Agents4Academia

AI agents are changing what individuals can build: a recurring frustration or a highly specific workflow can become a working tool in a fraction of the time it used to take. Across academia, people are already experimenting — literature discovery, knowledge organisation, reproducibility, review, teaching, administration — but mostly in isolation, with lessons rarely shared. Agents4Academia brings these efforts together: sharing practical experience, identifying common needs, and developing open, reusable tools shaped by researchers themselves.

Our goals are simple:

1. Learn together where agents add real value, where their limitations lie, and how best practices should evolve as the technology improves.
2. Build together open and reusable tools for shared academic needs, adapting them over time to new capabilities and ways of working.

We welcome researchers and collaborators from all institutions and disciplines to contribute to this shared effort. Our principles guide the work.

Our first cohort (Oxford–Singapore Hackathon, June 2026)

Our first cohort launched with a two-week hackathon (14–26 June 2026), running in parallel across Oxford Statistics, NUS, and NTU with generous support from Anthropic. We deliberately didn't pre-assign projects: participants identified concrete bottlenecks in their own scientific workflows and self-organised into small teams around them, so the work reflects researchers' real, felt needs rather than an imposed agenda.

The hackathon shipped five open-source agents spanning the research lifecycle:

1. Discover Prior auditable knowledge graphs from primary literature
2. Organise UReKA Zotero, Notion, Obsidian & arXiv, unified
3. Reproduce Benchmark-Replicator clean, runnable implementations of prior papers
4. Verify RefWarden do citations exist, and do they support the claim?
5. Review Auto-Reviewer claim–evidence maps, novelty and rigor checks

While building side by side, the teams repeatedly encountered the same infrastructure needs. We therefore extracted them into academia-core: shared components for full-text ingestion, citation resolution, and evidence-grounded judging that other research agents can build on.

Get involved

• Try the tools. Each repository includes setup instructions and examples.
• Contribute. Pull requests, evaluations, integrations, and tests on new domains are welcome.
• Build on the shared infrastructure. Use academia-core for your own research agents.
• Organise a chapter. Run an Agents4Academia hackathon at your institution.
• Join the next cohort. We are planning the next hackathon.
• Join the conversation. Find us on Discord, X, and Bluesky.