Batu Ergül

Corpus Hub contributor since 2026-10-25

Batu Ergül'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

10files

324lines

★ 2GitHub stars on repo

Totals across every corpus @Walbertb4 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 TaskVex corpus

Walbertb4/TaskVex: Windows AI assistant for real-time voice interaction and tool-driven desktop workflows. Built with Python, WebView2 and Gemini Live

Look up how TaskVex implements ai-assistant, desktop-automation, gemini-api, with answers cited to file and line.
Reuse a worked example: the commit “preserve bounded Live conversation memory across sessio…” (10 files · Python, JavaScript).
Answer from TaskVex's real Python source instead of memory (Web and frontend platform).

Example questions

How does TaskVex implement ai-assistant?
What does v1 do in TaskVex?

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

Search the GitHub repository Walbertb4/TaskVex with XERJ (https://hub.xerj.org/corpus/walbertb4--taskvex).
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/Walbertb4/TaskVex TaskVex && git -C TaskVex checkout dc7931801a83877e3a86c88b292072195c140e6b
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./TaskVex --url http://127.0.0.1:9200 --prefix taskvex --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 walbertb4--taskvex · Web and frontend platform
Related corpora: agentscope, dunorth595--ai-agent-chat, zaxchou/fermata, nano-br/voice-mate
Case study: reference coding for agents

Selected work

GitHub ★ 2

Walbertb4/TaskVex

dc7931801a feat(stage5): preserve bounded Live conversation memory across sessio…

selected commit: 10 files · 324 lines · Python, JavaScript · v1

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

live on the hub · licence clearedcorpus walbertb4--taskvexWEBMITai-assistantdesktop-automationgemini-apijavascriptpythonpywebview agreed 2026-10-25

[![XERJ Corpus Hub contributor](https://hub.xerj.org/contributors/Walbertb4/badge.svg)](https://hub.xerj.org/contributors/Walbertb4)

Included with the author's permission (email, 2026-10-25), 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.