microsoft/ResearchStudio

ResearchStudio: Our AI co-author, from research problem to final publication.

View on GitHub ↗Jump to charts ↓

Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 3 minutes ago
Added to GitGenius on October 4th, 2026
Created on April 27th, 2026
Open Issues & Pull Requests: 5 (+0)
GitHub issues: Enabled
Number of forks: 172
Total Stargazers: 3,036 (+0)
Total Subscribers: 17 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 11.2 hours
Mean response time: 3.1 days
90th percentile: 16.1 days
Tracked items: 7

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 1
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 30 days
Stale 30+ days: 0
Stale 90+ days: 0

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

No label distribution available yet.

Most active issues this week

Sign in to see which issues are moving.
Sign in

Detailed Description

ResearchStudio is a collection of AI-powered skills that assist researchers across the entire research lifecycle, from initial problem formulation through final publication.

The tool addresses the fragmented nature of research work by automating the generation of research artifacts at two critical junctures. For early-stage research, ResearchStudio-Idea transforms an under-specified research direction into a reviewer-defensible idea card by grounding suggestions in an empirical taxonomy derived from a large-scale corpus of conference submissions. For completed research, ResearchStudio-Reel converts a finished paper PDF into multiple publication-ready deliverables: an editable poster, a narrated video walkthrough, a bilingual blog post, and an interactive reel viewer. The skills run on Claude Code and Codex, leveraging large language models to reason about research intent and generate structured outputs.

Researchers working on papers destined for publication should consider this tool if they want to reduce the manual effort of creating supplementary materials and promotional content. The project is particularly suited to those submitting to major conferences, as the idea-generation component explicitly grounds its suggestions in patterns from ICLR, ICML, and NeurIPS submissions. The tool maintains editability throughout—outputs like PowerPoint slides and idea cards can be refined after generation rather than being locked into their initial form.

Development shows sustained, deliberate progress across multiple components. The project has released distinct modules addressing different research phases, with recent work expanding the video generation capability into a standalone open-source tool usable both as a skill and independently via CLI. Feature development demonstrates responsiveness to user workflows, such as persisting user queries through all reasoning phases and resolving paper references without explicit links. The codebase is organized into separate, documented subsystems with accompanying research papers and interactive demos for each major component.