jami
Adaptive AI study platform with exam practice, dual-model marking, flashcards, notebooks, revision planning and a deterministic student learning model
What XERJ indexed
Snapshot
The whole repository at commit e41f1aa10a (2026-10-13). main is 31 commits ahead.
Selected work
“Tutor agent: check on another family, only where a slip is plausible,…”. 7 files, 180 lines in tests, lib/ai, services.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-13. 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
educationflashcardslearningadaptive-learningaiedtechfirebasenextjs
Example questions
- How does jami implement education?
- What does lib/ai do in jami?
- Show the flashcards code in jami.
Inside the indexed corpus
- Languages by size: TypeScript 97.6%, CSS 1%, JavaScript 0.9%, Python 0.4%, Shell 0%.
- On GitHub since 2026-03-09, last push 2026-10-28, 1,240 commits on main.
- The pin is 31 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for jarems421/jami on 2026-10-29, and the LICENSE file at commit e41f1aa10a was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
James Thomson (@jarems421) has 1 selected repository on the hub.
Using XERJ with jami
- RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
- Ask questions about a GitHub repo without cloning it
- Index a reference library for a coding agent
- ripgrep vs a code index for coding agents: 30 tasks
The prompt
Paste it into your AI agent. It clones jarems421/jami at the pinned commit and indexes it on your machine.
Search the GitHub repository jarems421/jami with XERJ (https://hub.xerj.org/corpus/jarems421--jami). 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/jarems421/jami-flashcards jami-flashcards && git -C jami-flashcards checkout e41f1aa10ac1751f2a5c99507839d4f3ff807e64 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./jami-flashcards --url http://127.0.0.1:9200 --prefix jami-flashcards --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
James ThomsonAI, prompts and agents corporawysking--postgrad-study-engine12-factor-agentsedliz-zimbabwe-treatment-guidelinesaryan-dani/Utilityquizmill/quizmilluser-github-me/mori-study
Stats: GitHub API, fetched 2026-10-29. Selected work and consent: the XERJ registry.