alfredfrancis/ai-chatbot-framework

A python chatbot framework with Natural Language Understanding and Artificial Intelligence.

What it solves

This project provides a low-code platform for building AI chatbots without requiring deep expertise in artificial intelligence or extensive coding. It simplifies the creation of natural language conversational scenarios and the training of bots for specific tasks.

How it works

The framework uses a Python-based backend (FastAPI) and a React/NextJS frontend to provide a DIY admin dashboard. It combines several NLU techniques, including Spacy word embeddings, machine learning for intent recognition and entity extraction, and zero-shot NLU using Large Language Models (LLMs). It also supports multi-turn conversations, persistent memory, and the ability to fulfill API requests through tool calling.

Who it’s for

Developers and business owners who want to self-host a customizable AI chatbot platform that can be integrated into channels like Facebook Messenger or a website via REST API.

Highlights

  • Low-Code Admin Dashboard: Effortless bot development and training via a smooth UI.
  • Advanced NLU: Combines traditional ML (scikit-learn, TensorFlow) with LLMs for intent and entity recognition.
  • llm-powered tool calling: Ability to fulfill API requests during conversations.
  • Self-Hosted: Fully self-hosted infrastructure using Docker, Kubernetes, and MongoDB.
  • Multi-Channel Support: Integrations for web, Facebook Messenger, and upcoming support for Slack and WhatsApp.

Related

  • Project
    Weizhena/Deep-Research-skills

    A structured research workflow for Claude Code, OpenCode, and Codex that enables systematic outline generation, deep web investigation, and automated report creation.

  • Project
    Prism-Shadow/penguin-harness

    A local-first multi-agent development platform that automates the building, optimization, and deployment of AI agent applications, featuring a native self-evolution engine.

  • Project
    ggml-org/llama.vim

    A Vim/Neovim plugin that provides local LLM-assisted text completion and instruction-based editing via a llama.cpp server.

  • Project
    SlimeBoyOwO/LingChat

    An immersive AI companionship assistant that combines LLMs with emotion recognition, desktop vision, and Galgame-style visuals to create a reactive digital character.