Rupert Germann

What an agent can do with the ai-image-aura corpus

rupertgermann/ai-image-aura: Local-first AI image studio with OpenAI, Google, and local models. Batch generation, Autopilot prompt refinement, layered editing, cost…

• Look up how ai-image-aura implements image-generation, react, typescript, with answers cited to file and line.
• Reuse a worked example: the commit “preserve image work and replay across failures” (27 files · TypeScript).
• Answer from ai-image-aura's real TypeScript source instead of memory (AI, prompts and agents).

• Where does ai-image-aura handle “preserve image work and replay across failures”?
• How does ai-image-aura implement image-generation?
• What does e2e do in ai-image-aura?

Search the GitHub repository rupertgermann/ai-image-aura with XERJ (https://hub.xerj.org/corpus/rupertgermann--ai-image-aura).
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/rupertgermann/ai-image-aura ai-image-aura && git -C ai-image-aura checkout efb38afcafc4ae4c5e5e0c888672785748abeaa6
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./ai-image-aura --url http://127.0.0.1:9200 --prefix ai-image-aura --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 rupertgermann--ai-image-aura · AI, prompts and agents
Related corpora: prompt-engineering-guide, react-spectrum, fazal305/ai-research-notebook, fazal305/devflow
AI search and retrieval with XERJ · Case study: reference coding for agents