#43 · Primary category: Prompt Engineering Tools

graph-of-thoughts

graph-of-thoughts graph-structures graphs large-language-models llm prompt-engineering prompting

Official Implementation of "Graph of Thoughts: Solving Elaborate Problems with Large Language Models"

Project last updated:03/24/26

GitHub Stars

2.8K

Forks

217

Contributors

4

License

Other

Why we included this project

When a single prompt or a straight chain of reasoning keeps falling short on a problem, this framework gives you another way in. You describe the task as a graph of operations, with the LLM doing the actual work, which lets you branch, backtrack, and combine partial solutions instead of committing to one linear path. It ships with working examples like sorting and set operations, and you can express classic approaches such as chain-of-thought or tree-of-thought as graph structures, which makes it handy for comparing prompting strategies on the same problem. Teams prototyping multi-step reasoning get something more structured than hand-rolled prompt chains, and researchers benchmarking prompt methods get a clean, extensible harness. It is a research codebase though, so plan to configure your own LLM access and adapt the operations to your task; it is not a turnkey tool.

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