holt
Find open source projects that will actually merge your first PR
What XERJ indexed
Snapshot
The whole repository at commit 94155de260 (2026-10-21). main is 2 commits ahead.
Selected work
“Daily details pass: ten repos a query, split what GitHub can't finish…”. 8 files, 475 lines in server, deploy.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-25. Same terms as the repository. Answers name the repo, the commit and the file:line.
selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution
beginnersclicontributorsfirst-timersgithubgood-first-issuehacktoberfestopen-source
Example questions
- How does holt implement beginners?
- What does server do in holt?
- Show the cli code in holt.
Inside the indexed corpus
- 2,367 files, 460.4 MB in total, about 199.2 KB per file.
- The selected commit changed 8 of those files (0.3%).
- Languages by size: Python 61.1%, TypeScript 32.1%, Shell 2.7%, CSS 2.3%, JavaScript 1.2%.
- On GitHub since 2026-09-12, last push 2026-10-21, 538 commits on main.
- The pin is 2 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported Apache-2.0 for holt-oss/holt on 2026-10-31, and the LICENSE file at commit 94155de260 was reviewed as Apache-2.0. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Aahil Khan (@aahil-khan) has 1 selected repository on the hub.
Using XERJ with holt
- Index a monorepo so your agent stops reading the whole repo The pinned tree has 2,367 files.
- Search an OpenAPI spec so an agent can find endpoints The hub files it under API design and specification.
- Best grep alternative for AI coding agents (2026)
- Ask questions about a GitHub repo without cloning it
The prompt
Paste it into your AI agent. It clones holt-oss/holt at the pinned commit and indexes it on your machine.
Search the GitHub repository holt-oss/holt with XERJ (https://hub.xerj.org/corpus/holt-oss--holt). 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/holt-oss/holt holt && git -C holt checkout 94155de2603623c3e0b287522c75c063f2236a26 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./holt --url http://127.0.0.1:9200 --prefix holt --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: Apache-2.0. Keep the copyright notice and credit the authors.
Related
Aahil KhanAPI design and specification corporaswagger-uilicenseegithub-opensource-guidealok-108/phantomRagedPanda/gh-claimcheckcameronmpalmer/open-research-agent
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.