voidstack

What an agent can do with the expert-mentor corpus

voidstackloop/expert-mentor: Turn any LLM: Claude, ChatGPT, Gemini, or a local Ollama/llama.cpp model: into a calibrated expert mentor for any field. CLI + Claude…

• Look up how expert-mentor implements ai-tutor, chatgpt, claude, with answers cited to file and line.
• Reuse a worked example: the commit “Add provider bundles for Claude, ChatGPT, Gemini and Agensi” (3 files · Python).
• Answer from expert-mentor's real Python source instead of memory (AI, prompts and agents).

• Where does expert-mentor handle “Add provider bundles for Claude, ChatGPT, Gemini and Agensi”?
• How does expert-mentor implement ai-tutor?
• What does scripts do in expert-mentor?

Search the GitHub repository voidstackloop/expert-mentor with XERJ (https://hub.xerj.org/corpus/voidstackloop--expert-mentor).
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/voidstackloop/expert-mentor expert-mentor && git -C expert-mentor checkout b116ae408e89bc5c907612f4bef50db18fc4ec59
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./expert-mentor --url http://127.0.0.1:9200 --prefix expert-mentor --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 voidstackloop--expert-mentor · AI, prompts and agents
Related corpora: aider, wysking--postgrad-study-engine, HatsyRei/maid-native, sebin-gg/brevity-prompt
AI search and retrieval with XERJ · Case study: reference coding for agents