~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
Commits on main
chore(deps): bump puppeteer from 25.2.0 to 25.2.1 in /tests/puppeteer (#4771)
f781c6d dependabot[bot] committed 5 months ago
chore(deps): bump puppeteer from 25.2.0 to 25.2.1 in /tests (#4772)
5320441 dependabot[bot] committed 5 months ago
feat(search): cap local RAG results (default 20) + opt-in LLM relevance filter (#4765)
13c211b LearningCircuit committed 5 months ago
fix(fetch): return a recoverable tool message on a per-URL egress denial (#4761)
c81a56a LearningCircuit committed 5 months ago
fix(ci): seed link-analytics shard data + bump experimental badge to 12px floor (#4763)
f6537e1 LearningCircuit committed 5 months ago
chore(deps): bump @playwright/test in /tests/accessibility_tests (#4758)
7943b0b dependabot[bot] committed 5 months ago
fix(egress): close inference-path fail-open (LLM/embeddings PEPs use the single primary source) (#4752)
f6256f5 LearningCircuit committed 5 months ago
fix(egress): route RAG-indexing + SBERT embeddings PEPs through resolve_run_primary_engine (#4753)
fb785ed LearningCircuit committed 5 months ago
fix(ci): whitelist three vulture false positives to unblock vulture-gate (#4755)
f7a19b6 LearningCircuit committed 5 months ago
chore(deps): bump @axe-core/playwright in /tests/accessibility_tests (#4756)
7d301d2 dependabot[bot] committed 5 months ago
chore(deps-dev): bump @playwright/test in /tests/ui_tests/playwright (#4757)
5979e06 dependabot[bot] committed 5 months ago
fix(langgraph): propagate search context (DB password) into subagent pool (#4751)
7e7666c LearningCircuit committed 5 months ago
fix(egress): single source of truth for a run's primary engine (fixes mid-run scope_mismatch crash) (#4745)
8f5d57a LearningCircuit committed 5 months ago
fix(research): carry username in run snapshot so the agent can use document collections (#4746)
bc7a8d3 LearningCircuit committed 5 months ago
chore(deps): bump puppeteer from 25.1.0 to 25.2.0 in /tests (#4749)
3fe2df3 dependabot[bot] committed 5 months ago
chore(deps-dev): bump puppeteer in /tests/api_tests_with_login (#4747)
427094c dependabot[bot] committed 5 months ago
chore(deps): bump puppeteer from 25.1.0 to 25.2.0 in /tests/ui_tests (#4748)
3956cb7 dependabot[bot] committed 5 months ago
chore(deps): bump puppeteer from 25.1.0 to 25.2.0 in /tests/puppeteer (#4750)
e78fb2f dependabot[bot] committed 5 months ago
chore(deps): bump actions/checkout from 6.0.3 to 7.0.0 (#4738)
dd5a396 dependabot[bot] committed 5 months ago
chore(deps): bump zizmorcore/zizmor-action from 0.5.6 to 0.5.7 (#4739)
beb9817 dependabot[bot] committed 5 months ago
test(settings): remove stale duplicate cleanup rate-limit tests (#4735 follow-up) (#4741)
4668864 LearningCircuit committed 5 months ago
feat!: remove the MCP (ReAct) search strategy (#4548) (#4567)
f7af7af LearningCircuit committed 5 months ago
fix(metrics): rate-limit reset/cleanup operate on RateLimitEstimate (#4735)
fc3abe8 LearningCircuit committed 5 months ago
refactor(settings): drop !important specificity debt from mobile section-header (#4484)
c04c1a9 LearningCircuit committed 5 months ago
fix(settings): code review cleanup — inline styles, !important debt, breakpoint drift (#4483)
6e265ae LearningCircuit committed 5 months ago
fix(llm): cloud Anthropic model dropdown empty — list models via anthropic SDK (#4586)
84a6c20 LearningCircuit committed 5 months ago
fix(library): correct download manager total counter (was "X / 0 files") (#4685)
18e52b3 LearningCircuit committed 5 months ago
feat(chat): per-message Copy / Retry / Delete actions (#4659) (#4689)
06e731b LearningCircuit committed 5 months ago