sourced-intel
One question in, one sourced, verifiable HTML report out
A new way for AI to search for data
1GitHub stars
What XERJ indexed
Selected work
“harden the API and make installs reproducible”. 6 files, 248 lines in tests, src/sourced_intel, the project root.
Licence
The repository
MIT
Checked by a person at the pinned commit.
The XERJ corpus
MIT, with credit
The author agreed by email on 2026-10-21. 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
deep-researchlanggraphllm-agentsosintpythonrag
Example questions
- How does sourced-intel implement deep-research?
- Where does sourced-intel handle “harden the API and make installs reproducible”?
- What does src/sourced_intel do in sourced-intel?
The prompt
Paste it into your AI agent. It clones banzaicolo/sourced-intel at the pinned commit and indexes it on your machine.
Search the GitHub repository banzaicolo/sourced-intel with XERJ (https://hub.xerj.org/corpus/banzaicolo--sourced-intel). 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/banzaicolo/sourced-intel sourced-intel && git -C sourced-intel checkout e20ae5e841cacf0fd3be9fc6dd27d2d892b38a3c 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./sourced-intel --url http://127.0.0.1:9200 --prefix sourced-intel --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
BuckarooAI, prompts and agents corporacognitaadalflowhaystackShauryaaSharma/lore-backendSheikhSarvar/pyrag-corepipeshub-ai/pipeshub-ai
Selected work and consent: the XERJ registry.