RAG & retrieval — page 2

Evidence-first long-term experiment memory skill for AI coding agents, with optional Jev decision-model layers

Does a TypeSafe Jev rerank beat embedding search? Graded relevance eval (9,831 pairs, 164 zh/en queries) over the Agent Skills Hub catalog, with the judge-circularity bias measured.

Make room for useful evidence. Inspectable context selection for RAG, with Jev reranking and open benchmark studies.

Semantic code and document search CLI — BM25 recall + TypeSafe Jev calibrated precision

Test what your AI should remember. An experimental, source-aware memory admission evaluator powered by Jev, with editable cases and inspectable results.

A context compactor that can only score, never write — so an agent's memory can't hold a fact the transcript never contained. Working demo, runs offline.

Explore real-world use cases and projects built with TypeSafe AI's Jev: content moderation, AI agents, model routing, and semantic search. Curated by SeeAPI.

Hands-on agent memory notebooks and an interactive appbook for context engineering.

Zero-memory System-1 decision engine & TypeSafe Jev wire-compatible runtime powered by Mandelbrot wave dynamics (The Zero-VRAM Gauntlet).

Local knowledge search with three modes: BM25 + Jev by default, agentic multi-query lexical search + Jev without vectors, and optional BM25 + embeddings/RRF + Jev, with grounded streaming answers.

Shared memory Jev-based plugin for multi-agent coding: subagents and Codex/Claude Code/Cursor hand-offs share one project memory. 一个多agent协同高效记忆统筹插件

A pluggable decision substrate for RAG pipelines; explicit, calibrated state → Decision → confidence → action gates, with Jev as the first swappable backend.

Three measured experiments on RAG hallucination: quote-checking, TypeSafe's Jev, and IBM's STAIR. 850+ graded questions, raw responses included.

Topic memory for LLM agents — edited, not accumulated: a topic keeps the starting question, conclusion, impact and dependencies; process is not memory. OKF bundle for dsh, local-first, git-traceable, budgeted LLM-free injection.

JeVerifier: cheap Jev (TypeSafe) checks that keep code maintainable and docs consistent, plus context retrieval — modest token savings

Drop-in relevance filter for LangChain RAG retrievers powered by TypeSafe Jev.

Fast Memory is an agent memory system built with Jev + LLM.

Ten runnable Jev examples for agent decisions: memory conflicts, tool-result checks, recovery, context selection, and handoffs. JavaScript, zero dependencies.

Local-first Markdown memory alignment and source-linked search with optional Jev judgments

DGUI-HyperMem (DeckerGUI HyperMemory) - self-hosted hybrid memory MCP server on Cloudflare Workers with a JEV (Choice/Noul/Score) reasoning layer and a HuggingFace training-brain flywheel.

Typed, policy-driven decision workflows on top of TypeSafe AI Jev: confidence routing, fallbacks, evaluation, and RAG patterns for TypeScript apps.

Fast semantic code search & diff sanity auditor for AI coding assistants (Antigravity, Cursor, Claude Code) powered by TypeSafe System One.

Local-first chat agent that runs comfortably with small-context local LLMs (from 2B) without losing the original goal of a long conversation. Multi-window context with rollovers, SKILL.state runtime, memory carry-over, three-tier auto web search, and a stalled-session detector. Next.js + FastAPI + SQLite + LanceDB, packaged for Docker Compose.

Agentic RAG pipeline for biomedical evidence discovery: query planning and multi-round search across twelve public databases plus citation-graph expansion, ranking by relevance and study design, and citation-grounded synthesis with disagreements reported explicitly.