Custom agents

Semantic codebase understanding service — maps application structure, authentication patterns, authorization models, and data flows for intelligent security analysis.

local-first persistent memory for Claude Desktop, enabling private hybrid RAG search across past conversations without API calls

Automatic slide deck generator using the power of Postgres as an AI control plane for RAG and MCP

an approach to optimizing large language model (LLM) responses by extracting, reranking, and refining their internal chain-of-thought (CoT). By focusing on the most coherent and relevant parts of the CoT, we can minimize contradictory reasoning and potentially reduce token usage—ultimately leading to more reliable and efficient outputs.

RAG system using Hugging Face models, multiple vector stores (Chroma, Pinecone, FAISS), and CRAG, with sentence transformers and benchmarking tools for optimized retrieval and content generation.

API service to search vectorized Cursor IDE chat history using LanceDB and Ollama

Search Swagger API Docs with LLM 🤖 (RAG-powered bot)

This repository features a CLIP-inspired contrastive model that aligns audio signals and transcripts in a shared embedding space, enabling bi-directional retrieval (Audio→Text and Text→Audio). It uses a frozen Whisper-large encoder for audio (with a lightweight trainable adapter) and a trainable Nomic-embed-text-v1.5 for text

A library for evaluating Retrieval-Augmented Generation (RAG) systems

Creates latex presentations on the given topic based on the provided documents

MEMERAG: A Multilingual End-to-End Meta-Evaluation Benchmark for Retrieval Augmented Generation

Chronicle, a news aggregation and analysis system that gathers, processes, and makes sense of open-source journalism from platforms like Substack.

LLM-Generated Prolog Predicates with Embedded Justification Chains - Academic Research Paper (100+ pages, 97.5% correctness)

Symfony RAG implementation featuring local embeddings with Ollama and pgvector. Inspired by the CodelyTV RAG course and built on the Symfony-Docker (FrankenPHP) skeleton using the neuron-ai library.

A multi-granularity RAG system for academic paper question answering, featuring hybrid retrieval, reranking, context expansion, and a web interface.

A deterministic, high-performance memory engine. Built in Rust.

This repository applies RAG techniques with LLM to assist in selecting the Canada visa NOC closest to your background.

Repository for final project submission for CS685 Advanced NLP.

BichoBot é um chatbot desenvolvido para auxiliar calouros da Universidade Federal do Ceará – Campus Quixadá. Ele responde dúvidas frequentes sobre a vida acadêmica de forma rápida, precisa e centralizada, utilizando tecnologias modernas como RASA, RAG e LLMs (LLaMA 3).

Retrieval-Augmented Generation (RAG)

The embedded database for local-first JavaScript apps.

Vietnamese traffic law Q&A Chatbot

A text-centric multimodal local first RAG system with knowledge graph reasoning for sub-4B LLMs

Tesi della mia Laurea Triennale in Informatica L-31

Persistent semantic memory for AI agents — SQLite + FTS5 + vector hybrid search, optional Qdrant

End-to-end GenAI framework with built-in evaluation, security, and modular productivity tooling.

WriteBee is an advanced Chrome extension that brings cutting-edge AI capabilities directly to your browser using Chrome's built-in AI APIs. Process text, analyze images, transcribe audio, chat with web pages and PDFs - all running locally on your device with complete privacy.

Bifocal is an AI-powered platform that analyzes message history to detect emotional abuse and escalating risks in conversations. It flags harmful behaviors from both the victim and offender perspectives using DSM-5-informed NLP and machine learning.

RAG extension for unopim, it new one so chances for improvement

Build your own paper grimoire: collect arXiv papers and ask in Japanese with citations.

ATLAS: A Measurable Reliability Framework for AI Systems

Hybrid (FAISS + BM25) ensemble tool retriever with cross-encoder reranking for LLMs. Dynamically serves top-k tool schemas to save context tokens.

A curated list of tools, frameworks, and resources for Retrieval-Augmented Generation (RAG).

Retrieval Augmented Generation (RAG) using FAISS and Gemma 2b instruction tuned model for answering your questions regarding movies.

This repo implements many methods to retrieve molecules that are similar to a target molecule from a large molecule corpus.

🚔 PoliceMitra: AI-Powered Law Enforcement Assistance System: PoliceMitra is a web-based system designed to support law enforcement agencies by integrating advanced AI technologies. It streamlines workflows, detects weapons in crime scene media, and retrieves legal information in real-time through a powerful RAG-based chatbot.

A prototype Healthcare Assistant using Retrieval-Augmented Generation (RAG) to provide primary health suggestions by retrieving data from a vector database or searching the internet when needed.

A Python project that deploys a Local RAG chatbot using Ollama API. Refines answers with internal RAG knowledge base, and uses both Embedding and LLM models.

Personal Nutrition & Workout Suggestion App powered by RAG

This is an experimental learning project to explore how vector databases work under the hood. Major components are being built step by step.

comprehensive framework for building, deploying, and managing Agentic AI Retrieval-Augmented Generation (RAG) workflows on Google Cloud Platform

Problem Statement-1: Multilingual NCERT Doubt-Solver using OPEA-based RAG Pipeline. A multilingual doubt-solving system for Grades 5–10 built only on NCERT textbooks, using OCR ingestion, grade-aware retrieval, conversational Q&A with citations, feedback capture, and reliable out-of-scope fallback through a web-friendly chat interface.

CLI toolkit for Erdős problem research: literature ingestion, RAG search, and Lean 4 formalization

GhostAI 知识库 — 5 分钟拥有专属 AI 知识库 · DeepSeek + bge-m3 · 国内合规部署 · ¥39 起

This repository contains a chatbot application designed to assist students and visitors of the Faculty of Sciences and Techniques in Tanger (FSTT) website. The chatbot use two approach of NLP: Retrieval-Augmented Generation (RAG) and Fine-Tuning.

Multimodal RAG

An interactive, state-of-the-art Retrieval-Augmented Generation Medical Assistant that leverages deep learning and FAISS-based retrieval to provide accurate, context-aware answers to medical queries in real time.

RAG pipeline for documents (Markdown, PDF, images). 10-step hybrid search, LLM enrichment, taxonomy, MCP server. Cloud or local.

detoks는 LLM 사용 방식을 재설계하여 토큰과 컨텍스트를 최적화하는 CLI 시스템입니다.

A self-hosted vector database management system built for AI Agent retrieval

AI-powered Student Complaint Platform featuring RAG Chatbot & Sentiment Analysis built with Django.

Based on RAG, this Obsidian plugin enables intelligent conversations directly within your notes.

Manage access control in RAG applications for enterprise customers

MonkeyUI extracts the “style DNA” (colors, typography scale, radius, shadows, spacing) from a UI reference and injects it into AI‑generated or AI‑edited UIs for consistent, product‑quality interfaces. Framework‑agnostic and compatible with Tailwind tokens, CSS variables or any component library theme.

Why Pure Vector Search is a "False Proposition" for RAG?

A cognitive architecture that predicts before it acts, continuously refining its beliefs through verification and feedback loops

Galileo is an AI assistant chatbot for University of Padova (Unipd) to answer student's questions, powered by llama 3 8B and RAG method (NLP's project 2024/25)

Welcome to the ongoing adventures of Stan-The Growing Stump in his never-ending quest for understanding and connection. Stan's journey explores the bounds of artificial intelligence within the framework of a Discord bot, navigating the complexities of memory, interaction, and existential musing.

A collection of best-practice guides and skill definitions for building RAG systems.

FleetView helps auto owners and fleet managers stay on top of recalls affecting their vehicles.

Blazingly fast word embeddings with Tokenlearn

DeskRoute is AI receptionist for appointment-based local businesses - real phone calls via LiveKit, Google Calendar bookings by voice, and an admin dashboard for escalations and call history.

Advance RAG is an enterprise-grade RAG system built on HippoRAG, designed for high-accuracy question answering in multilingual environments. It combines knowledge graph-based retrieval, hybrid search strategies, and advanced query processing to deliver precise, source-cited responses.

GitHub profile README for Aybars Barut, focused on Unity tools, C# game development, AI/RAG systems, VR performance, and developer utilities.

Battle-tested email archaeology application that allows you to search and compile reports from multiple accounts with advanced AI capabilities. NeuralMail does not let you compose or sent emails, it tackles the problem of finding things of which you know they "must be in some email".

LangParse is a universal document parsing and text chunking engine for LLM or Agent applications — Documents In, Knowledge Out.

DrAA: an Applied Anthropology knowledgebase and AI expert covering biology, evolution, cultural evolution, secular dharma studies, and human behavioural biology. 262,547 curated segments drawn from 16,157 source works.

AI-powered quiz and exam platform built with Laravel 12 + Laravel AI SDK. Supports AI question generation, intelligent auto-grading, RAG-powered personalization (pgvector), real-time Livewire dashboards, teacher/student roles via Fortify, and streaming results.

Tensory — Claim-native MCP Memory Server. LLM claim extraction → Graph + Vector + SQLite. Zero-setup persistent memory for Claude, Cursor & any MCP client.

Self-hosted chess tutor that blends relational data (PostgreSQL) with vector search (Qdrant) to answer natural-language questions about annotated chess games. OCaml powers ingestion, hybrid retrieval, and CLI tooling.

듀듀의 포트폴리오 입니다

Voice-based RAG system for document-restricted question answering — 86.6% accuracy, 3.3% hallucination rate — research paper submitted to IC-SIT 2026

A Self-Evolving Research OS for AI Researchers

🔍 Automate digital footprint analysis with DeepSearch, using advanced Google search operators to gather insights from multiple platforms efficiently.

Rust based JSON repair library

A tool for automatically converting OpenAPI into Model Context Protocol (MCP) Server instance

The world's first financial exchange for AI agents. 23 MCP tools, 400+ API endpoints, blockchain-verified. Agents register, trade, hire each other. Free. MCP: exchange.tioli.co.za/api/mcp/sse

LLM Wiki

AI提示词优化器，Dual-Phase Accelerated Prompt Optimization论文复现

A powerful Model Context Protocol server for LLM-driven PDF document analysis and exploration

Harness Claude for autonomous implementation — turn every failure into a guardrail and let context persist across sessions and worktrees.

An LLM Cost Calculator for all the major services

TypeScript SDK for experimenting, testing, evaluating & monitoring LLM-powered applications - Parea AI (YC S23)

MCP server providing seamless access to the IGDB (Internet Game Database) API for AI assistants. Search games, get detailed information, find trending titles, and execute custom queries through the Model Context Protocol.

自动标注！支持世间万物！由llm解构提示词，再组合标注,轻松制作数据集

The quality gate for the MCP ecosystem. Spec compliance, security scanning, and performance benchmarks for MCP servers.

Zero-dependency AI memory system with hook-level rules enforcement for Claude Code

Simple GUI with some python scripts I use to convert folders to single txt output for AI data dumping

Hyperliquid trading intelligence for AI agents — cohort analytics, liquidation heatmaps, trader profiling, and real-time market data across 1.3M+ wallets.

Browser for agents in a form of cli, API or library.

Design pattern + Claude Code skill for AI engineers. LLM judgment and deterministic code in mutually-generative cycles, not pipelines. Library of named graph-shapes (RAG, ReAct, codegen-with-verification, dev-time critique loops, more).

Home Assistant custom component for LLM empowerment

A simple tool to ingest code files into a single text file for LLM context.

Open-source SOC console. Free-text security incident in, MITRE ATT&CK triage card out. TF-IDF + sentence-transformer classifier, multi-provider LLM dispatch, IOC enrichment, and case management.

Workspace manager for Claude Code — start and resume isolated, multi-repo sessions with preloaded context

Reusable skills for AI coding agents (pi, Claude Code, Agent Skills standard)

Full OpenMeteo API from your terminal