Research / Knowledge Work
Clusy is an agent-native notebook platform for ML and data science work in the cloud. The page says it can source data, inspect it, choose architecture and compute, and run end-to-end workflows, with a demo showing a finetuning task and follow-up work queued while the notebook runs.
The page clearly presents a real AI-adjacent product for researchers and data teams, with enough visible copy to understand the workflow, target users, and cloud notebook use case. It describes agent-driven execution for ML/data science tasks and includes product navigation plus a demo/case-study section, which is enough for a public listing.
The crawl snapshot does not show a working demo, detailed feature list, pricing details, supported data/model integrations, or enough documentation to judge how broad the notebook and evaluation features are in practice.
Last evaluated 16 days ago. Current rank #1043. Holding steady in the rankings.
An interactive dashboard that analyzes New York Times coverage since 2000 using the NYT Archive API, with views for reporters, beats, sections, subjects, geography, obituaries, and corrections.
An open benchmark and leaderboard for AI CAD agents, with 308 prompts across 20 categories and layered scoring for geometry, engineering, manufacturability, and cognition.
A research article from Applied Compute on how agentic, tool-using workloads differ from traditional LLM benchmarks, with production observations, workload profiles, and an open-source harness for replaying traces.
UnderstandDocs is a document analysis tool that summarizes pasted text or uploaded files, flags risks, extracts important dates, and simplifies dense language. The page shows a working analysis form, supported file types, a privacy/no-storage claim, and an example output for a tenancy agreement.
