Multi-Agent AutoResearch with Open Source Models

Hugging Face · Beginner ·🤖 AI Agents & Automation ·2mo ago

Skills: Multi-Agent Systems90%Tool Use & Function Calling70%

Key Takeaways

Sets up a multi-agent AutoResearch environment using open source models and OpenCode

Original Description

In this video, we walk through a multi-agent setup of AutoResearch using open source models and OpenCode. Timestamps 00:00 - Introduction: Multi-agent AutoResearch setup 01:07 - Agent Roles: Researcher, Planner, Worker, and Reporter agents 01:55 - Repository Setup: Exploring the repo structure and files 02:11 - Environment Configuration: Python setup, UVSync, HF Hub login 03:20 - OpenCode Interface: UI walkthrough and agent configuration 03:51 - Running the Experiment: Autonomous research pass execution 05:17 - Sub-agents in Action: Planner and Reviewer agent collaboration 07:08 - Trackio Metrics: Tracking training efficiency and job monitoring 08:23 - Hugging Face Hub: Jobs running on HF infrastructure 08:58 - Conclusion: Try it yourself with OpenCode Links: Repo: https://github.com/burtenshaw/multiautoresearch Twitter post with learnings: https://x.com/ben_burtenshaw/status/2045085809800356112

Watch on YouTube ↗ (saves to browser)

Sign in to unlock AI tutor explanation · ⚡30

More on: Multi-Agent Systems

View skill →

Command: a new tool for building multi-agent architectures in LangGraph

Command: a new tool for building multi-agent architectures in LangGraph

Hierarchical multi-agent systems with LangGraph

Hierarchical multi-agent systems with LangGraph

Building an multi-agent concierge system using LlamaIndex Workflows

Building an multi-agent concierge system using LlamaIndex Workflows

Practical Multi AI Agents and Advanced Use Cases with crewAI

Practical Multi AI Agents and Advanced Use Cases with crewAI

AutoGen: Multi-Agent AI Conversation, complete code

AutoGen: Multi-Agent AI Conversation, complete code

Workshop: Build Multi-Agent Workflows with Low-Code Interfaces - AI PM Community Session #61

Workshop: Build Multi-Agent Workflows with Low-Code Interfaces - AI PM Community Session #61

Product Management Exercises

Related Reads

How We Built a GDPR-Compliant AI Receptionist for Small Businesses

Learn how to build a GDPR-compliant AI receptionist for small businesses, overcoming challenges in compliance and latency

Arquitectura de una recepcionista IA para restaurantes en Mendoza: intake, urgencia y handoff

Learn to design an AI receptionist architecture for restaurants that captures intention, urgency, and context without overpromising

How Float Runs an AI Energy Company on a 3-Person Team with Tiger Data

Learn how Float uses Tiger Data to run an AI energy company with a 3-person team, achieving 99.3% data compression and efficient scaling

OKF vs. Harness Engineering: Two Answers to the Same Question

Learn how OKF and Harness Engineering can improve AI agent reliability

Chapters (10)

Introduction: Multi-agent AutoResearch setup

1:07 Agent Roles: Researcher, Planner, Worker, and Reporter agents

1:55 Repository Setup: Exploring the repo structure and files

2:11 Environment Configuration: Python setup, UVSync, HF Hub login

3:20 OpenCode Interface: UI walkthrough and agent configuration

3:51 Running the Experiment: Autonomous research pass execution

5:17 Sub-agents in Action: Planner and Reviewer agent collaboration

7:08 Trackio Metrics: Tracking training efficiency and job monitoring

8:23 Hugging Face Hub: Jobs running on HF infrastructure

8:58 Conclusion: Try it yourself with OpenCode

Langchain vs Langgraph #ai #langchain #langgraph