This repository is a collection of deployable templates and educational cookbooks for building real-time LLM applications using the Pathway framework. It provides ready-to-deploy RAG (Retrieval-Augmented Generation) solutions with live data synchronization from various sources (files, Google Drive, SharePoint, etc.), built-in vector and hybrid search, and integration with LangGraph for agentic workflows. The templates are production-oriented with Docker support, while the cookbooks demonstrate advanced patterns like Self-RAG with self-reflection and query rewriting. The codebase is well-structured but exhibits some duplication across templates, and the core logic relies heavily on the external Pathway library.
Kotaemon is a production-grade Retrieval-Augmented Generation (RAG) application for chatting with documents. It provides a full-stack Gradio web UI with user management, document indexing (PDF, DOCX, HTML, images, web URLs), hybrid retrieval (vector + full-text), reranking, and multi-step reasoning pipelines (simple QA, question decomposition, ReWOO agent). The architecture is a monolith split into two Python libraries: `kotaemon` (core components: embeddings, LLMs, indices, storages, loaders, agents) and `ktem` (application layer: UI pages, reasoning pipelines, database models, settings). It supports multiple LLM providers (OpenAI, Azure, Anthropic, Gemini, Cohere, Ollama, LlamaCpp), embedding models, vector stores (Chroma, LanceDB, Milvus, Qdrant), and document stores. The system is highly configurable via environment variables and a settings UI. While primarily an application, it includes data/research elements such as document loaders, OCR pipelines, graph-based indexing (GraphRAG, LightRAG, NanoGraphRAG), and a training dataset for question rephrasing.
ChatRWKV is a collection of inference tools, demos, and a pip package for the RWKV language model family (v4-v7), a 100% RNN architecture that rivals transformers in performance. The repository provides interactive chat scripts (chat.py, v2/chat.py), API demos (API_DEMO_CHAT.py), model conversion utilities, state merging, music generation (MIDI/ABC), and benchmarking scripts. The core RWKV model class (rwkv_pip_package/src/rwkv/model.py) supports flexible deployment strategies (CPU/GPU, fp16/fp32/bf16, int8 quantization, streaming) and includes custom CUDA kernels for efficient WKV operations. The tokenizer module (tokenizer/rwkv_tokenizer.py) offers a fast trie-based byte-level tokenizer alongside a reference implementation. While the repository is primarily a research/demo project with many ad-hoc scripts and hardcoded paths, the pip package and core components are well-crafted and demonstrate significant engineering skill in GPU optimization and model inference. The codebase is actively maintained and supports the latest RWKV-7 architecture.
Evolution API is a production-grade, multi-tenant WhatsApp API gateway built with Node.js, TypeScript, and Express. It manages independent WhatsApp instances via Baileys (WhatsApp Web), Meta Business API, and its own Evolution API channel, providing REST endpoints for messaging, chat management, groups, labels, and media. The system integrates deeply with chatbot platforms (Typebot, OpenAI, Dify, Flowise, N8N, EvoAI, EvolutionBot) and event systems (Webhook, WebSocket, RabbitMQ, SQS, NATS, Kafka, Pusher), and includes storage via S3/MinIO and CRM sync with Chatwoot. The architecture follows a modular controller-service pattern with Prisma ORM (supporting MySQL and PostgreSQL), Redis caching, and centralized configuration. It is actively maintained with frequent updates, extensive migrations, and CI/CD pipelines.
This is an embedded firmware application for ESP32-based AI voice assistant devices. The code implements a full voice interaction pipeline: microphone input via I2S/PCM, Opus audio encoding/decoding, WebSocket/MQTT communication with a server, wake-word detection (ESP-SR), an LVGL-based user interface with emoji and chat display, an MCP (Model Context Protocol) server exposing device tools to the AI, and support for OTA updates. The architecture is a monolithic FreeRTOS application using ESP-IDF, with a strong board abstraction layer that allows support for over 130 hardware variants (ESP32-S3, C3, C6, P4, etc.) with different audio codecs, displays, cameras, and network modules (WiFi, 4G, Ethernet). The codebase is actively maintained with regular commits and a large community, but suffers from significant code duplication across board definitions, especially in power management and display initialization, which increases maintenance burden.
This repository is an Obsidian plugin that integrates GitHub Copilot's AI-powered coding assistance directly into the Obsidian note-taking application. It provides two main features: inline code suggestions as you type (similar to Copilot in IDEs) and a chat interface for interacting with Copilot in a sidebar. The plugin handles authentication with GitHub Copilot, manages conversation history, renders Mermaid diagrams from AI responses, and allows linking to Obsidian notes using [[double bracket]] syntax in chat conversations. The architecture separates concerns into distinct modules for inline suggestions (using LSP protocol) and chat functionality (using direct API calls), with React powering the chat UI and Zustand managing state.
Talkio is a local-first desktop (Windows/macOS/Linux via Tauri 2) and Android application for multi-AI group chat. Unlike a conventional ChatGPT wrapper, it orchestrates conversations where multiple AI models β OpenAI Chat Completions, OpenAI Responses, Anthropic Messages, plus DeepSeek/Groq/Ollama via compatible endpoints β converse together in one thread, each bound to a configurable persona/identity with its own system prompt and model selection. Core features include streaming SSE generation, an MCP (Model Context Protocol) client with both stdio subprocess (desktop) and custom streamable-HTTP transports, a tool-call loop supporting iterative tool execution, automatic conversation context compression, chat branching/regeneration, file attachment parsing (PDF/Word/Excel/images), and export to Markdown/PDF. All data is local: conversations persist in SQLite via the Tauri SQL plugin, while providers, identities, MCP servers, and settings live in localStorage.
The QwenLM/Qwen3 repository provides resources for the Qwen3 family of large language models, including model cards, documentation, and usage examples. It serves as an application-focused hub for inference, deployment, training, and evaluation of Qwen3 models. The repository contains extensive multilingual documentation, inference demos (web and CLI), deployment guides for various frameworks (vLLM, SGLang, etc.), training examples (using Axolotl, LLaMA-Factory, etc.), quantization techniques, and evaluation harnesses (notably for ARC-AGI). While the core model weights are hosted externally, this repo enables end-to-end usage through well-organized examples and scripts.
XianyuAutoAgent is an AI-powered customer service bot for the Chinese second-hand marketplace platform Xianyu (ι²ι±Ό). It connects via WebSocket to Xianyu's messaging service, receives user messages, and generates intelligent replies using a Large Language Model (LLM) with multi-expert routing. The system features intent classification (price negotiation, technical support, general query), dynamic pricing negotiation with gradual concessions and adaptive LLM temperature, context-aware conversation management via SQLite, and a manual takeover mode. It handles authentication via cookies, token refresh, heartbeat, and captcha-triggered cookie re-entry. The bot operates as a long-running async process, suitable for deployment via Docker.
ChatWiki is an open-source, multi-service AI chatbot and workflow automation platform primarily targeting the WeChat ecosystem. In production, it operates as a suite of Go microservices (chatwiki, message_service, code_run, websocket, plugin, llm_runner) behind a Gin web server, with a Vue 3 admin panel, separate mobile/PC/Electron frontends, and an embeddable SDK. The core functionality includes knowledge base management (document ingestion, chunking, vector storage with pgvector), a LogicFlow-based visual workflow builder, multi-channel messaging (WeChat Official Account, Mini Program, Feishu, DingTalk, Telegram, WhatsApp, LINE), and an AI agent framework called Clawbot with skill reuse. External dependencies include PostgreSQL (with pgvector and AGE graph extension), Redis, NSQ message queue, and optional Neo4j and E2B sandbox. While the system is primarily an application, it incorporates data-intensive components such as RAG pipelines, LLM request logging, and daily statistics, giving it a hybrid character.
GeeksBlabla is a Moroccan tech community podcast website built with Astro. It serves as a content hub for podcast episodes (200+ episodes in Darija), blog articles, community projects (BlablaConf, State of Dev, Awesome Morocco), and a team page. The site features a chatbot (BlaBlator) powered by RAG over podcast transcripts using ChromaDB and OpenAI, an episode creation workflow integrated with Notion as a CMS, and YouTube API for metadata. The frontend uses Astro with React interactive islands, Tailwind CSS, and Rive animations for engaging visuals. The architecture is a hybrid of static site generation (Astro static output) with dynamic server actions and API routes deployed to Cloudflare Workers. It includes CI/CD workflows for episode validation, Spotify upload, and YouTube description syncing. While well-structured and feature-rich, it relies on many external services (Notion, OpenAI, ChromaDB, YouTube, Cloudinary, Supadata) and has some code duplication (two identical server action files).
This repository implements a full-stack AI-powered food recommendation application called 'δ»ε€©εδ»δΉ' (What to eat today). The system combines a Next.js frontend with a Python Flask backend that uses a GraphRAG (Retrieval-Augmented Generation) architecture leveraging Neo4j for graph-based recipe relationships and Milvus for vector similarity search. Users interact via a chat interface to receive personalized recipe recommendations with step-by-step cooking instructions. The application includes a comprehensive recipe knowledge base in markdown format, Docker-based deployment orchestration, and a modular RAG pipeline with intelligent query routing and session management.
The repository is a simple Flask web application demonstrating interaction with the Google Gemini API for text and multimodal chat. It provides a UI for sending text messages and uploading images, maintaining a chat session via the Gemini API and streaming responses using Server-Sent Events. The architecture is monolithic with backend logic in app.py, served frontend static files, and a single HTML template. Key endpoints include '/' for the main page, '/upload' for file handling, '/chat' for message reception, and '/stream' for response streaming. While functional for demonstration, the application relies on global variables for state management (chat session, pending message, pending image), making it unsuitable for production multi-threaded environments without modification. The code is straightforward and serves as an educational starting point for Gemini API integration, but lacks reusable components due to tight coupling and simplicity-focused design. Dependencies are current, and the repository shows recent maintenance activity.
This repository is primarily a large collection of GPT prompt templates (markdown files) designed for use with AI chat platforms like FlowGPT or gptcall.net. Each prompt file defines a specific role or task for the AI, such as a resume editor, coding tutor, fitness planner, or creative writing assistant. The repository also includes an Android application (OpenClaw and Codex) referenced in the README, along with Node.js scripts (update.mjs, db.mjs) for managing the prompt data. The prompts are structured with placeholders for user input and often request specific output formats, enabling users to import them into chat interfaces to obtain specialized AI behavior without crafting prompts from scratch. While the prompt library is extensive, it contains significant duplication, minimal-effort entries, and some policy-risking content (e.g., jailbreaks, NSFW role-play), which affects overall quality and reuse potential.
Flowise is an open-source, low-code platform for visually building AI agents, chatbots, and LLM-powered workflows. The monorepo contains a full-stack application: an Express/TypeORM backend (packages/server), a React/MUI frontend (packages/ui), a component library (packages/components) defining hundreds of pluggable nodes for LLMs, tools, memory, vector stores, and retrievers, a newer canvas SDK (packages/agentflow) for embedding agent flows, and an observability package (packages/observe) for execution monitoring. The platform supports multi-tenancy, RBAC, SSO, job queues (BullMQ), and enterprise features like usage quotas and audit logging. Despite being archived, the codebase demonstrates a comprehensive architecture for a visual AI orchestration platform with extensive third-party integrations (LangChain, LlamaIndex, OpenAI, Anthropic, etc.). However, the code exhibits significant technical drift: many nodes are marked as deprecated, database migrations are duplicated across four dialects, and there is evidence of incomplete migration from v1 to v2 canvas components. The repository is large and functionally rich, but its maintenance status (archived) and accumulation of deprecation warnings reduce its long-term viability.
This repository is a Chinese-language chatbot built with Rasa 1.10.18, a now-deprecated version of the Rasa framework. It implements a simple customer service bot for telecom queries (phone bill and data usage) using a BERT-based NLU pipeline (HFTransformersNLP with bert-base-chinese) and a rule-based dialogue management system with story-driven flows. The codebase is minimal: a single custom action for querying consumption, a few intents and entities, and a set of dialogue stories. The project is functional but lacks tests, CI/CD, or modern Rasa practices. The pinned dependencies (rasa==1.10.18, transformers==2.4.1) are severely outdated, and the code relies on deprecated Rasa components. While the repository has accumulated stars (983) due to its accompanying blog series, the actual code is a basic Rasa template with little reusable craftsmanship. It serves as a learning example for building a Chinese chatbot with Rasa 1.x, but is not suitable for production or reuse without significant modernization.