hkuds/ai-researcher

[NeurIPS2025] "AI-Researcher: Autonomous Scientific Innovation" -- A production-ready version: https://novix.science/chat

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 19 minutes ago
Added to GitGenius on September 11th, 2026
Created on March 11th, 2025
Open Issues & Pull Requests: 65 (+0)
GitHub issues: Enabled
Number of forks: 723
Total Stargazers: 5,732 (-1)
Total Subscribers: 41 (+0)

Repository Insights (GitGenius)

Most active contributors

Sign in to see contributor activity.

Related repositories by overlapping contributors

No overlapping-contributor repos identified yet.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 58
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 421 days
Stale 30+ days: 58
Stale 90+ days: 56

Recent activity

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

Top labels

  • bug (4)
  • enhancement (3)
  • documentation (2)

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

AI-Researcher is an autonomous scientific discovery system that automates end-to-end research workflows from concept through publication using AI agents.

The tool addresses the challenge of accelerating scientific innovation by automating traditionally manual research processes. It accepts research direction at two levels: users can provide detailed descriptions of specific research ideas for the system to implement, or they can submit reference papers and request the system to generate novel research concepts based on those references. The system then orchestrates the full pipeline, handling strategy development, implementation, and publication preparation autonomously.

Researchers working on novel problems where they want AI assistance in exploring ideas and executing research workflows would benefit from this tool. It suits projects where users either have a clear research direction they want to automate or possess reference materials from which they want to derive and implement new research directions. The tool is positioned as production-ready with a hosted version available alongside the open-source implementation.

Almost all open issues are raised by outside users rather than the core team, indicating a substantial base of adopters reporting real-world use. Maintainers typically respond to new issues and pull requests within a few days. Work in the issue tracker is dominated by bug reports, enhancement requests, and documentation improvements.