GitHub agents

Extract, chunk, and embed documents from 88+ formats directly into SurrealDB.

Foundational platform for integrating knowledge and AI. Simple, Secure and adaptable to your use case.

A Node.js RESTful server for a Retrieval-Augmented Generation (RAG) system using ChromaDB and Ollama!

Free, local, open-source RAG with Mistral 7B LLM, using local documents.

Chat with your documents using Generative AI & Retrieval-Augmented Generation (RAG)

Multi-user RAG chat in Azure powered by Neon Serverless Postgres. Try the live demo using the link

A modular, multilingual, and multimodal Retrieval-Augmented Generation (RAG) system tailored for the financial analysis of Public Investment Fund (PIF) annual reports.

Vectrain is a high-performance, modular, plug-and-play RAG pipeline that ingests data, generates vector embeddings, and stores them in vector databases for semantic search, recommendations, and analytics.

A RAG system is just the beginning of harnessing the power of LLM. The next step is creating an intelligent Agent. In Agentic RAG the Agent makes use of available tools, strategies and LLM to generate response in a specialized way. Unlike a simple RAG, an Agent can dynamically choose between tools, routing strategy, etc.

RAG-based Web Scraping

A local search system implementation using Elasticsearch for Wikipedia data indexing and retrieval.

A Discord bot that seamlessly executes bleeding-edge Retrieval-Augmented Generation (RAG) in tandem with a Large Language Model (LLM), specifically ChatGPT.

minRAG is a RAG system that starts from scratch, pursuing the ultimate simplicity and power. It consists of no more than 10,000 lines of code, requires no installation, and can be launched with a double-click

Memory system for LLMs that remembers everything you teach it during conversation. No reindexing, no context window limits. CPU by default, GPU optional.

search_with_lepton 的自部署版

AI Community Tutorial, including: LoRA/Qlora LLM fine-tuning, Training GPT-2 from scratch, Generative Model Architecture, Content safety and control implementation, Model distillation techniques, Dreambooth techniques, Transfer learning, etc for practice with real project!

Workshop on development of a Local Retrieval Augmented Generation (RAG) system

Code for the paper [SIGIR'26]“Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation”

Never forget the resource that helps to close that sales call! Power a real-time speech-to-text agent with retrieval augmented generation based on webscraped customer use-cases.

An automated project intelligence and evaluation tool for performance and migration readiness.

A web app based AutoGPT clone

Test code was written for research and verification of some Python libraries.

A game of pong made by MetaGPT and ChatGPT Code Interpreter

The web GUI & productivity workspace for OpenClaw (237K+ stars) — tasks, news, dashboards, package tracking, skill marketplace. Self-hosted & private.

AI Agent Framework with Unlimited Memory — PostgreSQL-native, self-evolving, near-zero cost

Local-first agent skill manager for VS Code / Cursor. Manage, browse, and import skills across Claude, Cursor, Codex and more.

nanobot-ts is the TypeScript version of nanobot, an ultra-lightweight personal AI assistant framework.

27 Android skills for AI agents (Claude Code, Codex, Cursor). Fixes Supabase auth, Hilt errors, design inconsistency, kapt→ksp, missing UiState states. Reduced my token bills 5×. FitGenZ AI shipped in 18 days.

Remote Agent Invocation Layer

Open Manifesto for AI Agents Touching Production Systems

Self-hosted AI agent platform. Multi-model chat, skills, memory, mTLS.

A local-first AI workspace that keeps your work private, organized, and ready to run.

AI-assisted development template with structured SRS/PRD/task workflows

Arbor — The Agentic RL Sandbox. Checkpoint-native. Branch-safe. Self-hosted.

The "Cloudflare for AI Agents". 7-layer security interceptor, real-time observability dashboard, and automated reliability testing for MCP and AI tool chains. Prevent hallucinations, prompt injection, and destructive tool calls.

T20: Multi-Agent. Orchestrator-delegate model. TAS. Goal -> plan -> delegate. Agents: Gemini family. Autonomous, traceable. Logs sessions. CLI. Usage: `t20-cli "goal string"`. Artifacts of high value.

Boilerplate for multi-LLM agent applications using Langchain v3 with multi-model reasoning capabilities.

Volute Reasoning Engine (VRE): Structural Epistemic Enforcement for Agentic AI

LinkedIn Job Search & Application Agent

A 100-day journey building AI-powered agents using Python, TypeScript, and LLMs to automate real-world tasks

Uncensored Language Model using FastAPI and Wizard Vicuna 30B (PoC)

This is an agentic AI system designed to help Construction Architects review construction documents and identify inconsistencies between original specifications/drawings and Contractor Submittals.

Automated Unit Test Generation with AI

The Solidity Smart-Contract Advisor is a cutting-edge tool designed to extend the capabilities of traditional language models in understanding and advising on Solidity smart contracts

This is a Streamlit-based PDF Chatbot powered by OpenAI's Language Models. The chatbot allows users to upload PDF files, extract text content, and ask natural language questions about the PDF content

Code repo for paper "KERAP: A Knowledge-Enhanced Reasoning Approach for Accurate Zero-shot Diagnosis Prediction Using Multi-agent LLMs"

VibeBox is a powerful three-agent development environment that combines Claude Code, Cursor, and Task Master AI to work together on complex software development tasks.

AI agents for Claude Code — 15 specialists that run your full software development sprint cycle. Strategy, architecture, code review, QA, security audit, and shipping. Open-source Claude Code plugin.

Multi-agent control plane for provisioning, operating, and reusing Hermes Agents on a single host.

First-class protocol and framework for enabling collaborative intelligence and communication across specialized Data Agents.

A comprehensive advanced course for building production-ready AI agents using the Strands Agents SDK. This repository contains 6 progressive labs that teach advanced capabilities including tool integration, memory persistence, Model Context Protocol (MCP), and comprehensive observability.

Vouch compiles human-owned intent into obligations, links evidence artifacts to those obligations, and produces deterministic release decisions for agent-written changes.

Search for music tracks using natural language prompts or video content via the Harmix AI API. Use when the user asks to find music, search for songs, discover tracks, needs music recommendations based on mood/genre/tempo/scene, or wants to find music for a video, video soundtrack, or music that matches video content

Conversational Data Collection. Built with Neuron AI Framework.

WORLD-TO-IMAGE: GROUNDING TEXT-TO-IMAGE GENERATION WITH AGENT-DRIVEN WORLD KNOWLEDGE

Lightweight, composable framework for building muti-agent systems with Model Context Protocol (MCP)

Glass-box agent execution engine. Deterministic, forensic audit trails, EU AI Act compliant. The PyTorch for Agents.

Demo projects and examples for Apache Flink Agents

Neovim plugin for AI-assisted coding: Claude CLI & Codex CLI backends with MCP-powered editor control

Track Al coding assistants by GitHub pull requests

Codex CLI development framework that transforms product ideas into production-ready software through structured workflows and seamless Codex CLI integration.

📚 Local paper management + AI-powered reading assistant with RAG, vector search, and multi-session chat.

Extended Claude Code framework based on SuperClaude.

Drop-in AI persona files for Skippy the Magnificent from the Expeditionary Force series. Make your AI assistant call you a dumdum.

Use Gemini on Discord, with highly customizable features. Using Thread to Create Personal Conversations with AI.

一个面向Android的多模型聊天应用。

CipherGPT is an advanced SAAS chatbot AI meticulously crafted using the MERN (MongoDB, Express.js, React.js, Node.js) stack coupled with TypeScript and the OpenAI API.

Este repositório foi criado com o intuito de automatizar algumas funções dentro do Instagram.

Self-hosted AI assistant with hybrid memory, evolving personality, and multi-channel support (WhatsApp, Telegram, Discord, Slack)

Chatbot app for creating charts with React, FastAPI, and OpenAI

Modular and scalable WhatsApp bot built with Golang.

Package for easily creating Twitch Bots

AIChatAssist is a intelligent chatbot powered by OpenAI ChatGPT API. The bot engages in natural language conversations with users.

EduBot is a powerful RAG (Retrieval-Augmented Generation) chatbot that utilizes the latest SOTA models to provide a seamless and interactive learning experience.

Open-source AI app builder. Create mobile apps by chatting and Ship directly to app store.

A repository dedicated to exploring, experimenting with, and applying Generative AI concepts and tools in practical, everyday scenarios.

A simple framework for using Claude Code or Codex CLI as the frontend to any cloud or local LLM on Apple Silicon. Connect locally via LiteLLM + MLX or LM Studio, or remotely via Z.AI, Gemini/Google AI Studio, DeepSeek, or OpenRouter.

MCP server for Storybook - provides AI assistants access to components, stories, properties and screenshots. Built with TypeScript and Model Context Protocol SDK.

Setup an MCP server in 60 seconds.

Framework to talk to AI models and intelligently route

Store all your LLM Interactions

SmartChunk is a lightweight, structure-aware semantic chunking toolkit designed to supercharge RAG (Retrieval-Augmented Generation) and LLM pipelines. Unlike naive splitters that break text arbitrarily, SmartChunk respects document structure (headings, lists, tables, code blocks) and semantic flow, ensuring cleaner, more coherent chunks.

Web Vector Storage (WVS) is a lightweight and efficient vector database that stores document vectors in the browser's IndexedDB. It supports perform semantic similarity searches on text documents using vector embeddings. Embedding is enabled through use of OpenAI, Ollama or HuggingFace Transformer embedding models.

This example shows how a multitenant service can distribute requests evenly among multiple Azure OpenAI Service instances and manage tokens per minute (TPM) for multiple tenants.

ChatGPT-like Application using RAG pattern that allows to ask question to my own documents - I Used Semantic Kernel to integrate a LLM (OpenAI) using C# to orchestrate AI pluggins (Azure Cognitive Services). For the document embeddings I used Qdrant for the vector database and Pdfpig to extract the content from the pdfs

PathRAG System - A Path-based Retrieval-Augmented Generation implementation with knowledge graph visualization and Ollama integration for enhanced question answering.

PolyG: Adaptive Graph Traversal for Diverse GraphRAG Questions

A Flutter toolkit for local and cloud LLM apps. Run GGUF models on Android and iOS, connect to OpenAI, Gemini, Claude and others through one unified API, and build fully local RAG pipelines. Supports streaming, multimodal vision models, and mobile-first AI workflows.

Context Search Engine is an AI-powered semantic document search platform built for learning, experimentation, and real-world prototyping. It demonstrates the full lifecycle of modern vector-based search — from document ingestion to chunking, embedding, indexing, and contextual query matching.

Context Engineering for LLMs: structured notes on RAG, system prompts, MCP, Agents, and Memory Management — compiled from multiple expert sources.

OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval (ACL 2025 Main Conference)

A comprehensive tool designed to enhance the retrieval and generation of academic content from the arXiv database, leveraging advanced Retrieval-Augmented Generation (RAG) techniques.

Your External Brain, Amplified 🧠 An ADHD-optimized memory augmentation system with 20+ cognitive tools, semantic search, and hyperfocus-powered knowledge management

A Python hypergraph library with provenance and SQLite persistence.

口袋大龙虾 Pocket Lobster for Android: Codex + OpenClaw, dual terminals, Shizuku system shell, shared storage, and on-device AI task execution.

CLI remote control for Unity Editor. Zero dependencies, single binary. AI agents can play, build, test, and screenshot your Unity project — no Python, no setup, just curl.

Autonomous issue resolver

Real-time visualization dashboard for Claude Code agents, teams & swarms — isometric pixel world + monitoring dashboard