A curation of awesome tools, documents and projects about LLM Security.
Feast is an end-to-end open source feature store for machine learning. It allows teams to define, manage, discover, and serve features, delivering structured data to AI and LLM applications during training and inference. Documented use cases include real-time recommendations, fraud detection, risk scoring, and customer segmentation.
Vellum is a personal AI assistant available locally or in the cloud, with long-term memory across conversations. It can send emails, manage calendars, browse the web, create slides, write code, run research, and execute recurring background tasks. It offers fine-grained permissions requiring approval for high-stakes actions until marked trusted. Two plans exist: Base (free) and Pro packages Mighty, Super, and Ultra.
Gensim is a free open-source Python library for topic modelling and semantic NLP. It trains large-scale semantic models, represents text as semantic vectors and finds semantically related documents. The site describes streaming of arbitrarily large corpora, platform independence, and pretrained models and corpora published by the community.
The AI Safety Summit 2023 is a global event held on 1 and 2 November at Bletchley Park, Buckinghamshire. It brings together international governments, AI companies, civil society groups and researchers to consider AI risks, especially at the frontier of development, and discuss mitigation through internationally coordinated action.
A personal notes site with writings on topics the author is thinking about, learning, and working on. It includes an upcoming entry about building Atlas, described as an AI tool for thought, and an archive of earlier posts.
Stanford MLSys Seminar Series is a seminar series on the frontier of machine learning and systems. Its 2025 "Hidden Layer" series schedule lists talks, and earlier limited series covered systems for machine learning and foundation models. Stanford students could sign up for associated classes, and an email list provides speaker and livestream notifications.
Community notes
Be the first to share how this project worked for you.
Sign in with a verified account to leave a review or join the discussion.
Sign in to reviewKeep exploring
Feast is an end-to-end open source feature store for machine learning. It allows teams to define, manage, discover, and serve features, delivering structured data to AI and LLM applications during training and inference. Documented use cases include real-time recommendations, fraud detection, risk scoring, and customer segmentation.
Vellum is a personal AI assistant available locally or in the cloud, with long-term memory across conversations. It can send emails, manage calendars, browse the web, create slides, write code, run research, and execute recurring background tasks. It offers fine-grained permissions requiring approval for high-stakes actions until marked trusted. Two plans exist: Base (free) and Pro packages Mighty, Super, and Ultra.
Gensim is a free open-source Python library for topic modelling and semantic NLP. It trains large-scale semantic models, represents text as semantic vectors and finds semantically related documents. The site describes streaming of arbitrarily large corpora, platform independence, and pretrained models and corpora published by the community.
The AI Safety Summit 2023 is a global event held on 1 and 2 November at Bletchley Park, Buckinghamshire. It brings together international governments, AI companies, civil society groups and researchers to consider AI risks, especially at the frontier of development, and discuss mitigation through internationally coordinated action.
A personal notes site with writings on topics the author is thinking about, learning, and working on. It includes an upcoming entry about building Atlas, described as an AI tool for thought, and an archive of earlier posts.
Stanford MLSys Seminar Series is a seminar series on the frontier of machine learning and systems. Its 2025 "Hidden Layer" series schedule lists talks, and earlier limited series covered systems for machine learning and foundation models. Stanford students could sign up for associated classes, and an email list provides speaker and livestream notifications.
