starlight
General-purpose agent platform for intent-driven missions, verified outcomes, and interoperable agents
A new way for AI to search for data
2GitHub stars
What XERJ indexed
Selected work
“Add bounded HTTP JSON agents, service health demo and mission preflight”. 10 files, 452 lines in test, src/platform, examples.
Licence
The repository
MIT
Checked by a person at the pinned commit.
The XERJ corpus
MIT, with credit
The author agreed by email on 2026-10-14. 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
Example questions
- What does src/platform do in starlight?
- What changed in starlight for “Add bounded HTTP JSON agents, service health demo”?
The prompt
Paste it into your AI agent. It clones starlight-protocol/starlight at the pinned commit and indexes it on your machine.
Search the GitHub repository starlight-protocol/starlight with XERJ (https://hub.xerj.org/corpus/starlight-protocol--starlight). 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/starlight-protocol/starlight starlight && git -C starlight checkout edcab0c360859cc21328484ffb99bf03b3c49eb7 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./starlight --url http://127.0.0.1:9200 --prefix starlight --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
DhirajAI, prompts and agents corpora
Selected work and consent: the XERJ registry.