chatbot
14 repositories
A growing archive of leaked chatbot system prompts — This repo collects verbatim, regularly updated system prompts from Claude, ChatGPT, Gemini, Grok, Cursor, Kimi and more. It's useful for prompt engineers, researchers, or anyone curious how major AI assistants are instructed behind the scenes; contributions via PR are welcomed to keep entries accurate.
Build AI Agents, Visually
AstrBot: one bot core for Telegram, Discord, QQ and LLM agents — AstrBot bundles chat platform integrations, LLM access, plugins and agent features into a single Python framework, positioned as a self-hosted alternative for building AI assistants across IM apps. It supports MCP and runs via Docker, aimed at developers who want one codebase instead of separate bots per platform.
QwenPaw: a self-hosted personal AI assistant with layered memory — QwenPaw is a self-hostable personal AI assistant built on Alibaba's agentscope stack, deployable locally or in the cloud with no mandatory API key via its built-in QwenPaw-Flash models or Ollama/LM Studio. It adds a three-layer memory system (working context, full history, self-evolving knowledge base), sandboxed security guards, and multi-agent orchestration, aimed at users wanting a private, extensible assistant across chat channels.
Tencent's Go-based platform turns documents into RAG, agents and wikis — WeKnora is a Tencent open-source framework that converts raw documents into a queryable knowledge base, combining RAG retrieval, an autonomous reasoning agent, and a self-updating wiki. It ships with Chrome extension and WeChat Dialog integrations, aimed at teams building Q&A chatbots and internal knowledge tools.
An open-source RAG-based tool for chatting with your documents.
An enterprise agent platform combining RAG, workflows and MCP tools — MaxKB pairs retrieval-augmented generation with a workflow engine and MCP tool-use, letting teams build knowledge-grounded agents for customer service, internal knowledge bases, and education. It supports document upload, web crawling, and models like DeepSeek-R1, Llama3 and Qwen3, aimed at enterprises wanting lower hallucination Q&A.
Self-hosted CRM pairs AI agents with WhatsApp sales flows — DeskcommCRM is an open-source, self-hosted alternative to Kommo, Octadesk and Intercom, built around native AI agents that qualify and sell via WhatsApp (WAHA). It's multi-tenant, MCP-ready and LGPD-aware, with a one-command VPS setup kit — aimed at businesses selling through chat who want no subscription fees and full data control.
FireRed-OpenStoryline is an AI video editing agent that transforms manual editing into intention-driven directing through natural language interaction, LLM-powered planning, and precise tool orchestration. It facilitates transparent, human-in-the-loop creation with reusable Style Skills for consistent, professional storytelling.
One connector, nine IM channels into DeepSeek Harness — DSH-IM is a plugin that bridges IM bots—Feishu, WeChat, DingTalk, WeCom, QQ, Slack, Telegram, Discord, WhatsApp—into DeepSeek Harness via QR code or credential login. Built on Cordis, it targets teams wanting a single integration layer instead of writing separate bot connectors per platform. It's reportedly a top-ranked DSH plugin by downloads.
Easily select, start, and manage your preferred AI digital assistants on Android.
Self-hosted WhatsApp gateway with multi-session dashboard and 109+ API endpoints — WA-AKG turns WhatsApp into a self-hosted REST API using Next.js 16, Baileys and Prisma. It supports multi-session accounts, scheduled messages, auto-replies and webhooks, with 109+ documented endpoints, making it suited for developers building bots, automation or customer-service gateways.
A 2007 Nokia can't search Google anymore, so I gave it Claude, ChatGPT, Gemini and Grok. J2ME app for Nokia S40/S60 + tiny Go server.
A Two-Agent Review Pipeline for Community Support Answers — answerLoops drafts replies to community questions from your own docs/knowledge base, has a second AI agent verify them, then routes them to your team for approval (or auto-send) before posting. It's self-hostable with your own LLM, connects across Discord, Slack, GitHub, Discourse, Telegram and more, and turns resolved threads back into knowledge.