Custom agents

JavaScript library for Implementing NLP in JavaScript

UI Chatbot for ADK Agent

Data for "OntoChatGPT Information System: Ontology-Driven Structured Prompts For ChatGPT Meta-Learning" paper

Botticelli is an open-source .NET Core framework for building universal chatbots. It enables seamless integration with databases, queue brokers, speech engines, and AI models (like ChatGPT, DeepSeek, and YandexGPT) to create intelligent conversational agents and programs.

It is a chatbot for question and answering using RAG based on LLM

chatbot for stock predictions utilizing machine learning

WhatsApp Web automation to send customized messages or bulk messages to contacts with a GUI.

The not-that intelligent, but cute Artificially Intelligent bot, created when I was bored.

A Discord chatbot, based on GPT-J, trained using OKBH messages

Simple Google Gemini ChatBot for Nodejs

Flexiee is a customizable Python voice assistant that understands spoken commands, performs useful tasks,

Add smartness and conversational UX to Hubot with API.AI as back-end

Ask-Ollama is a command-line tool that allows users to interact with the Ollama models directly from the terminal. This tool provides a simple and intuitive way to ask questions and receive responses from Ollama models.

Files required for creating a college enquiry chatbot using RASA which is an open-source machine learning framework used for building automated text and voice- based chatbots. The given chatbot is able to answer user's queries on courses, admissions and placements before applying to a college.

An offline CPU-first low-resource chat application to perform RAG on your corpus of data. Powered by OpenChat and CTranslate2.

open source API for your RAG Workflows. by Maux

Miscellaneous codes and writings for MLOps

Nucleus is a modular Rust library for building advanced local AI tools and applications, built-in RAG for private documents, and an extensible plugin system for custom workflows.​

GRAG is a simple python package that provides an easy end-to-end solution for implementing Retrieval Augmented Generation (RAG). The package offers an easy way for running various LLMs locally, Thanks to LlamaCpp and also supports vector stores like Chroma and DeepLake.

Local-first Supabase AI starter kit with n8n, pgvector RAG, Ollama, Kong, and one-command setup.

Set up a modern LLM app by running one command

A Retrieval-Augmented Generation (RAG) Model-Controller-Provider (MCP) server designed to assist AI agents and developers in understanding and navigating codebases.. It supports incremental indexing and multi-language parsing, enabling LLMs to understand and interact with code.

[TPAMI 2026] Recurrence Meets Transformers for Universal Multimodal Retrieval

Oscillink — Self‑Optimizing Coherent Memory for Embedding Workflows

AI skill for @chenglou/pretext — exact text metrics without DOM reflows

One memory, every terminal — a shared memory layer for any MCP client.

BluePilot is AI Powered Website Builder

🤖 Automated bot/agent for developer workflows

Data Dialogue enables natural language querying of databases by integrating LLMs with SQL databases.

Bayesian decision theory engine for AI agents — Beta posteriors, VOI, and EU maximisation. Foundation for credence-router.

JAX Multi-Agent RL, Neuro-Evolution, and A-Life Library

Securing Agentic AI Developer Day shows developers how to take an agentic AI reference workflow to production securely.

由古埃及莎草纸得名，高效的AI Agent知识管理工具

🍣 Chonky - A Superhuman LLM Auditing Agent for Solidity

Shell AI - An agentic cli powered by ollama.

模块化 AI Coding Skills 仓库，覆盖开发工具、自动化、Obsidian 与视频处理场景

Bring free CodeRabbit AI code reviews into Neovim via the CLI

🚀 A blazingly fast, modern chat interface built with Rust/WASM and Leptos, featuring local AI model execution via WebLLM. Privacy-first design with no backend dependencies.

C#/.NET binding of llama.cpp

In this course you'll learn to use Gradio to create user-friendly apps with minimal code: Summarize text using a large language model, generate image captions, and chat with an open source LLM. Gain practical knowledge to build interactive demos faster.

Sample App to integrate SalesIQ Android SDK (Mobilisten)

Chatbot that answers OpenStreetMap-related queries powered by Rasa Open Source.

An LLM-powered chatbot for fediverse. A tech demo for BotKit.

Compare chatbots pairwise via multi‑round evaluations for SE tasks.

Subscribe to instant notifications from Student Portal. Don't miss Marvel movie tickets again!

Fine-tuning a quantized Llama 2 chat model on Q&A pairs from counselchat.com to provide empathetic and appropriate mental health advice

WhatsApp Cab Booking Bot is a Node.js project for easy cab reservations via WhatsApp. It features user-friendly booking for passengers and convenient command-based management for owners. Enhance the cab booking experience with this streamlined solution in the familiar WhatsApp interface.

Library of composable well-architected CDK solution blueprints for real-world use cases — AI agents, document processing, serverless applications and more. Deploy or customize on AWS in minutes.

An AI conversational solution based on a framework-agnostic core SDK and a decoupled architecture.一个基于框架无关 Core SDK 和解耦式架构的 AI 对话解决方案

PWA chat with Gemini Nano running locally in Chrome using Prompt API, no server, no API key, works fully offline.

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

synchronizes a directory with e.g. markdown files with a knowledge base in OpenWebUI

Knowledgeable Embedding: Injecting dynamically updatable entity knowledge into embeddings to enhance RAG

An AI-powered investment analysis tool 📈 that leverages simple ReAct AI agent flow framework and financial analysis techniques to provide comprehensive portfolio insights. This intelligent agent helps investors make data-driven decisions by offering deep portfolio risk assessment, stock profiling, and personalized recommendations.

A2UI for Google Apps Script provides a seamless way to implement Google's Agent-to-User Interface (A2UI) protocol entirely within the Google Workspace ecosystem.

Self-hosted personal AI — remembers what matters, stays on your server

Advancement at the intersection of cognitive science, temporal knowledge graphs, database systems, and AI.

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.

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

Open-source MCP execution-evidence recorder: wraps one upstream MCP server and records what an agent declared, what the proxy observed, and what it reported — a signed local chain for humans to reconcile.

This repository contains sample code demonstrating how to implement a verified semantic cache using Amazon Bedrock Knowledge Bases to prevent hallucinations in Large Language Model (LLM) responses while improving latency and reducing costs.

Structured local memory storage and retrieval for LLM agents

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.

File-first memory infrastructure for AI agents, built with .NET 8 and Azure backends

A collection of step-by-step marketing playbooks for executing various marketing strategies. Each playbook can be fully executed by Toffu the AI Agent.

Shoe store WebMCP Demo for Google Chrome

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

Privacy-first AI interview assistant with live transcription, real-time AI suggestions for any type of interviews and coding challenges

夏杰语音插件AI管家，AI Manager

问AI是一个专为服务器运维和个人主机管理设计的CLI工具，通过集成AI能力，帮助用户快速查找和执行系统命令，提升运维效率。它能够智能解析用户需求，提供精准的命令建议和执行方案，是运维人员的得力助手。

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

🗿Java Library For Wit.ai

DesktopClaw is a state-aware desktop pet interface for your OpenClaw instance. It brings your AI to life as a reactive companion you can interact with via voice or text, while providing real-time session visibility, task feedback, and quick action triggers through a persistent, animated desktop presence.

ChatGPT style interface for open-source LLMs, allowing completely free, offline, and private AI use. Connect with models downloaded from Ollama, or load models directly in the browser with WebLLM.

PDF Screenshot OCR Analysis with Google Gemini Pro

Self-hosted hybrid search over your documents: BM25 plus embeddings, optional reranking, folder watching, and the page, passage and reasons behind every result.

[ACL 2025] GaRAGe: A Benchmark with Grounding Annotations for RAG Evaluation.

CodeGrok MCP is a Model Context Protocol (MCP) server that enables AI assistants to intelligently search and understand codebases using semantic embeddings and Tree-sitter parsing.

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

Neural Computation Protocol (NCP): composable, sandboxed Bricks + graphs for auditable, replayable agentic systems.

Mine code MCP is a MCP for minecraft datapack/mod/ressource pack devs. It is for ai agents and provides them tools to access wikis, generators, latest bugfixes, and changelogs per update.

The only true Desktop agent that can do actual job, Create your company AI brain and departments

Single-container deployment: Gastown + OpenClaw + KimiGas — multi-agent AI workspace with Telegram overseer

A simple open-source dashboard to analyze how AI is disrupting the Data Science job market

Light-weight AI agent evaluation and optimization framework

Joanium Personas

🥾 _b00t_: state of the art agentic harness tooling & dynamic context initialization

PandaGenie's official modules source code

AI SEO platform created with nuxt

ARLC 2026 Agentic RAG Legal Challenge — Legal QA pipeline for DIFC court documents. Hybrid BM25 + vector retrieval, cross-encoder reranking, answer-grounded page verification.

It shows how to use wiki for the data source of agent.

API/MCP wrapper for RagAnything

LLM-maintained markdown wiki on a git-native substrate. Obsidian-compatible, three-layer retrieval (grep + BM25 + embeddings), explicit supersession. Built on js-doc-store, js-vector-store, js-git-store.

ShopFilter 是由 OpenCode AI 智能体驱动的跨平台电商商品聚合与智能选品助手。输入关键词即可触发智能体自动化工作流：多平台并发抓取商品数据，多维条件筛选（价格、评分、评论、包邮等），加权综合评分模型自动排序，最终输出最优购买决策。基于 Qt6 + C++17 构建，采用插件式架构与多线程并发，界面简洁现代。全程由 AI 智能体辅助开发，人机协作打造。

A full-stack, agentic workflow programming platform. Built for vibe-coding and with vibe-coding.

Self-hosted Telegram bot — remote control your Windows PC with Gemini AI, OCR automation, live desktop streaming & scheduling.

Model Context Protocol server for BlackDuck Coverity Connect static analysis platform

A Python-based logical reasoning system combining rule-based engines with Large Language Models (LLMs) for business automation. Supports deduction and hypothesis testing, partial fact completion, and automated fact retrieval via documents or chat. Features include explainable reasoning, workflow integration, and customizable knowledge bases.