hexabot-ai/Hexabot

Hexabot v3 is an AI workflow automation platform, combining workflows, actions, agents, and conversational channels in one runtime.

What it solves

Hexabot provides a platform to automate repetitive tasks by building agentic workflows that can operate across different communication channels. It bridges the gap between static automation and AI-driven agents by combining workflows, actions, and conversational interfaces in a single runtime.

How it works

Users define workflows using YAML files with typed runtime contracts. The system uses a schema-first architecture (powered by Zod) to ensure that inputs and outputs are validated. It employs a binding system to separate configuration and capabilities from the actual task logic, and integrates the Model Context Protocol (MCP) for better tool and context interoperability. For data storage, it uses TypeORM with support for SQLite (local) and Postgres (production).

Who it’s for

Developers looking to build AI agents and automated workflows that require memory, RAG capabilities, and the ability to interact across multiple channels.

Highlights

  • Agentic Workflows: YAML-based definitions for structured AI behavior.
  • MCP Integration: Support for the Model Context Protocol to enhance tool interoperability.
  • Multi-channel Continuity: Ability to maintain consistency across different conversational channels.
  • Schema-first Design: Extensive use of Zod for strict validation of inputs and outputs.
  • Memory & RAG: Built-in support for explicit memory definitions and retrieval-augmented generation.

Related

  • Project
    microsoft/agent-framework

    A multi-language framework for building production-grade AI agents and multi-agent workflows in .NET and Python, featuring graph-based orchestration and built-in observability.

  • Project
    xpert-ai/xpert

    An open-source Agent platform that uses a hybrid agent-workflow architecture and a unified plugin system to build governed, enterprise-grade agentic applications.

  • Project
    spacedriveapp/spacebot

    An opinionated agent infrastructure that uses a multi-process architecture to handle concurrent conversations, long-term typed memory, and autonomous background tasks for teams and communities.

  • Project
    Shy2593666979/AgentChat

    A modern intelligent dialogue system that enables the creation and management of AI agents with multi-agent collaboration, RAG, and a three-layer memory architecture.

  • Project
    langbot-app/LangBot

    LangBot is an open‑source, production‑grade platform that lets you attach LLMs to dozens of instant‑messaging services (Discord, Slack, Telegram, WeChat, etc.). It provides a web dashboard, built‑in RAG/tool‑calling, a plugin marketplace, and a Model Context Protocol (MCP) server so other AI agents can manage bots programmatically. Quick start options include a one‑line `uvx langbot` launch, Docker Compose, or hosted LangBot Cloud. The project targets use cases like AI‑driven customer support, internal workflow automation, and cross‑platform community bots.