# Haidra-Org/AI-Horde

A crowdsourced distributed cluster for AI art and text generation

Repository: https://github.com/Haidra-Org/AI-Horde
Canonical: https://ross.abutalabs.com/products/ai-horde
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: ai, distributed-computing, flask-api, gpt, opt, stable-diffusion, volunteer-computing
Last push: 2026-08-24T21:26:59+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 100
- inputs: {"age_days": 1450, "days_push": 9, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1536, forks 175 (observed 2026-08-28T04:04:59.989127+00:00)

## What it is
AI Horde is a crowdsourced distributed cluster where volunteers share GPU/CPU compute to generate AI images and text for others for free. This repository contains the Flask-based API server that coordinates requests, workers, and the kudos-based fairness system.

## Use cases
- generate ai art for free without a gpu
- run a volunteer worker to share my gpu for ai image generation
- generate text with community-provided llm compute
- build an app that uses a free crowdsourced ai generation api
- earn kudos by contributing compute to a community ai cluster

## When to choose
- you want free AI image or text generation without owning a GPU
- you want to donate idle GPU compute to a community service
- you're building a client app and need a free, community-run generation API
- you value equitable, non-commercial access to AI generation

## When to avoid
- you need guaranteed low-latency or SLA-backed inference
- you need full control over models, versions, or private infrastructure
- you require commercial licensing or paid support
- you need high-throughput batch generation with predictable throughput

## Facets
- artifact type: service
- maturity: active
- function: llm-inference, stable-diffusion, api-framework, http-server, agent-framework
- domain: artificial-intelligence, image-processing, large-language-models, microservices, self-hosted
- platform: python, self-hosted
- tags: crowdsourced-compute, volunteer-computing, kudos-economy, ai-art, text-generation, flask-api, web-server, docker

## Member repositories
- Haidra-Org/AI-Horde (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:59.989127+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:31:03.118285+00:00, confidence not recorded.
  - readme: https://github.com/Haidra-Org/AI-Horde (fetched 2026-08-28T04:04:59.989127+00:00, sha e7e072e17589)
- Data as of 2026-08-30T08:39:29.467469+00:00.