MLE-Agent is an open-source project on GitHub with about 1,574 stars, most recently updated in 2026. MLE-Agent is an intelligent companion for machine learning engineering and research, built by the MLSysOps team. It integrates with arXiv and Papers with Code to ground its suggestions, uses code retrieval-augmented generation over your repository, and supports models from OpenAI, Anthropic, Gemini and local Ollama deployments.
Published on GitHub under the MIT license, MLE-Agent has attracted a community of about 1,574 stars, which places it among the more visible open-source AI projects in its niche. Development was still active as of 2026, based on the repository’s latest updates. Because the full source code is public, teams can audit how it works, adapt it to their own stack, and self-host it rather than depending on a closed hosted product.
The repository is tagged with topics including agent, ai, llm, ml, mle, which gives a quick picture of where it fits in the open-source AI ecosystem. New users can explore the examples and documentation in the repository to understand the main workflows before integrating it into their own projects, and the public issue tracker shows what the maintainers are actively working on and what the community is asking for.
MLE-Agent is MIT-licensed open source and free to use; you only cover the cost of any model APIs you connect.
MLE-Agent is best suited for ML engineers and researchers who want an assistant that understands both the literature and their codebase. Anyone evaluating it should start with the GitHub repository, where the documentation, examples and issue tracker show exactly what the current version can do.