DivergentAI/dreamGPT
DivergentAI/dreamGPT has 596 GitHub stars and 39 forks. GitHot measured 0 stars in 24 hours and 0 in 7 days. Last checked 2026-11-09 13:39 UTC. Last push 2024-05-07.
Leverage hallucinations from Large Language Models (LLMs) for novelty-driven explorations.
Measured star growth
- in 24h
- 0
- in 7 days
- 0
- in 15 days
- Update delayed
- in 1 month
- Update delayed
Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.
README.md
OriginaldreamGPT: AI powered inspiration
dreamGPT, the first GPT-based solution that uses hallucinations from LLMs for divergent thinking to generate new innovative ideas. Hallucinations are often seen as a negative thing, but what if they could be used for our advantage? dreamGPT is here to show you how. The goal of dreamGPT is to explore as many possibilities as possible, as opposed to most other GPT-based solutions which are focused on solving specific problems.

This is how it works:

To use dreamGPT, you will need to have the following installed:
- Python 3.10+
- Poetry
Setup
- Clonse the dreamGPT repository from GitHub:
git clone https://github.com/DivergentAI/dreamGPT.git
- Rename
.env.exampleto.envand fill in the values.OPENAI_API_KEY: Your OpenAI API key.- Optional: If you wish to store the "dreams" in Pinecone, fill in the following values:
PINECONE_API_KEY: Your Pinecone API key.PINECONE_ENVIRONMENT: The name of the Pinecone environment.
Then, you can run the dreamGPT script to generate new ideas:
- Run
poetry installto install dependencies. - Run
poetry run startto start dreamGPT.- If you wish to provide a guiding theme, you can run
poetry run start --theme "climate change".
- If you wish to provide a guiding theme, you can run
Once you run it, dreamGPT generates a random seed of concepts and will use these as a starting point for its dreaming process. Here is a screenshot of the first iteration. Notice that the scores are not very high. As dreamGPT evolves the dreams, you will start to see higher scores with even better ideas.

Explore related projects
affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
300,295 starsNousResearch/hermes-agent
The agent that grows with you
262,115 starsmultica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
231,433 starsfirecrawl/firecrawl
Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥
200,178 stars