RAG and retrieval — page 5

A small RAG web app that visualizes every step of the retrieval-augmented generation pipeline

Vibe check before you reply: an Android accessibility overlay that reads the chat on screen and judges the turn with TypeSafe Jev, with per-person memory and RL on the phone

Federated knowledge retrieval engine for AI agents. Routes queries across specialized backends (FTS5, ChromaDB, graph) via a registry-first orchestrator with TypeSafe/Jev AI routing and evidence re-ranking. Read-only by default, security-gated by design.

Low-memory autonomous web classification with HTTPX, Lightpanda and Jev

Memory plugin for DeepSeek Harness: every memory read/write is a typed judgement by TypeSafe Jev (choice/noul).

RAGのretrievalにTypeSafe APIを使うアイデアの実装

Corrective RAG where every decision gate is a typed System One model call instead of an LLM judge. 7x fewer LLM calls, 4x lower p50 latency.

Context-carrying graph retrieval with Jev: branching walks, reproducible ablations, and a visual replay.

TypeSafe’s Jev AI + an n-ary memory tree = efficient agentic memory routing and retrieval.

Semantic search for webpages using TypeSafe AI's Jev typed decision model. Find relevant passages even when your query doesn't match the exact words on the page.

国服《英雄联盟》版本更新公告的本地 RAG 问答：数字只来自公告，Jev（TypeSafe System One）负责候选重排与回答自检

Agent memory that decides what to hydrate — local topology recall + TypeSafe Jev gates (not another dump-everything store).

Lint a Markdown knowledge base (Obsidian vault or LLM wiki) for contradictions, stale claims, unresolved markers and missing pages, using TypeSafe Jev

RAG Gatekeeper — TypeSafe chunk score/filter before LLM

Evidence-aware local RAG and HandoffProof: controlled causal testing for operational handovers, with optional TypeSafe/Jev evidence governance.

Memory for AI agents that only remembers the latest truth: a bi-temporal belief ledger + transcript index in one SQLite file.

AI Eval Platform — an evaluation and quality-engineering layer for LLM, RAG and agentic systems, with production observability integrations.

Adaptive memory routing for agent harnesses -- a router that decides which memory shards to contact by cost, confidence, and access scope, carried by a real agent harness.

Shared memory layer for coding agents across harnesses (Claude Code / Codex / Cursor / Kiro), exposed via MCP

A framework for generic RAG in enterprise environment

Chatbot web em um único arquivo HTML com roteamento de modelos via Jev (modos Pro e Lite) e RAG vetorial com embeddings do Google Gemini

CUPI Wiki — internal knowledge base of Cornell Physical Intelligence (CUPI), a Cornell University student robotics organization.

AI Powered Automation B2B Wholesaler Website

A small, fast Go TUI for chatting with your starred GitHub repositories. It downloads your stars, stores structured metadata + READMEs in SQLite, creates embeddings, and runs a local RAG-style chat so you can ask things like *“I’m building a Go OAuth server—what libraries do I have starred?”*.