#semantic-search

Find code by asking what it does. A CLI for coding agents that uses Jev to discover relevant files and source context.

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

The #1 Obsidian MCP for AI memory — freshness-aware, cited, local-first and read-only by default. Dataview, Bases, PDFs, every agent.

Local-first memory engine for AI-agent teams — private/team/project ACL, associative recall, federated sync, and a built-in MCP server. One SQLite file, no LLM required. Apache-2.0.

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.

AI-powered GitHub stars manager with CLI & TUI. Sync, search, analyze, organize, and generate awesome lists.

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

Qdrant-backed semantic memory provider for Hermes Agent

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

Self-hosted persistent memory for AI agents. Markdown for humans, MCP for agents.

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.

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.

Memex.ai-Inspired AI Knowledge Base 2026 - Smart Markdown Wiki with Graph Search & Static Publishing

AgentTrail is a local-first AI agent layer for Ollama/local models that shows its work: semantic search, diff-safe edits, receipts, replay, memory, MCP, reports, and trust controls.

AI-powered multi-agent research platform for literature discovery, synthesis, and citation generation using LangGraph, RAG, and Gemini AI.

AI-powered research assistant that enables semantic search, question answering, and citation-grounded insights from academic papers using RAG.

Explainable agentic job-fit analysis system using LangGraph, semantic matching, and Streamlit.

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.

🦛 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.

An AI-powered YouTube Q&A system that lets users chat with video content using RAG pipelines, LangChain, FastAPI, and vector search.

Turn natural-language search queries into structured JSON filters using the Claude API. Production-grade intent extraction pattern.

Agentic AI portfolio: planning agents, multi-agent orchestration, RAG, memory systems, semantic routing, evaluation pipelines, and business workflow automation.

A fully local, zero-cost RAG chatbot for mac.du.ac.in — built with FAISS, Llama 3.2 3B, FastAPI, and React. CPU-only, 8GB RAM, zero cloud dependency.

AI-powered career intelligence platform built with FastAPI, PostgreSQL, pgvector, and Ollama. Analyze resumes, identify skill gaps, generate learning roadmaps, prepare for interviews, and chat with an intelligent career assistant using Retrieval-Augmented Generation (RAG).

Enterprise document assistant built with ASP.NET Core, FastAPI, PostgreSQL, Redis, Docker Compose, semantic search and a local RAG workflow.

AI-powered resume analyzer that matches candidates to jobs via semantic similarity, detects skill gaps, and generates personalized career reports using Groq LLM — with an interactive analytics dashboard and PDF export.

AI-powered FAQ chatbot with semantic search — understands meaning, not just keywords. Built with Streamlit, sentence-transformers, ChromaDB, and Groq LLM. Features a dynamic, hot-reloadable system prompt, two-sided chat UI, and guideline-driven handling of small talk, off-topic questions, and safety edge cases.

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

Personalized AI assistant capable of handling automated conversations across WhatsApp and Gmail using LLM APIs, Retrieval-Augmented Generation (RAG), semantic search, conversation memory, and real-time information retrieval.

AI-powered customer support agent using intent classification, semantic retrieval, Gemini-based grounded responses, and escalation handling.

The universal open database and semantic vector search engine for AI Agent Skills, MCP Servers, Project Directives, and Rules. 3.48M+ assets across 7 ecosystems.

🔍 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.

AI-powered Industrial Knowledge Copilot that uses Retrieval-Augmented Generation (RAG) with Google Gemini to answer questions from equipment manuals, SOPs, maintenance guides, and safety documents using semantic search and source citations.

Hands-on implementation of Retrieval-Augmented Generation (RAG) using vector databases, embeddings, semantic search, and Anthropic Claude.

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

ReviewGuard is an AI-powered review moderation platform combining LLMs, semantic embeddings, and rule-based detection to identify toxicity, spam, and duplicate content. Built with React, Node.js, MongoDB, Redis, and BullMQ, it features real-time moderation, role-based dashboards, audit logs, scalable async AI pipelines, and live telemetry feeds.

A filesystem for AI agents — mount the Unison brain as a real FS (FUSE on Linux, NFS on macOS) with a local SQLite cache, sync loop, and semantic grep.