jev-recall

Retrieve by relevance, not resemblance: filter an AI assistant's memories with TypeSafe's Jev

How it uses Jev

Jev Recall gives you LLM re-ranker quality retreival at semantic search prices and speed

Getting started

A TypeSafe key is all the library itself needs. The other two are only for benchmark baselines and for recording the demo's replays.

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to jev-recall

Browse all
pi-jev-compaction project preview
Agent tooling
Automatic Jev context clearing for Pi. Keep the conversation, prune stale tool output, retrieve originals without rerunning commands.
jev-search project preview
Agent tooling
Search the web with TypeSafe's Jev: source selection, query understanding and relevance ranking. Built with Search1API.
reflex (kaustav1996) project preview
A coding agent and personal assistant with System One reflexes (TypeSafe Jev) on top of the Pi coding agent
wechat-jev-assistant project preview
Windows 微信对话分析助手:本地读取、脱敏、TypeSafe Jev 判断与加密历史
typesafe-assist project preview
Integrations
Home Assistant Assist conversation agent powered by TypeSafe's Jev (System One) model
pi-jev-context (Nyarlathoteppppp) project preview
Cache-neutral context trimming for the pi coding agent, powered by TypeSafe Jev: long tool output cut to verbatim key lines before it enters context, with lossless recall. Measured, with pre-registered benchmarks.
scam-shield project preview
Applications
Scam text message filter powered by TypeSafe's Jev model
jev-reranker project preview
Applications
Jev-powered relevance filtering and reranking for RAG in Python.
jev-harness project preview
Benchmarks & research
Decision harness for TypeSafe Jev — confidence gates, shadow mode, recipes, and evals. Claude CLI 48.9s → Jev 1.3s on the same row-filter job.