Build an AI agent on Livepeer

Build an AI agent using the Eliza framework with Livepeer as the model provider for decentralised GPU inference. Complete tutorial with working code.

---

This tutorial is adapted from the Livepeer Agent SPE guide on Mirror.xyz, published as part of the Agent SPE incentive programme. The original tutorial was written by the Agent SPE team and made available under an open licence.

Eliza is an open-source multi-agent framework (ai16z) that supports pluggable model providers. The Livepeer plugin routes Eliza’s LLM inference requests to the Livepeer AI gateway, where they run on decentralised GPU infrastructure instead of centralised cloud providers.

What you will build: An Eliza agent that uses Livepeer as its LLM backend, running meta-llama/Meta-Llama-3.1-8B-Instruct (or any Ollama-compatible model) on the network.

Prerequisites

• Node.js 22 or later
• pnpm (npm install -g pnpm)
• For development: no API key required (the community gateway at dream-gateway.livepeer.cloud is unauthenticated)
• For production: an API key from a gateway provider

Build your agent

Extending the agent

Switch the model. Change settings.model in your character file to any Ollama-compatible model available on the Livepeer network. See model support for supported variants and warm availability.

Add memory and knowledge. Eliza supports RAG (retrieval-augmented generation) via knowledge files and vector stores. Add entries to the knowledge array in your character file to give the agent domain-specific context.

Integrate with Slack or Discord. The Eliza framework includes client connectors for Slack, Discord, and Twitter. Add "slack" or "discord" to the clients array and configure the respective credentials in .env.

Build a multi-agent swarm. The SwarmZero framework integrates with Livepeer’s inference APIs and supports multi-agent orchestration. See the SwarmZero Livepeer example for a working YouTube video generator swarm.

Supported LLM models

The Livepeer LLM pipeline uses an Ollama-based runner. Any Ollama-compatible model works. Warm models respond immediately; cold models load on the first request (30 seconds to 5 minutes).

Model	Warm on network	VRAM required
meta-llama/Meta-Llama-3.1-8B-Instruct	Yes	8 GB
mistralai/Mistral-7B-Instruct-v0.3	Check network	8 GB
google/gemma-2-9b-it	Check network	10 GB
Qwen/Qwen2.5-7B-Instruct	Check network	8 GB

AI agent prompt

Complete the "Build an AI agent on Livepeer" tutorial as a runnable ElizaOS agent. First verify the current ElizaOS install path from https://github.com/elizaOS/eliza and npm package metadata because the active framework may use bun or the elizaos CLI instead of the older pnpm monorepo flow. Create an agent named LivepeerAgent that routes LLM calls to LIVEPEER_GATEWAY_URL=https://dream-gateway.livepeer.cloud for development, with optional LIVEPEER_API_KEY=<gateway provider bearer token> for production. Add a character file using modelProvider "livepeer" and model "meta-llama/Meta-Llama-3.1-8B-Instruct", run the agent locally, and test it with a curl message asking for a one-sentence Livepeer explanation. Do not require a Livepeer Studio API key.

The Eliza Livepeer plugin tutorial covers the plugin architecture in more depth, including custom inference routing and multi-pipeline configuration.