OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Workflow Agents

Dark Factory Experiment

Dark Factory Experiment is a public repository for a web application maintained through scheduled Archon workflows. AI coding agents triage GitHub issues, implement changes, review and test pull requests, and merge approved work. The repository’s app provides cited, transcript-grounded chat about YouTube videos.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Dark Factory Experiment — OpenViST project profile in Workflow Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use the repository when you want to study an agent-managed issue-to-merge process or inspect its accompanying cited YouTube-transcript chat application. Its setup guide is relevant when preparing that app locally.

Who it is for

  • Developers studying AI-agent workflows for repository issue handling and software changes.
  • Teams exploring how to coordinate coding agents with deterministic workflow steps and GitHub labels.
  • People interested in a chat application that answers questions about YouTube videos using cited transcript passages.

Documented uses

  • Examine a workflow that routes GitHub issues through triage, implementation, validation, and merge.
  • Study how Archon coordinates coding-agent sessions with scripts, GitHub operations, and branching decisions.
  • Set up the included transcript-based chat application locally.
Before you choose

Requirements & limits

  • The factory does not create its own issues; people file them and promote stable releases.
  • Authentication, rate limiting, deployment configuration, and governance files are described as protected from factory changes.
  • The quick start requires PostgreSQL 16 or later with pgvector, plus Python, uv, Bun, and an OpenRouter API key.

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

Set up the chat application locally

Prepare and start the repository’s web application on a local machine.

Before you start

  • Python 3.11 or later and uv
  • Bun
  • PostgreSQL 16 or later with the pgvector extension
  • An OpenRouter API key
  • A DATABASE_URL and JWT_SECRET in app/.env

Steps

  1. Clone the repository and create app/.env, using deploy/.env.example as the annotated variable reference.

  2. Run the database migrations with cd app/backend && uv run alembic upgrade head.

  3. Start the app with cd app && ./start.sh on Unix or Mac, or cd app && start.bat on Windows.

  4. Open http://localhost:5173.

Expected outcome

The local FastAPI backend and Vite frontend start for the YouTube-transcript chat application.

Guide limitations

  • PostgreSQL with pgvector is required; the README says there is no SQLite fallback.
  • A fresh database starts without videos unless SEED_ENABLE=true is set for the mock video library.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Agent orchestration

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Dark Factory ExperimentExamine a workflow that routes GitHub issues through triage, implementation, validation, and merge.Cloud
Agentic AI Helpdesk PlatformClassify tickets by issue domain and category, and estimate urgency and complexity.Cloud, Docker, Web
TgoConfigure multiple AI agents for different customer-service scenarios and connect supported LLM providers.Docker, Self-hosted, ServerThe repository describes Tgo as open source and provides self-hosting instructions. Its README lists minimum server requirements of four CPU cores and 8 GiB of RAM; local development setup lists macOS, Linux, and WSL2.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
coleam00/dark-factory-experiment · Official homepage title · retained in its source language
How we review sourcesSuggest a correction