OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Multi-Agent Systems

Gladiator

Gladiator is a Python project that coordinates two zero-human AI companies competing on the same product through Hermes Agent workers and Paperclip orchestration, with a dashboard for showing progress, evidence and results.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Gladiator — OpenViST project profile in Multi-Agent Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it for a controlled multi-agent competition where distinct teams pursue the same product objective and their strategies can be compared.

Who it is for

  • Developers experimenting with autonomous multi-agent organizations
  • Builders comparing agent strategies against a shared product objective
  • Hackathon teams prototyping orchestrated AI competitions

Documented uses

  • Run separate autonomous agent teams against identical starter repositories
  • Compare growth-first and quality-first strategies within one competition
  • Visualize agent tasks, code comparisons, progress and audit evidence
  • Prototype skill transfer and team-merging experiments
Before you choose

Requirements & limits

The repository is public and MIT-licensed. The documented setup requires local infrastructure, an Anthropic API key and a listed estimated cost of about $5–6 per ten-minute competition run using nine Sonnet agents.

  • It combines Hermes Agent workers with Paperclip orchestration rather than presenting a standalone agent.
  • The example competition uses two named strategies: growth-first and quality-first.
  • The documented stack spans Python, Node.js, PostgreSQL, FastAPI, server-sent events and SQLite.
  • The repository notes adapter registration and possible patches for hermes-paperclip-adapter version 0.1.1.
  • Changing the shared product objective is Likely compatible, but the relevant configuration or implementation points are not shown.

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 Gladiator’s Hermes Agent and Paperclip environment

Prepare the documented agent, orchestration and dashboard dependencies for Gladiator.

Before you start

  • Python 3.11 or newer
  • Node.js 20 or newer
  • pnpm 9 or newer
  • PostgreSQL 16 or newer
  • An Anthropic API key with Claude Sonnet or Haiku access

Steps

  1. Install Hermes Agent with the official installer, configure the Anthropic provider in the Hermes environment file, and run the documented Hermes chat check.

  2. Clone Paperclip, install its dependencies with pnpm, and create the documented PostgreSQL user and database.

  3. Register the Hermes Paperclip adapter where required, including the documented adapter package and registry changes; the setup notes also describe two patches for adapter version 0.1.1.

  4. Clone Gladiator, create the Python virtual environment under base-product, install the listed FastAPI, Uvicorn, HTTPX, Rich and SSE Starlette packages, and add the Anthropic key to .env.

Expected outcome

The documented Hermes Agent, Paperclip, database and Gladiator dashboard components are configured for the next integration stage.

Guide limitations

  • The available setup material does not document the complete company-and-agent creation procedure or establish that a competition has run successfully.
  • The adapter patches may depend on the Paperclip and hermes-paperclip-adapter versions in use.
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
GladiatorRun separate autonomous agent teams against identical starter repositoriesCloud, Self-hosted, ServerThe repository is public and MIT-licensed. The documented setup requires local infrastructure, an Anthropic API key and a listed estimated cost of about $5–6 per ten-minute competition run using nine Sonnet agents.
Insurance Agentic AIRoute insurance questions to a life, home or auto specialist.Docker, Self-hosted, Web
AI ChatkitCreate and orchestrate agents with custom behavior logic.Linux, Self-hosted, Server, WebThe repository is public and identified as open source. Its README documents a local development setup with Python and Node-based frontend tooling.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
4 October 2026
Original website title
runtimenoteslabs/gladiator · Official homepage title · retained in its source language
How we review sourcesSuggest a correction