DeepResearch_AI

Open-source research assistant and MCP audit toolkit for systematic reviews: cited research reports, PRISMA tracking, evidence and claim…

A new way for AI to search for data
View on GitHub
91GitHub stars

Python

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 74d345b216 (2026-10-02).

Selected work

Aryan Pardeshi
@Aryan-Pardeshi

“stop labelling resolved claims "verified"”. 9 files, 230 lines in tests, backend.

Licence

The repository

MIT

Checked by a person at the pinned commit.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-20. Same terms as the repository. Answers name the repo, the commit and the file:line.

in licence reviewnot in the hub yetsuggested use: adapt with attribution

academic-researchai-agentsdockerfastapihuman-in-the-loopjavascriptlanggraphllm

Example questions

The prompt

Paste it into your AI agent. It clones Aryan-Pardeshi/DeepResearch_AI at the pinned commit and indexes it on your machine.

Search the GitHub repository Aryan-Pardeshi/DeepResearch_AI with XERJ (https://hub.xerj.org/corpus/aryan-pardeshi--citeproof-ai-mcp).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/Aryan-Pardeshi/DeepResearch_AI DeepResearch_AI && git -C DeepResearch_AI checkout 74d345b216971e6ea0419e6a0f37c54cc5fad9e2
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./DeepResearch_AI --url http://127.0.0.1:9200 --prefix deepresearch-ai --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

Related

Selected work and consent: the XERJ registry.