LLM chatbot integration framework / multi-channel bot builder
A lightweight Python framework that connects large language models (ChatGPT, Claude, Gemini, etc.) to a dozen application channels (Telegram, Slack, Gmail, WeChat, web, terminal) through a single config file.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Choose it for a much larger plugin ecosystem and built-in web dashboard, at the cost of AGPL-3.0 copyleft instead of MIT.
AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
Pick it when you want the same model/channel matrix shipped as one low-footprint Go binary rather than a Python runtime.
supports Telegram, Discord, Slack, Lark（飞书），钉钉, 企业微信, QQ, 微信, compatible with various LLMs including OpenAI, Gemini, DeepSeek, Doubao, and OpenRouter. It offers intelligent conversation, image generation, video creation, and more. Works seamlessly in both private chats and group settings.
Choose it for a Node.js stack with WhatsApp/WeChat auto-reply and group moderation features.
🤖 Multi-platform IM AI Agent for Telegram, WhatsApp, Lark, and WeChat. Connects ChatGPT / Claude / Kimi / DeepSeek / Ollama / Pi for auto-replies, community analysis, contact management, and inactive-friend detection.
Pick it when you need knowledge-base orchestration and a plugin system under Apache-2.0 with a web console.
Production-grade platform for building agentic IM bots - 生产级多平台智能机器人开发平台/ Agent、知识库编排、插件系统 / Bots for Discord / Slack / LINE / Telegram / WeChat(企业微信, 企微智能机器人, 公众号) / 飞书 / 钉钉 / QQ / Matrix e.g. Integrated with ChatGPT(GPT), DeepSeek, Dify, n8n, Langflow, Coze, Claude, Gemini, GLM, Ollama, SiliconFlow, Moonshot, openclaw / hermes agent, deerflow
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Choose it if your stack is already the Koishi bot framework and you want LLM chat as a plugin rather than a standalone service.
多平台模型接入，可扩展，多种输出格式，提供大语言模型聊天服务的插件 | A bot plugin for LLM chat with multi-model integration, extensibility, and various output formats
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Use only if WhatsApp is your single channel and you want a minimal TypeScript bot instead of a multi-channel framework.
ChatGPT + DALL-E + WhatsApp = AI Assistant :rocket: :robot:
Discord-only and slash-command driven — take it when your users already live inside Discord.
Make Discord your LLM frontend - Supports any OpenAI compatible API (OpenRouter, Ollama and more)
Only for AWS Lambda deployments needing pre-LLM multi-platform bot scaffolding; unmaintained for 4+ years and no LLM providers.
Create chat bots for Facebook Messenger, Slack, Amazon Alexa, Skype, Telegram, Viber, Line, GroupMe, Kik and Twilio and deploy to AWS Lambda in minutes
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
Use it when you only need a hosted Next.js web chat UI, not multi-channel IM integration.
A full-featured, hackable Next.js AI chatbot built by Vercel
These projects were analysed and named bot-on-anything among their alternatives. The relationship is not symmetric — how bot-on-anything rates them is a separate judgement, made when bot-on-anything is analysed in its own right.
calls bot-on-anything “Pick it when you need Telegram plus Slack/Gmail/web endpoints from one Python codebase.”
💬 Telegram bot with ChatGPT & Claude Python-based, using OpenAI's API.