Curated Open-Source AI Repositories

“I run RAG for Junagadh client docs where plain vector search misses multi-hop answers across invoices plus specs. M-flow scoring evidence paths instead of chunk similarity matches how I debug retrieval misses in my lab, and its MCP-server mode plugs straight into my Cursor morning-scan pipeline.”

“I watch recall degrade past 10K memories in long-running Junagadh agents where stale facts crowd out live decisions. YantrikDB adding temporal decay plus contradiction detection on top of HNSW is the maintenance loop my memory layer lacks, and its 87ms p50 skill recall fits my Rs 6K VPS latency budget.”

“I run RAG for client docs where plain vector search misses multi-hop answers, and provenance is the gap — which notebook cell plus which source produced this claim. Open-science wiring agents to Python/R notebooks with reproducible trails is the audit shape my 90-day ledger demands. I would trial it for Kimi-class research runs before trusting outputs in client reports.”

“I self-host SearXNG so client queries never leak, and hister as a personal engine in Go is the lighter sibling I would test for single-seat research. One binary, own index, zero third parties — the shape my DPDP-sensitive briefs want. I would run it beside SearXNG for a month and keep the one with better Gujarati recall.”