SAG Wiki: open-source local knowledge base indexing folders without embeddings or vector DB
AIFlow_ML · x · 2026-11-14
SAG Wiki, powered by SAG2, is a free open-source local knowledge base that turns existing folders into searchable knowledge without embeddings, a vector database, or model calls during indexing — a bold bet against the standard AI retrieval pipeline.
A commenter questions how it ranks results when two notes disagree, which is exactly the trade-off of skipping semantic indexing. Worth evaluating if you're building a local knowledge base.
Related event: SAG Wiki Builds Local Knowledge Bases Without Vector Databases(2 posts)→
More from coding & agent
- Inside the MI300X: 23-min visual guide from compute chiplets to a Gluon GEMM — saurabhtwq · 2026-11-14
- Job hunter's trick: fix a real issue in a startup repo, send the PR as evidence — minhnguyen · 2026-11-14
- Screenshot shows multi-agent, multi-user chat with realtime 3D video and long-term memory — nptacek · 2026-11-14
- DeepSeek opens its entire app stack via API: search, voice, OCR, ASR, TTS — churchkey · 2026-11-14
- Garry Tan's 52-task eval: Fable 5.2 matches Opus 5.5 on pass rate but costs 2.80x more — garrytan · 2026-11-14
- YC's Garry Tan open-sources agent harness evals: pass rates tie, costs differ 2.5x — garrytan · 2026-11-14