Generative-retrieval memory router (DSI: query→note-id) vs. embedding retrieval on a small, linked, franglais personal-memory corpus — with a hardened, confound-free eval. Reproducible.
-
Updated
Jul 4, 2026 - Python
Generative-retrieval memory router (DSI: query→note-id) vs. embedding retrieval on a small, linked, franglais personal-memory corpus — with a hardened, confound-free eval. Reproducible.
Self-evolving pain memory for AI agents: detect tool-call failures, match past pain via local embedding, inject behavioral rules to avoid repeats.
Diagnostic engine for RAG retrieval failures. Component-level analysis, root cause detection, optimization recommendations. Fix what's broken, not just metrics.
To associate your repository with the embedding-retrieval topic, visit your repo's landing page and select "manage topics."