test_*.js' --exclude 'test_helpers.js' --watch"
},
"overrides": {
"diff": "^8.0.3",
"minimatch": "^11.0.3",
"glob": "^14.0.3",
"yocto-queue": "^1.1.1",
"serialize-javascript": ">=7.1.4",
"yauzl": "^3.2.1",
"js-yaml": "^4.2.0"
},
"devDependencies": {
"chai": "^6.3.0",
"mocha": "^12.0.3",
"puppeteer": "^25.16.0"
},
"allowScripts": {
"puppeteer": false
}
}