agent-challenge  by nosana-ci

Build and deploy personal AI agents on decentralized compute

Created 9 months ago
260 stars

Top 97.5% on SourcePulse

GitHubView on GitHub
Project Summary

Summary

This repository provides a framework and challenge for building personal AI agents using ElizaOS, deployable on the Nosana decentralized GPU network. It targets developers and enthusiasts aiming to create self-hosted AI solutions, offering a $3,000 USDC prize pool and the opportunity to leverage decentralized compute infrastructure. The benefit lies in empowering individuals with AI control and fostering innovation in personal agent development.

How It Works

Agents are constructed using the ElizaOS framework, leveraging its plugin ecosystem for extended functionality. Core LLM capabilities are provided by a hosted Qwen3.5-27B model endpoint, with embeddings handled by Qwen3-Embedding-0.6B, both managed by Nosana. The unique aspect is deployment on Nosana's decentralized compute network, which distributes workloads across a network of GPU providers, offering a cost-effective and permissionless alternative to traditional cloud services. Developers containerize their ElizaOS agents using Docker for deployment.

Quick Start & Requirements

  • Primary Install/Run: bun i -g @elizaos/cli, elizaos dev for local development.
  • Prerequisites: Node.js 23+, pnpm, Docker, Git.
  • Dependencies: ElizaOS CLI, specific plugins (e.g., @elizaos/plugin-openai).
  • Setup: Requires forking the repo, configuring .env with Nosana endpoint details, and containerizing the agent.
  • Links:
    • Challenge Submission: superteam.fun/earn/listing/nosana-builders-elizaos-challenge/
    • Builders Credits: nosana.com/builders-credits
    • Nosana API Key: deploy.nosana.com/account/

Highlighted Details

  • Prize Pool: $3,000 USDC distributed among top participants.
  • Decentralized Compute: Agents run on Nosana's distributed network, promoting data sovereignty and cost efficiency.
  • Model Integration: Leverages Nosana-hosted Qwen3.5-27B LLM and Qwen3-Embedding-0.6B models.
  • Deep Integration Focus: Challenge rewards projects demonstrating thorough integration with Nosana's decentralized infrastructure beyond basic deployment.

Maintenance & Community

  • Community Support: Nosana Discord, ElizaOS Discord.
  • Updates: Follow @nosana_ai and @elizaos on Twitter/X.
  • Issue Tracking: GitHub issues for the agent-challenge repository.

Licensing & Compatibility

  • License: MIT License.
  • Compatibility: Permissive for commercial use and integration into closed-source projects.

Limitations & Caveats

  • Challenge Deadline: The challenge has a specific submission deadline of April 14, 2026.
  • Deployment Complexity: Requires familiarity with Docker, Docker Hub, and Nosana's deployment mechanisms (Dashboard or CLI).
  • Credit Airdrops: Compute credits are airdropped twice daily, necessitating patience for initial allocation.
Health Check
Last Commit

3 days ago

Responsiveness

Inactive

Pull Requests (30d)
7
Issues (30d)
0
Star History
126 stars in the last 30 days

Explore Similar Projects

Starred by Elie Bursztein Elie Bursztein(Cybersecurity Lead at Google DeepMind), Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and
7 more.

SuperAGI by TransformerOptimus

0.1%
17k
Open-source framework for autonomous AI agent development
Created 2 years ago
Updated 1 year ago
Feedback? Help us improve.