Distillate is a tool designed to automate and orchestrate machine learning research by turning research questions into autonomous agents that can conduct experiments and extract insights from scientific papers. It is aimed at users engaged in ML research who want to streamline the process of reading, experimenting, and synthesizing knowledge. The platform enables users to describe an experiment, after which an agent—referred to as Nicolas—sets up a git repository, drafts a prompt, and manages the experiment within a specified time budget.
Key features include spawning and steering research agents, tracking experiment progress, and analyzing results through side-by-side comparisons. Users can extract key findings from experiment histories and get an overview of all ongoing and completed experiments. The tool facilitates turning insights from research papers into new experiment ideas, supporting replication and adaptation of published techniques. Distillate also provides a library function to sync papers from Zotero, extract highlights, generate AI summaries, and manage notes from various reading devices, including reMarkable and iPad. Users can browse trending research from HuggingFace, receive personalized reading suggestions, and extract detailed insights from individual papers.
Distillate is available as both a command-line interface (CLI) and a desktop application for macOS and Windows. The CLI serves as the core, with the desktop app acting as a graphical interface. The platform integrates with tools such as Zotero, Obsidian, email, and reMarkable, allowing users to configure connectors individually. Experiment results and research insights are saved as rich lab notebooks in Obsidian, and users can export metric charts as PNG files for sharing or publication. Dashboards and email notifications keep users informed about experiment progress, reading habits, and suggested papers. The tool supports exporting the entire library state to JSON and provides automated backup to prevent data loss.
Distillate offers a free account with no credit card required and is open-source at its core. The workflow is designed to help researchers move quickly from reading to experimentation, with features that support both the management of research literature and the execution of autonomous ML experiments.
Distillate is an Other AI product. It focuses on automating and orchestrating machine learning research experiments and extracting insights from papers. Distillate is an open-source project aimed at machine learning researchers. The project is open source (MIT). It runs on the web, the command line, macOS, and Windows.
Distillate first shipped in 2026. The project is developed in the open on GitHub with 72 stars and 2 commits in the last 90 days. Among its 5 catalogued features are auto-experiment orchestration, research agent spawning, and paper insights extraction. Distillate is currently in beta.
Latest indexed changes and source events
Other apps tracked under the same category.
