Thought Papers

  • Towards AGI Part 2: Multiverse of Actions

    Towards AGI: [Part 2] Multiverse of Actions

  • Towards AGI: [Part 1] Agents with Memory

  • Meet SuperAGI’s VEagle: An Open-source vision model that beats SoTA models like Bliva & Llava

  • Introducing AutoNode: Advancing RPA with a Multi-Expert AI System

  • Small Agentic Model

    Introducing SAM – A 7B Small Agentic Model that outperforms GPT-3.5 and Orca on reasoning benchmarks

  • Extending Context Window of a 7B LLM from 8k to 32k using PoSE (Positional Skip-wisE)

  • Building Agentic Application with SuperAGI Python Client Library

  • Hacktoberfest 2023 – A guide for contributing to SuperAGI

  • Introduction to RAGA – Retrieval Augmented Generation and Actions

  • Understanding Knowledge Embeddings in SuperAGI

  • Autonomous Agents Hackathon’23 Rewind

  • Introduction to Agent Summary – Improving Agent Output by Using LTS & STM

  • Building Autonomous Business Processes using AI Agent Workflows

  • Processing Structured & Unstructured Data with SuperAGI and LlamaIndex

  • Building your own tool in SuperAGI

    Building Your Own Custom Tool in SuperAGI: A Step-by-Step Guide

  • Understanding dedicated & shared tool memory in SuperAGI

  • Introducing AACP (Agent to Agent Communication Protocol)

  • Adding Custom Tool in SuperAGI

    Adding your own custom tool/toolkit to SuperAGI

  • SuperCoder: A SuperAGI Agent Template for Coding Projects

  • Agent Instructions: Autonomous AI Agent Trajectory Fine-Tuning