Research

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.

OpenScience is an open-source AI workbench for scientific research. It can read papers, plan hypotheses, write and run code, manage experiments, query scientific databases, and present results in a browser-based workspace.

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.

A research article benchmarking bot detection systems against scripted browsers, stealth browsers, and modern AI browsing agents, with comparative results across five detection products.

Doubt is an open-source, zero-dependency CLI and Agent Skill for turning contested questions into source-grounded evidence maps with supports, contradictions, unknowns, and portable HTML output.

Slashspace is a local-first infinite canvas for AI chat and agentic work, designed for research, writing, development, and long-form thinking. It supports multiple models, MCP connections, local storage, and desktop apps for Mac, Windows, and Linux.

An open benchmark and leaderboard for AI CAD agents, with 308 prompts across 20 categories and layered scoring for geometry, engineering, manufacturability, and cognition.

AI forecasting platform with a public track record, API/docs, and integrations for Claude Desktop and Claude Code. The page highlights benchmark results, live market usage, and example forecast types for probability, numeric, date, categorical, and decision questions.

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.

A data-backed study showing which major websites block specific AI crawlers in robots.txt, with breakdowns by crawler, site type, and a downloadable CSV.

A GitHub repository documenting how Claude re-derived a published one-loop quantum gravity calculation, with step-by-step derivations, reproducible checks, and reported corrections to the paper.

Revline is an AI web app for researching TikTok and Instagram posts, breaking down viral hooks and formats, and finding creators that fit a brand. It includes searchable public-post research, evidence-backed matches, creator checks, and AI-assisted next-step ideas for brands and creators.

A native bibliography manager for Omarchy that combines paper reading, note capture, and agent workflows with built-in MCP support.

An infinite canvas that turns LLM conversations, readings, and notes into an editable thought graph. It supports human-in-the-loop workflows, cited passages, replayable dependencies, and local-first backups.

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.

A deterministic Python project for empirical law discovery in elementary cellular automata, with simulation, discovery, reproducibility guides, and published preprints.

Mostly Right is an AI-agent-powered platform for finding, building, and maintaining datasets for real-world prediction models. The page shows both a dataset browsing flow and a custom dataset builder, with agents handling source discovery, cleaning, joining, and ongoing updates.

A research site for LittleLearner, a language model trained only on K–5 curriculum data to study how bounded pretraining affects capability, scaling, post-training, and in-context learning. The page includes a live chat demo, model scales, controls, and experiment summaries.

Bootable Rust no_std kernel built as an inference substrate for LLMs, with tensor-native memory allocation, layer-boundary scheduling, and streaming-focused runtime primitives.

A research project exploring multi-agent LLM coordination in Pokémon Showdown. It compares talk modes, reports win rates and token costs, and frames the environment as a benchmark for studying collaboration between agents.

Panel is an early-stage research workspace where an agent works alongside the user in panes for chat, files, PDFs, notebooks, and custom viewers. The repo includes setup instructions, runtime requirements, supported features, and current limitations.

Valovest is an AI stock sentiment analysis tool that synthesizes analyst reports, earnings calls, news, and social sentiment into a short investment brief. The page shows timeframe filters, stock examples, a weekly featured stock, and outputs like overall sentiment, bull vs. bear arguments, and key themes.

A research project and interactive visualization on how agent-generated code behaves after merge in real-world open source repositories, with a paper, replication package, and data-driven findings.

Clusy is an agent-native notebook platform for ML and data science that lets users describe a goal in plain language and have the system source data, set up experiments, run notebook cells, and return editable results in the cloud.