# Ten GitHub repos for building AI research agents with citations

> Original title: Building an AI research agent? Start with these 10 GitHub repos.

- Source: X search: AI startup funding (we raised, seed, Series A)
- Published: 2026-11-02T12:47:23.000Z
- Bad Influence: https://badinfluence.news/items/dmroqx2avh2x9blwaryho1rqx
- Original: https://x.com/RodmanAi/status/2117237131651461380

## Summary

The post lists ten GitHub repositories for building AI research agents, including OpenAlex, Open Deep Research, PaperQA, GROBID, and Haystack. The tools cover finding sources, reading research PDFs, extracting structured information, and generating evidence-backed answers. The author argues that a research agent's value lies in how well it finds evidence and checks sources, not just how well it writes.

## Post

Building an AI research agent? Start with these 10 GitHub repos.

They help AI find credible sources, read research papers, extract information, and generate answers backed by evidence.

1. OpenAlex – Explore scholarly research data.
https://github.com/ourresearch/openalex

2. Open Deep Research – Build agents that conduct multi-step research.
https://github.com/langchain-ai/open_deep_research

3. PaperQA – Get answers from scientific papers with citations.
https://github.com/Future-House/paper-qa

4. GROBID – Extract structured information from research PDFs.
https://github.com/kermitt2/grobid

5. Semantic Scholar API – Access paper metadata and citation data.
https://github.com/allenai/s2-folks

6. Open Research Knowledge Graph – Turn research findings into structured knowledge.
https://orkg.org

7. http://arxiv.py – Search and track research papers from arXiv.
https://github.com/lukasschwab/arxiv.py

8. Haystack – Build search, retrieval, and question-answering pipelines.
https://github.com/deepset-ai/haystack

8. LlamaIndex – Connect LLMs to documents and external data.
https://github.com/run-llama/llama_index

10. Oxylabs Web API MCP – Give research agents access to live web data.
https://github.com/oxylabs/web-api-mcp

The real value of a research agent isn't just how well it writes.

It's how well it finds evidence, checks sources, and supports its answers.

Bookmark this list for your next AI project.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWHv6W6acAAd7Tq.jpg&mode=thumb&exp=1793836800&sig=9d7cc03fd4ac85b8)