#embeddings

MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup

Self-hosted personal AI assistant on Telegram. Powered by OpenCode + Claude Sonnet (free big-pickle). OpenClaw skills compatible. SQLite + MCP live memory with optional Ollama vector search.

Wolbarg — modular, provider-agnostic semantic memory SDK for AI agents

Local semantic search over your AI coding agent session transcripts, using Ollama embeddings and sqlite-vec

Offline semantic search for everything on your disk - documents, code, PDFs, scanned images (OCR), video by the second. 100% local AI: hybrid RAG with keyword + vector + rerank, no API key, no cloud. Desktop app + 26 MCP tools for Claude Code, plus a multi-engine web researcher that quotes sources verbatim. 本地离线多模态语义检索

Смыслотрон — экспресс-кластеризация SEO-ядра по эмбеддингам: 11 моделей (OpenAI/Gemini/Voyage/Qwen), смысловой дедуп, HAC-деревья, интенты DeepSeek, мгновенный срез кластеров в браузере

ServicIA: agente de diagnóstico y matching para apps de servicios. Convierte un problema contado por texto, foto o voz en un pedido estructurado (rubro, urgencia, costo) y recomienda profesionales explicando por qué. Para plataformas que ya tienen técnicos: probalo en la demo, integralo por API o desplegalo con tus profesionales.

HermesClaw Zero‑Config Sidecar is a lightweight local vector‑memory engine for Hermes and OpenClaw. It runs as a zero‑config sidecar, providing fast embeddings, persistent memory, and instant retrieval for agents and MCP tools. Built for speed, simplicity, and full local control.

AI Video Intelligence & Knowledge Synthesis Platform built with LangChain,LangSmith, ChromaDB, Whisper, and LLMs.

Nokori (残り) — behavioral memory layer for Claude Code and Cursor. Turns your corrections into rules that come back when it counts. 经验留下的痕迹，比记忆更深。

The continuity substrate for AI agents — memory that becomes a mind: a versioned self-model, a cognitive heartbeat, a shared cortex, metacognition & debate, on temporal-graph memory. Apache-2.0, zero-dep core.

Self-hosted knowledge base for AI agents: ingest Markdown into Qdrant with H1-H...-aware chunking, hybrid (dense+sparse) search and cross-encoder reranking.

Persistent memory for AI agents — MCP server, knowledge graph, hybrid semantic search. Self-hosted & private: your data stays on your machine. Память для ИИ-агентов (Claude, GPT, DeepSeek): MCP-сервер, граф знаний. Триал 7 дней.

Self-healing RAG on n8n with LLM-as-judge eval, drift detection, investigator agent, and canary A/B deploys.

A practical, first-principles handbook on production RAG & agentic systems — RU/EN/SK, built with Docusaurus.

Agente RAG conversacional sobre IA Generativa con Google Gemini, ChromaDB y LangGraph. Memoria por thread, interfaz Streamlit y base de conocimiento propia. Práctica final del Máster en Data Science e IA.

A native desktop client for free access to Claude Mythos AI across Windows, macOS, and Linux.

Retrieval-augmented generation assistant over a document corpus

Local-first AI agent memory for coding projects: SQLite context, MCP server, Codex skill, Rust CLI, and optional embeddings.

Fleet-grade local memory for AI agents over plain Markdown — hybrid recall, multi-tenant, one process, no cloud/Docker/LLM

Query billions of AI events by what they mean. PrismDB is a semantic event store: columnar analytics, similarity search, and meaning-based clustering over your LLM and agent telemetry — in one engine, one SQL query, at full retention.

MCP server giving coding agents semantic + structural search over your codebase, so they reuse proven patterns instead of guessing. Finalist - Cursor × Superteam Georgia Hackathon 2026.

AI-powered music discovery platform with RAG pipeline, neural reranking, and real-time audio feature extraction. Describe any vibe, get a curated playlist.

🦛 A hippocampus for your AI. Long-term memory for Claude & any MCP client, stored as Markdown in your own GitHub repo: hybrid semantic search, knowledge graph, auto-memory, compaction-proof, token-lean.

🏥 AI-powered Clinical Document RAG Engine — Ask questions about medical documents, get precise answers with citations. 86% retrieval accuracy. Free LLM support (Gemini/Groq/Claude).

Persistent AI Memory for TypeScript Agents 2026 🧠 | LanceDB & Server-Free

Agente de RR. HH. con LangGraph, RAG, FAISS, Groq y Llama 3.3 para responder consultas internas, solicitar información adicional y generar tickets de soporte.

TypeScript RAG pipeline extracted from a production system — local Ollama embeddings, cosine retrieval, opt-in LLM reranking that fails open. Vitest + CI.

Retrieval-Augmented Generation (RAG) chatbot using FAISS, Transformer embeddings, and semantic search.

Medical Chatbot using Python, RAG, PDF Knowledge Base, LangChain & Mistral AI. Extracts medical information from PDFs and answers user questions with intelligent retrieval and AI-powered responses.

🔍 100%-offline-capable multimodal semantic search for macOS. Find your files by meaning, not name — text, code, PDFs, images, audio. Ollama + Qwen3-VL local, Gemini/OpenAI optional. Power-user tool, macOS-only.

RAG in pure Python: PDF ingestion, OpenAI embeddings, SQLite vectorstore, cosine similarity, Claude generator. No LangChain.

Local RAG assistant in Python: ingestion → chunking → OpenAI embeddings → ChromaDB vector search → grounded answers with sources. CLI + FastAPI web UI, Docker.

Educational project exploring deterministic RAG and tool-using AI agents with FastAPI, PostgreSQL, pgvector, and OpenAI.

OpenAI uyumlu inference endpoint'lerini test etmek için çapraz platform betikler: chat, model keşfi, TTFT'li yük testi ve embeddings sağlık paketi (Bash · PowerShell · Python, bağımlılıksız)

Turn any website into an OpenAI-compatible LLM provider via Chrome Extension & Cloudflare Workers Durable Objects. Supports /v1/chat/completions, /v1/responses, /v1/embeddings, /v1/models.

Tu segundo cerebro para proyectos e investigacion. Asistente de conocimiento local-first sobre n8n + RAG con citas exactas (Claude + Chroma + Next.js).

Confidence-Aware RAG Memory Engine for LLMs and coding agents - typed memory (facts, decisions, episodes, code), confidence scoring with answer modes, context packing, semantic caching, hybrid retrieval, MCP server, and Invoke Mode for Claude Code.

Apex-relevance subgraph retrieval for AI agents — feed your LLM the most relevant slice of a knowledge graph, within a token budget.

Fast, private, client-side developer tools and clear references — plus explainers on modern AI infrastructure (context windows, MCP, RAG, embeddings, agent patterns). Everything runs in your browser; nothing is uploaded.