blume
The open-source docs framework for humans and agents
A new way for AI to search for data
1,804GitHub stars
What XERJ indexed
Selected work
“don't reprint startup diagnostics after a port bump”. 4 files, 241 lines in packages/blume.
Licence
The repository
MIT
Checked by a person at the pinned commit.
The XERJ corpus
MIT, with credit
The author agreed by email on 2026-10-24. 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
docsmdxtypescript
Example questions
- How does blume implement docs?
- Where does blume handle “don't reprint startup diagnostics after a port bump”?
- What does packages/blume do in blume?
The prompt
Paste it into your AI agent. It clones haydenbleasel/blume at the pinned commit and indexes it on your machine.
Search the GitHub repository haydenbleasel/blume with XERJ (https://hub.xerj.org/corpus/haydenbleasel--blume). 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/haydenbleasel/blume blume && git -C blume checkout a7678cdb42d84785e84a118bb475eb21883e5480 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./blume --url http://127.0.0.1:9200 --prefix blume --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
CyberSproutWriting and copy corporaatoma-run--atomain-solidarity-botlexbuildToniChowBea/chowbea-axiosqiyuhuating/quorum-labnestjs/nest
Selected work and consent: the XERJ registry.