Research

Open Science is an open-source AI workbench for scientists. It combines literature, code, figures, reports, and review into a local-first desktop workflow with model choice, reproducible artifacts, and scientific agent skills.

Open-source research skill that helps Claude, Codex, and OpenClaw run a more disciplined AI research workflow, from hypothesis and literature review through baselines, leakage checks, analysis, and paper writing.

A simple AI tool that renames up to 10 screenshots in one batch, generating searchable filenames from image content without requiring sign-up.

A research project and proxy for Claude Code that chooses per-step reasoning effort with Jev while preserving the prompt cache. The repo includes benchmark results, a real-session measurement, and notes on how the mechanism works.

A Claude Code skill that delegates coding, review, analysis, and research tasks to Google Antigravity CLI sub-agents so Claude can keep working while background jobs run.

arXiv paper describing QUEST, an open family of deep research agents from 2B to 35B parameters, plus a synthetic-task training recipe and released models, data, and scripts.

A daily AI intelligence journal for builders, covering notable model, tooling, and release updates in a short sourced digest.

Physics AI is a physics homework and study tool that solves problems from photos or typed prompts, with step-by-step explanations, tutor mode, and visual breakdowns for diagrams and vectors.

A research report on the current MCP ecosystem, with live crawl numbers, verification rates, category breakdowns, and examples of both strong and weak MCP-positive sites.

Anthropic research post showing Claude applied to attack surface analysis and reduction across 25 open-source codebases, with concrete findings and security-focused methods.

CTGT’s research post shows how deterministic LLM serving can still produce inconsistent pipeline outcomes, and introduces Concordance, an Apache 2.0 instrument for tracing where AI workflows diverge. The page includes the problem setup, benchmark details, findings, limitations, and a linked repo for reproduction.

arXiv paper on Javo, a sales agent trained on commercial conversations and evaluated through public benchmarks plus a randomized field trial across 100 live websites.

A reproducible GitHub research repo comparing Codex reasoning-token usage between API and ChatGPT Pro access across 960 completed responses, with code, data, and verification steps included.

A long-form research article on why browser-based AI agents fail on real websites and how accessibility engineering and task-level tests can reveal the breakpoints.

Research code for improving agent harnesses through regularized recursive self-improvement, with evaluation, selection, pruning, and domain-specific adapters.

A research repo that replays real Claude Code and Mooncake traces to test prefix-cache eviction policies and compare them against LRU.

A research post from Prime Intellect comparing 153 autonomous runs across 18 frontier models on a nanoGPT optimizer speedrun. It presents the setup, harness, results, and discussion around autonomous AI research performance.

Chrome extension that tracks major AI companies, pulls in AI news and research, and generates daily summaries with Gemini, including language-aware summaries and article deep dives.

AI-native workspace for writers, bloggers, and lifelong learners. It combines source collection, an idea map, AI-assisted exploration, and a focused writing editor designed to support long-form thinking.

AI-powered trade signal product for retail traders that turns financial news into ranked trade plans with entries, stops, targets, and tracked accuracy.

Anthropic research post analyzing Claude Mythos 5’s behavior in a UK AISI cybertesting evaluation, including overreach, deception, and follow-up analysis of newer models.

A dated research report from Vouch that analyzes the MCP registry at scale, including corpus growth, transport split, credential classes, schema quality, and unreachable servers. It also points to queryable live data and the methodology behind the counts.

A research page comparing 153 autonomous runs across 18 frontier models on the nanoGPT optimizer speedrun, with rankings, trajectories, token/compute stats, and equal-budget comparisons.

A sourced model and short report exploring whether Europe could train a sovereign frontier AI model using public compute it already owns, with reproducible code, datasets, and a PDF report.