OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

Openclacky

Openclacky is an MIT-licensed, Ruby-based open-source AI agent framework for building agent applications with reusable skills, a compact tool layer and OpenAI-compatible model providers.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Openclacky — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Openclacky when an open-source Ruby agent foundation, configurable model provider and skill-oriented workflow are useful requirements.

Who it is for

  • Ruby developers building AI-agent applications.
  • Teams prototyping server-side automation workflows.
  • Developers who want reusable, natural-language-defined agent skills.
  • Operators evaluating CLI, server or Docker-based agent setups.

Documented uses

  • Create a Ruby application around an AI-agent foundation.
  • Organize agent capabilities as reusable skills.
  • Connect an agent to an OpenAI-compatible model provider.
  • Prototype a server-side workflow with a CLI or container deployment.
Before you choose

Requirements & limits

The repository documents desktop installers, command-line scripts, RubyGems installation and Docker deployment. Ruby installation requires Ruby 3.1.0 or newer. The repository is MIT-licensed.

  • Ruby is the primary implementation language, with Ruby 3.1.0 or newer specified for the Ruby installation path.
  • The project documents a 16-tool core with an invoke_skill meta-tool rather than exposing every capability as a separate core tool.
  • Model access follows a BYOK approach through OpenAI-compatible APIs.
  • Docker networking affects browser automation: the README documents host networking on Linux and possible limitations on macOS and Windows.
  • The repository presents token-cost and cache figures as its own internal measurements.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Start Openclacky with Docker

Launch the documented Openclacky container and expose its server locally.

Before you start

  • Docker.
  • A published Openclacky image from GitHub Container Registry, or a locally built image.
  • On Linux, host networking is required for the documented Chrome remote-debugging connection.

Steps

  1. Pull the documented image from GitHub Container Registry, replacing the owner and version values as appropriate.

  2. On Linux, run the container with host networking and the persistent /root/.clacky volume.

  3. On macOS or Windows, run the container with port 7070:7070 and the persistent volume.

  4. Open http://localhost:7070 after starting.

Expected outcome

The container is started with the documented local server endpoint.

Guide limitations

  • The supplied Docker instructions use a placeholder repository owner and do not establish a particular release as available.
  • Browser automation may be limited on macOS and Windows because host networking is not supported there.
  • The steps do not document model credentials or a complete task run.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
3 October 2026
Original website title
clacky-ai/openclacky · Official homepage title · retained in its source language
How we review sourcesSuggest a correction