Turn YouTube videos into searchable knowledge with AI summaries, timestamps, tags, social posts, and chat powered by captions

Organize AI agent context into four memory tiers for token-efficient, always-available layered memory and cleaner prompt control

AI-powered codebase documentation engine - AST parsing, LLM doc generation, knowledge graph, SQL lineage & RAG chatbot

Provides a cognitive memory system for AI agents to manage knowledge and improve decision-making in TypeScript environments.

🧠 Build a simple, local memory system that learns and adapts without complexity or authentication, designed for Claude Code.

📚 Build an offline multimodal RAG system that retrieves grounded answers from diverse document types with full citation support, all in one unified interface.

🚀 Index and search documents quickly with QuickRAG, using your preferred embedding provider and LanceDB for efficient similarity retrieval.

🤖 Collaborate with multiple AI models to get verified, consensus-driven answers that you can trust and rely on for accurate information.

🤖 Orchestrate AI agents with ease using this production-ready platform, featuring real-time streaming and multi-tool execution capabilities.

🛠️ Streamline agent development and debugging with the Agent Development Kit Web UI for a seamless Google ecosystem experience.

AI-native developer portfolio — RAG chatbot, AI agents, full-stack apps. FastAPI + Next.js, built spec-first with Claude Code.

Voice-first public-service assistant for multilingual government guidance using Vapi, OpenRouter, and Qdrant.

Unified digital platform for New Valley Governorate, Egypt — connecting tourists, residents, merchants, guides, and investors. Built with NestJS microservices, React, PostgreSQL, and AI-powered Egyptian Arabic chatbot.

Beyond chatbots: an AI platform that understands user intent and dynamically renders contextual UIs. 1,100+ tools, 30+ models, 100+ integrations.

Filesystem watcher that keeps a Qdrant vector store in sync with document changes. Config-driven rules engine, semantic search API, and CLI.

Knowledge synthesis engine for the Jeeves platform. Discovers .meta/ directories, gathers context from files and vector search, and produces structured synthesis artifacts via a three-step LLM pipeline (architect, builder, critic).

KI-Gedächtnis & Code-Intelligenz — Semantische Code-Suche, Wissensaustausch und Projekt-Pläne über MCP (Model Context Protocol). Verbindet lokale CLIs (Claude Code, Codex) und Web-KIs (Claude.ai) mit Qdrant + Ollama Embeddings.

AI tools write code fast, but they have zero memory of your team's history. mergelore sits in your CI pipeline and surfaces past architectural decisions, reversed patterns, and constraint violations before they ship again. No new infrastructure required, just add it to your workflow.

A production grade RAG platform for Indian Law : simplifying legal access for citizens with semantic search, dual LLM routing, multilingual support, and strict safety guardrails.

Enterprise-grade (40m+ lines) codebase intelligence in a zero-setup, private and local Plugin/Skill or MCP: managed indexing, hybrid semantic search, polyglot code dependency graphs, cross-project/repo & branch-aware search, and DB/API/infra knowledge. Benchmark: 61% less tokens, 84% fewer calls, 37x faster than standard AI grep.