theopenconversationkit/tock

Tock, the open source conversational AI toolkit.

Tock – The Open Conversation Kit

What it is – Tock is an open‑source platform for building conversational AI bots. It bundles a natural‑language‑processing (NLP) stack, a visual studio (Tock Studio) for designing dialogue flows, a Kotlin‑based DSL (with Node.js, Python and REST bindings) and ready‑made connectors to many chat‑ and voice channels.

Key components

  • NLP engine – works with popular libraries such as OpenNLP, Stanford CoreNLP and Rasa, letting you plug‑in the language models you prefer.
  • Tock Studio – a web UI where non‑technical users can author “stories” (dialogue scripts), test bots and view analytics.
  • Conversational DSL – a Kotlin‑flavoured language for defining intents, entities and flow logic; the same concepts are exposed through Node.js, Python SDKs and a generic REST API.
  • Connectors – out‑of‑the‑box integrations for Messenger, WhatsApp, Google Assistant, Alexa, Twitter, etc., so a bot can be deployed to many channels without custom code.
  • Toolkits – front‑end starter kits for React (web) and Flutter (mobile) to embed a bot UI in your own applications.
  • Deployment – Docker images and Helm charts that let you run Tock on any cloud provider or on‑premise infrastructure.

Typical workflow

  1. Define intents & entities using the DSL or via the Studio UI.
  2. Train the NLP model (leveraging OpenNLP/Stanford/Rasa back‑ends).
  3. Design conversation flows (stories) in Studio, optionally testing them interactively.
  4. Connect the bot to a channel through a pre‑built connector or a custom one.
  5. Deploy the whole stack with Docker, monitor usage through built‑in analytics.

Who uses it – Companies that need a self‑hosted, extensible chatbot framework (e.g., banks, insurers, e‑commerce sites) and developers who want a Kotlin‑first approach but still need multi‑language SDKs.

Project health – The repository is actively maintained (badge shows recent commits, CI via Travis, Maven Central releases). Documentation, a live demo, and a community chat (Gitter) are provided.

Getting started – Clone the repo, run the Maven install command (or use the Docker configurations in the companion tock-docker repo), then open Tock Studio in a browser to begin building bots.

TL;DR – Tock is a full‑stack, open‑source conversational AI platform that lets you build, train, and deploy bots across many messaging and voice channels, with a Kotlin‑centric DSL plus Python/Node.js bindings, all runnable via Docker.

Related

  • Project
    hubtype/botonic

    An open source full-stack framework for building and deployable chatbots and conversational apps using React, Serverless, and Tensorflow.js.

  • Project
    dograh-hq/dograh

    Dograh AI is an open‑source, self‑hostable platform for building and testing voice conversational agents. It provides a visual workflow editor, telephony integrations (Twilio, Vonage, etc.), and a modular LLM/STT/TTS stack that you can replace with any provider. One‑command Docker setup gets the whole system running locally, and Python/Node SDKs let you create agents programmatically. The project is BSD‑2 licensed and backed by a Slack community.

  • Dispatch
    CopilotKit Channels SDK Open-Source Release Enables Any AI Agent on Slack, Teams, Discord, and More

    CopilotKit released the open-source Channels SDK, letting developers attach any AG‑UI‑compatible AI agent to Slack, Microsoft Teams, Discord, Telegram and other chat platforms with native interactive UI.

  • Project
    TanStack/ai

    TanStack AI is a TypeScript SDK that provides type‑safe, provider‑agnostic building blocks for chat, tool‑calling agents, structured JSON outputs, multimodal generation, realtime voice, and sandboxed code execution. It ships as a core package plus optional adapters for many LLM providers (OpenAI, Anthropic, Gemini, Ollama, etc.) and framework bindings for React, Vue, Solid, Svelte, and Preact, allowing developers to compose only the features they need.

  • Project
    botpress/botpress

    Botpress Cloud is an open‑source platform for building AI‑powered chatbots. The repo contains the CLI, SDK, client libraries, example bots, and a collection of public integrations that can be deployed to Botpress Cloud workspaces. Developers use `bp init` to scaffold a bot or integration, write TypeScript with the SDK, and deploy with `bp deploy`. The system is designed for developers who want programmatic control over chatbot creation, with optional publishing of integrations to the Botpress Hub. All code is MIT‑licensed.