مهراد یعقوبی
مهراد یعقوبی's work was selected for the XERJ Corpus Hub, the open reference memory AI coding agents search before they write code. When an agent meets the same problem, it gets this implementation back as a worked example, with the author and the repository attached.
Totals across every corpus @MehradYaghoubi appears in; a commit selected for two corpora counts once. Files and lines count the selected commits; each corpus indexes the whole repository at its pinned commit.
What an agent can do with the jev-research-engineering corpus
MehradYaghoubi/jev-research-engineering: Free, MIT-licensed skill for coding and research. Screen relevant evidence with your chosen model while your main agent stays in charge
- Look up how jev-research-engineering implements agent-skills, claude-code, codex, with answers cited to file and line.
- Reuse a worked example: the commit “support configurable decision providers and report tokenizer ov…” (12 files · Python).
- Answer from jev-research-engineering's real Python source instead of memory (AI, prompts and agents).
- How does jev-research-engineering implement agent-skills?
- What does scripts do in jev-research-engineering?
Search the GitHub repository MehradYaghoubi/jev-research-engineering with XERJ (https://hub.xerj.org/corpus/mehradyaghoubi--jev-research-engineering). 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/MehradYaghoubi/jev-research-engineering jev-research-engineering && git -C jev-research-engineering checkout 1d63f101e3a7dbec881612b32941ab432f884fbd 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./jev-research-engineering --url http://127.0.0.1:9200 --prefix jev-research-engineering --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.
corpus mehradyaghoubi--jev-research-engineering · AI, prompts and agents
Related corpora: flexrag, xobotyi--cc-foundry-rust, juyterman1000/entroly, jaredchu/context-docs
AI search and retrieval with XERJ · Case study: reference coding for agents
Selected work
MehradYaghoubi/jev-research-engineering
Free, MIT-licensed skill for coding and research. Screen relevant evidence with your chosen model while your main agent stays in charge
The corpus is the whole repository at the pinned commit, not only the files of the selected commit.
Sign in with GitHub or Hugging Face to see more: every selected commit in full (commit date, every folder, licence review state, pin) and the pack builds of each corpus.
[](https://hub.xerj.org/contributors/MehradYaghoubi)
Included with the author's permission (email, 2026-10-29), under each repository's own licence, with attribution. Own more repositories? Sign in with GitHub and add them. Want something removed? Reply to the email, withdraw it on /add, or open an issue on xerj-org/xerj.