theopenconversationkit/tock

Tock, the open source conversational AI toolkit.

What it solves

Tock is an open-source conversational AI platform designed to simplify the creation of bots. It bridges the gap between deterministic, rule-based conversation flows (stories) and modern generative AI, allowing developers to build bots that can handle both structured tasks and flexible, document-based answering.

How it works

The platform combines several components to provide a comprehensive bot-building experience:

  • Generative AI & RAG: It integrates with LLM providers like OpenAI, Azure OpenAI, AWS Bedrock, and Ollama, and uses vector stores such as PGVector and OpenSearch to implement Retrieval-Augmented Generation (RAG) for answering questions based on specific documents.
  • NLP Stack: It uses an open-source NLP stack compatible with tools like OpenNLP, Rasa, and Amazon SageMaker.
  • Tock Studio: A visual user interface for designing conversation stories, configuring generative AI settings, and analyzing conversation logs.
  • Multi-channel Support: Built-in connectors allow bots to be deployed across various channels including WhatsApp, Messenger, Teams, Slack, and Google Chat.
  • Developer Tools: It provides a Conversational DSL for Kotlin, Nodejs, and Python, as well as a REST API for integration.

Who it’s for

Tock is aimed at developers and conversation designers who want to build sophisticated conversational agents that can be deployed on-premise or in the cloud via Docker or Kubernetes.

Highlights

  • Hybrid Approach: Combines RAG-based generative AI with deterministic conversation stories.
  • Broad Integration: Supports multiple LLM providers and vector databases.
  • ** uma own UI**: Includes Tock Studio for visual bot management.
  • Omnichannel Deployment: Native connectors for major messaging platforms.
  • Flexible Deployment: Supports Docker and Kubernetes (Helm chart) for cloud or on-premise hosting.

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
    vercel/chat

    Chat SDK is a TypeScript library that lets you write a single bot and run it on many chat platforms (Slack, Teams, Discord, etc.) via plug‑in adapters, with built‑in support for AI streaming, rich UI cards, and state management.

  • Project
    TykTechnologies/tyk

    Tyk is an open‑source, Go‑based API gateway that handles REST, GraphQL, gRPC, TCP and the AI‑focused Model Context Protocol. It provides auth, rate‑limiting, analytics, plugins and hot‑reload, and includes AI‑specific features (MCP proxy, integration with Tyk AI Studio). Deployable via Docker, Helm, Ansible or source compilation, it’s dual‑licensed (MPL 2.0 + commercial) and backed by an active community.

  • Project
    nrslib/takt

    TAKT is a Node‑JS CLI that orchestrates AI coding agents (Claude, Codex, Cursor, etc.) via declarative YAML workflows. It runs each step in isolated Git worktrees, enforces review/fix loops, logs every action, and can auto‑create PRs. Designed to make AI‑driven development repeatable, auditable, and less dependent on fragile prompts.

  • 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.