Open-source alternatives to Bottender

nlp.js is a JavaScript natural language processing library and development framework used to build natural language understanding engines. It provides a toolkit for creating local machine learning models for intent classification and acts as a multilingual text processor that detects languages and normalizes text across various dialects. The framework distinguishes itself by supporting local execution on both servers and mobile devices, enabling chatbot functionality without an internet connection. It features a specialized system for conversational slot filling to collect mandatory informati

Pipecat is a framework and software development kit for building real-time multimodal AI agents and speech-to-speech systems. It utilizes a frame-based data pipeline to route audio, video, and text through a modular sequence of processors, enabling the orchestration of low-latency conversational AI. The project is distinguished by its ability to coordinate complex multimodal services, including speech-to-text, language models, and text-to-speech, within a single pipeline. It features semantic voice activity detection for natural turn-taking, state-machine conversation flows for dialogue manag

Agent Squad is a multi-agent system orchestrator and language model agent orchestration framework. It serves as an AI workflow automation engine and tool integration layer designed to coordinate teams of specialized agents to solve complex tasks through routing, parallel execution, and state management. The project is distinguished by its ability to dynamically compose purpose-specific agents on-demand and route requests based on intent, language, or domain expertise. It supports advanced coordination patterns, including parallel subtask distribution, sequential task pipelines, and the abilit

Telebot is a framework for building interactive bots using the Telegram Bot API. It provides a type-safe API wrapper and an asynchronous event handler to manage messages, commands, and user interactions. The project features a middleware-based request interception system and pattern-based event routing to map triggers to custom logic. It includes a dedicated inline query engine for generating real-time suggested results and an interactive keyboard builder for creating custom reply and inline buttons. The framework covers a broad range of capabilities, including rich media management for albu

Halley is a modular C++ game engine designed for building cross-platform interactive applications. Its core identity is defined by a hardware-abstraction graphics pipeline for consistent rendering across different operating systems and an entity-component-system architecture that separates game state from processing logic. The framework features a hot-reloading development environment that allows updating application logic and assets at runtime without requiring a full process restart. It also includes a multiplayer networking framework based on an asynchronous messaging system to manage real

Miniflare is a local simulator and emulator for Cloudflare Workers. It provides a serverless runtime environment on a local machine, allowing for the development and testing of functions and edge APIs without deploying to a production cloud environment. The project implements a local simulation of edge storage primitives, including key-value stores, object storage, and durable objects. It further enables a local integration test bed where serverless functions are executed within isolated sandboxes. The toolset covers a broad development surface, including hot-reloading via file-system monito

tModLoader is a modding framework and toolset designed for expanding game content and extending core game logic. It provides a polymorphic content API that allows for the creation of new items, NPCs, projectiles, and world assets through object-oriented inheritance. The project is distinguished by its advanced code modification capabilities, utilizing intermediate language bytecode patching and reflection-based private access to alter internal game behavior. It features a hot-reloading assembly runtime that enables developers to recompile and apply source code changes in real-time without res

Padrino is a full-stack web application framework that extends Sinatra to build modular applications. It provides a structured environment for organizing URL endpoints into hierarchical controllers with named route aliases, dynamic parameters, and custom request lifecycle filters. Developers can combine multiple independent web sub-applications into a single running instance with isolated routing and configuration. The framework includes command-line automation tools for project generation, controller and action scaffolding, database model creation, and database migration generation. It featu

DailyHotApi is a trending data aggregator and serverless backend API. It collects and normalizes trending information from multiple online sources into a unified data structure and serves this information as an asynchronous data fetcher. The system transforms aggregated data into standardized RSS and JSON formats for distribution to client applications. It incorporates a caching layer that stores frequently accessed results for a set duration to reduce redundant network requests. The project is designed for deployment on serverless platforms or containerized environments using environment-ba

Koishi is an open-source framework for building multi-platform chatbots, designed around an adapter-driven architecture that lets a single bot connect to multiple messaging services with consistent logic. It provides a plugin-based development platform with hot reload support, enabling developers to write and update bot extensions using TypeScript without restarting the application. A web-based management console offers a graphical interface for configuring plugins, commands, permissions, and monitoring runtime status. What distinguishes Koishi is its combination of a dynamic plugin lifecycle

This project provides a comprehensive architectural framework and set of standardized patterns for building, securing, and scaling production-ready Node.js applications. It serves as a foundational guide for establishing consistent development workflows, operational observability, and reliable service integration across distributed software systems. The framework distinguishes itself by emphasizing a schema-first approach to API development, ensuring that interface definitions drive the creation of server stubs, client libraries, and type definitions. It promotes a cloud-native posture by int

This project is a cross-platform bot manager and development framework built on Nonebot2. It enables the creation and deployment of automated assistants that function across multiple chat services using a unified codebase and a shared communication protocol. The system distinguishes itself with an integrated virtual economy plugin for tracking currencies and user rankings, alongside a dedicated administration web interface for monitoring system health and configuring plugin permissions. It utilizes an asynchronous event-driven architecture and an adapter-based abstraction layer to maintain co

OpenClawChineseTranslation is a framework for building conversational assistants that functions as a cross-platform chat gateway. It synchronizes conversational data between multiple external messaging applications and a centralized core, allowing users to interact with an assistant across different platforms. The system utilizes a plugin-based extension architecture to integrate external services such as note-taking and password managers. It features a model-agnostic provider interface, which enables the underlying intelligence to be swapped by selecting different large language model provid

Typebot is a visual chatbot builder and conversational platform designed for lead generation and data collection. It provides a drag-and-drop workflow designer that converts visual nodes into structured conversation logic, allowing users to build interactive forms and chatbots with conditional routing. The platform is designed as a self-hosted conversational infrastructure, enabling the deployment of the entire application stack on private servers using Docker and PostgreSQL. This allows for complete control over data storage and server maintenance. The system integrates with external servic

Baileys is a TypeScript API client library used to interact with the WhatsApp Web API via WebSockets without requiring a browser. It functions as a real-time communication tool that handles bidirectional data exchange and event-based socket connections. The project includes a dedicated toolkit for managing WhatsApp Business profiles and product catalogs, alongside a session manager that authenticates accounts using QR codes or pairing codes and persists session state to disk. Its capabilities cover a wide range of messaging functions, including multi-type message transmission, chat history s

ChatUI is a React conversational UI library and framework designed for building messaging interfaces. It provides a set of components for creating conversation flows, including message bubbles, input areas, and structured message hierarchies. The library distinguishes itself through specialized AI agent interface features, such as the visualization of an agent's reasoning process and simulated typing animations that render text character-by-character. It also includes a system of pre-designed conversational card templates for rendering banners, selection lists, and questionnaires within a cha

This project is a JavaScript library for integrating applications with the WeChat public platform. It provides the infrastructure necessary to automate message processing, manage user interactions, and connect backend services to the platform. The library enables the design of conversational flows through an interactive menu system and state-based reply mechanisms. It supports customer service automation by routing conversations between automated bots and live human agents, and it includes specialized processing for messages sent from connected hardware devices. Capability areas cover automa

Koog is an LLM agent framework used to build autonomous entities that execute tool-based workflows. It utilizes a graph-based workflow engine to define agent behaviors and decision paths as a directed graph of nodes and edges. The framework distinguishes itself through a model provider orchestrator that enables dynamic switching, load balancing, and automatic fallbacks between different AI backends. It implements the Model Context Protocol to connect agents to remote tool servers and features a RAG memory system using vector embeddings to maintain long-term conversation context. The project

wxauto is a Python library and bot framework designed for the programmatic control of the WeChat Windows desktop client. It functions as a wrapper that enables the automation of messaging and social feed functions by simulating user interface interactions. The library distinguishes itself by providing a bridge between network requests and local UI automation, allowing users to expose automation capabilities via a web interface. It utilizes background execution and simulated system-level inputs to trigger application events without moving the physical mouse cursor. The project covers extensiv

GLaDOS is a multimodal AI agent framework designed to create autonomous systems that process text, speech, and visual data to interact with users and their environment. It centers on an AI personality framework that emulates complex character personas using a multi-agent architecture and configurable behavioral profiles. The project distinguishes itself through an integrated tool layer that connects language models to external hardware, smart home devices, and system APIs via a standardized protocol. It features a character text-to-speech engine with low-latency playback and interruption hand

JDA is a Java library that serves as a Discord API wrapper, bot framework, and voice API client. It enables applications to interact with the Discord REST API and real-time gateway to build automated assistants, manage servers, and handle user interactions. The project includes a sharding manager to distribute gateway connections across multiple shards for scaling high-volume deployments. It also provides a UI component library for constructing interactive buttons, select menus, and modal forms within messages. Its capabilities cover voice and audio management, including audio streaming and

MaiBot is an intelligent conversational agent and plugin-based framework designed to simulate authentic human personality and digital companionship. It functions as a multi-platform messaging bot that connects a central agent to various instant messaging services through a standardized adapter system. The project is distinguished by its use of a knowledge graph memory system to maintain consistent personas and long-term user profiles. It also acts as a tool orchestrator, coordinating multi-turn reasoning and external tool calls to manage the natural pacing and flow of conversations. The fram

Context-Engineering is a prompt engineering framework and cognitive architecture for large language models. It provides a set of patterns and methodologies for designing structured prompts and modular reasoning flows that decompose complex tasks into specialized, step-by-step problem solving templates. The project distinguishes itself through stateful prompt management and context window optimization. It maintains persistent memory across multiple interaction turns by compressing conversation history into compact internal state cells and employs techniques to maximize information density per

This Python SDK provides a comprehensive toolkit for synthetic audio generation, voice cloning, and the development of conversational AI agents. It enables the creation of lifelike spoken audio from text, the replication of human voices through custom cloning, and the deployment of real-time voice agents capable of interacting with external large language models. The library distinguishes itself through deep integration of conversational AI capabilities, including the design of agent personas and the execution of real-time actions via APIs. It supports professional-grade audio production thro

Wenda is a self-hosted infrastructure and gateway platform for deploying language models within internal networks to ensure data privacy and security. It functions as a centralized hub and API gateway that unifies communication between various offline model runners and online service providers through a single interface. The platform includes a workflow orchestrator that uses custom scripts and API calls to automate complex conversation flows and model settings. It also incorporates a retrieval system that augments model responses with external knowledge retrieved from vector databases and se

The agent-framework is an LLM agent orchestration framework and multi-agent workflow engine designed for building autonomous AI agents. It provides a tool integration layer for binding external functions, APIs, and sandboxed code as executable tools for language models. The framework distinguishes itself through a graph-based system for designing sequential and parallel task flows, featuring state management and checkpointing for long-running processes. It implements comprehensive conversational state management and an observability suite that uses telemetry to trace execution flows and monit