What it does
CodeGen is a set of AI models from Salesforce AI Research that generate computer code, a task called program synthesis. There are several generations and sizes, and later versions can fill in missing code in the middle of a file.
The models are available on Hugging Face for programmers to download. Salesforce says the release is for research only and asks users to check accuracy, safety and fairness before using it in real products.
Who it's for
Researchers and developers studying or experimenting with code-writing AI models.
Can I use it without coding?
Developers only. Using the models requires Python code. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- More on staying safe
Where people are talking about it
- CodeGen2: Lessons for Training LLMs on Programming and Natural LanguagesResearch paper · May 2023
- CodeGen: An Open Large Language Model for Code with Multi-Turn Program SynthesisResearch paper · Mar 2022