Searches uploaded documents and URLs for MCP clients, with Jev scoring every passage before retrieval reaches the model.
FyleContext stores PDFs, documents and URLs once, then lets Claude or another MCP client search them with exact-page citations. Jev filters passages and permits an explicit no-result response.
A self-hosted proxy that trains a local model on Jev's answers. It served 72% of Banking77 locally at 15 ms, with a 2% audit and a bound on disagreement.
tomerglick57 · Tools & apps · 15 ms local
tomerglick57
GitHub
Tools & apps
-
15 ms local
Semantic-aware linting with System One models: rules you can state in a sentence, checked against your code by Jev.
@nalexpeae · Tools & apps
@nalexpeae
Site
Tools & apps
-
-
Typo tolerance, typeahead, barcodes and facet counts in plain Postgres SQL, plus an optional Jev step that asks one question per top-10 result.
@alex_forman1 · Tools & apps
@alex_forman1
GitHub
Tools & apps
-
-
built a virtual closet & outfit generator from raw closet videos. classification + semantic search thanks to jev 🥰. clueless closet dreams finally coming to life
@maitreemervana · Tools & apps
@maitreemervana
X post
Tools & apps
-
-
Launching FyleContext. 1/5 Upload PDFs, docs and URLs once. Claude (or any MCP client) searches them and cites the exact page. TypeSafe Jev scores every passage before it reaches your model. Nothing relevant? It says so instead of guessing. Link in comments.
