Romina Parimi

Corpus Hub contributor since 2026-10-22

Romina Parimi'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.

1corpus

1selected commit

19files

1,531lines

★ 1GitHub stars on repo

Totals across every corpus @rominap22 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 strandsharness-langchain-jev corpus

rominap22/strandsharness-langchain-jev: How to build typed decision layers in front of an LLM using Strands Harness, Jev, Strands Decider, and LangChain. Demos from…

Reuse a worked example: the commit “add Strands Decider harness for side-by-side comparison with Jev” (19 files · Python).
Answer from strandsharness-langchain-jev's real Python source instead of memory (AI, prompts and agents).

Example questions

Where does strandsharness-langchain-jev handle “add Strands Decider harness for side-by-side comparison with Jev”?
What does tests do in strandsharness-langchain-jev?

Paste it into your AI agent. It clones the repo at the pinned commit and indexes it on your machine.

Search the GitHub repository rominap22/strandsharness-langchain-jev with XERJ (https://hub.xerj.org/corpus/rominap22--strandsharness-langchain-jev).
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/rominap22/strandsharness-langchain-jev strandsharness-langchain-jev && git -C strandsharness-langchain-jev checkout 9d11206d0b429a0b93483e668ab99f825d4a4ffd
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./strandsharness-langchain-jev --url http://127.0.0.1:9200 --prefix strandsharness-langchain --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 rominap22--strandsharness-langchain-jev · AI, prompts and agents
Related corpora: awesome-mcp-servers, 12-factor-agents, flagembedding, kotaemon
AI search and retrieval with XERJ · Case study: reference coding for agents

Selected work

GitHub ★ 1

rominap22/strandsharness-langchain-jev

9d11206d0b feat: add Strands Decider harness for side-by-side comparison with Jev

selected commit: 19 files · 1,531 lines · Python · tests, harness_decider, demo_slides

The corpus is the whole repository at the pinned commit, not only the files of the selected commit.

selected · in licence reviewcorpus rominap22--strandsharness-langchain-jevAIMIT agreed 2026-10-22

Not installable yet: this corpus is not in the hub registry until its licence review passes, so xerj corpus add and xerj ask cannot fetch it. It becomes installable when this card says live in the hub.

[![XERJ Corpus Hub contributor](https://hub.xerj.org/contributors/rominap22/badge.svg)](https://hub.xerj.org/contributors/rominap22)

Included with the author's permission (email, 2026-10-22), under each repository's own licence, with attribution. Want it removed? Reply to the email or open an issue on xerj-org/xerj.