#32 · Primary category: Prompt Engineering Tools

tree-of-thoughts

artificial-intelligence chatgpt deep-learning gpt4 multimodal prompt prompt-engineering prompt-learning prompt-tuning

Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%

Project last updated:07/29/25

GitHub Stars

4.6K

Forks

376

Contributors

9

License

Apache-2.0

Why we included this project

Most language models stall when a single prompt isn't enough to think through a problem. This library implements Tree of Thoughts, a research technique that has the model generate several candidate reasoning paths, score them, and drop the weak ones before answering. It's a pip-installable Python package with ready-made agents, so you can swap in your own model or API endpoint without rebuilding the search logic. If your work involves math puzzles, logic problems, or multi-step planning, this is a practical way to get more deliberate reasoning out of a model, and the bundled prompting templates are useful even if you'd rather run the search yourself.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category