#embeddings

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

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

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.

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

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

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

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.

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。

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.

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

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

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.

Retrieval-augmented generation assistant over a document corpus

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 + 24 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

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

Talunor is a local-first terminal AI agent written in Go, with persistent, auditable SQLite memory, guarded tool use, and a complete step-by-step course explaining how it is built.

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.

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.

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

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

🏥 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).

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

RAG em Python puro: PDF ingestion, OpenAI embeddings, SQLite vectorstore, cosine similarity, Claude generator. Sem LangChain.

🔍 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.

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.

A context database for LLMs: structured storage and hybrid retrieval (BM25 + vectors, RRF-fused, token-budgeted) over SQLite, exposed to Claude as an MCP server

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

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.

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

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.

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

From Scientific Papers to Knowledge Graphs: Exploring Agentic AI Literature.

Dynamic episodic memory for LLMs. Self-hosted Rust microservice. Vector index + temporal graph + tiered retrieval + REST/MCP.

Polyglot Go client for OpenAI, Anthropic, Bedrock, Vertex, Gemini, Cohere + 18 more. Chat, embeddings, TTS, STT, realtime sessions. One OpenAI-shaped API. Build LLM gateways and voice agents.