Rabee Elkholy

Corpus Hub contributor since 2026-10-20

Rabee Elkholy'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

5files

276lines

★ 8GitHub stars on repo

Totals across every corpus @rabee-elkholy 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 android-agent-harness corpus

rabee-elkholy/android-agent-harness: Stricter proof, not heavier workflow: an Antigravity-first Android AI harness for approval-bound changes, adaptive verification, and…

Look up how android-agent-harness implements ai-agents, android, antigravity, with answers cited to file and line.
Reuse a worked example: the commit “add opt-in discard for locally modified files and docto…” (5 files · Python).
Answer from android-agent-harness's real Python source instead of memory (AI, prompts and agents).

Example questions

How does android-agent-harness implement ai-agents?
What does agents do in android-agent-harness?

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

Search the GitHub repository rabee-elkholy/android-agent-harness with XERJ (https://hub.xerj.org/corpus/rabee-elkholy--android-agent-harness).
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/rabee-elkholy/android-agent-harness android-agent-harness && git -C android-agent-harness checkout 62cc584b39f02647b25722975de6eecc7d39038f
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./android-agent-harness --url http://127.0.0.1:9200 --prefix android-agent-harness --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 rabee-elkholy--android-agent-harness · AI, prompts and agents
Related corpora: xerj-blogposts, agno, dagoSte/squadra, stoneskin/open-memex
AI search and retrieval with XERJ · Case study: reference coding for agents

Selected work

GitHub ★ 8

rabee-elkholy/android-agent-harness

62cc584b39 feat(update): add opt-in discard for locally modified files and docto…

selected commit: 5 files · 276 lines · Python · agents, the project root

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

selected · in licence reviewcorpus rabee-elkholy--android-agent-harnessAIMITai-agentsandroidantigravityclaude-codecode-reviewcopilot agreed 2026-10-20

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/rabee-elkholy/badge.svg)](https://hub.xerj.org/contributors/rabee-elkholy)

Included with the author's permission (email, 2026-10-20), under each repository's own licence, with attribution. Want it removed? Reply to the email or open an issue on xerj-org/xerj.