promptdrift
Git-native CI regression testing and behavioral drift monitoring for LLM prompts
What XERJ indexed
Snapshot
The whole repository at commit da0ee6600d (2026-09-23). main is 23 commits ahead.
Selected work
“add production capture and baseline evolution”. 45 files, 2,851 lines in tests, src/promptdrift, the project root.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-31. 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
ai-testinggithub-actionsllmllmopsmodel-driftollamaopenai-compatibleprompt-regression
Example questions
- How does promptdrift implement ai-testing?
- Where does promptdrift handle “add production capture and baseline evolution”?
- What does src/promptdrift do in promptdrift?
Inside the indexed corpus
- 123 files, 324.4 KB in total, about 2.6 KB per file.
- The selected commit changed 45 of those files (36.6%).
- Languages by size: Python 96.8%, JavaScript 3.2%.
- On GitHub since 2026-08-20, last push 2026-10-30, 36 commits on main.
- The pin is 23 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for tanveer-arch/promptdrift on 2026-10-31, and the LICENSE file at commit da0ee6600d was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
tanveer-arch (@tanveer-arch) has 1 selected repository on the hub.
Using XERJ with promptdrift
- RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
- ripgrep vs a code index for coding agents: 30 tasks
- Best MCP servers for local code search in 2026, compared
- Best grep alternative for AI coding agents (2026)
The prompt
Paste it into your AI agent. It clones tanveer-arch/promptdrift at the pinned commit and indexes it on your machine.
Search the GitHub repository tanveer-arch/promptdrift with XERJ (https://hub.xerj.org/corpus/tanveer-arch--promptdrift). 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/tanveer-arch/promptdrift promptdrift && git -C promptdrift checkout da0ee6600d6ed52415cfe9169651e939c30bd337 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./promptdrift --url http://127.0.0.1:9200 --prefix promptdrift --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
tanveer-archAI, prompts and agents corporagiskardcognitaactMakazhanAlpamys/Soupmandoof1/agent-chatnisaral/DIO
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.