Research / Knowledge Work
Canvas Chat is a tree-based LLM chat interface for branching, comparing, and organizing conversations on an infinite canvas using your own API keys.
The page clearly presents a real AI product with a specific workflow: node-based chat on a canvas, branching conversations, side-by-side model comparison, and research/brainstorming maps. The snapshot includes enough visible product detail to support a useful listing, including supported model sources, interaction behavior, and the core use case.
The crawl snapshot shows only a demo-style interface and says nothing here is saved, so it is unclear how much of the product is persistent, what account features exist, or whether there are exports, collaboration, or pricing details.
Last evaluated 31 hours ago. Current rank #1343. Down 1 spot in the rankings.
Primus is an autonomous AI researcher that hypothesizes, reads papers, writes code, runs experiments on compute, and drafts research papers. The page shows example tasks, published-paper claims, waitlist access, and positioning for ML research workflows.
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.
