Michelle Budri Bognar

What an agent can do with the my-jarvis corpus

MichelleBudri/my-jarvis: Fully local voice assistant for macOS (Apple Silicon): Ollama + Whisper + Piper. No cloud, no tokens

• Look up how my-jarvis implements ai-assistants, macos, offline-ai, with answers cited to file and line.
• Reuse a worked example: the commit “Spotify voice control and music ducking (phase 9)” (11 files · Python, TypeScript).
• Answer from my-jarvis's real Python source instead of memory (AI, prompts and agents).

• Where does my-jarvis handle “Spotify voice control and music ducking (phase 9)”?
• How does my-jarvis implement ai-assistants?
• What does backend do in my-jarvis?

Search the GitHub repository MichelleBudri/my-jarvis with XERJ (https://hub.xerj.org/corpus/michellebudri--my-jarvis).
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/MichelleBudri/my-jarvis my-jarvis && git -C my-jarvis checkout 3032fa16b054004db7b2ab201519ee2928078dad
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./my-jarvis --url http://127.0.0.1:9200 --prefix my-jarvis --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 michellebudri--my-jarvis · AI, prompts and agents
Related corpora: icd10cm-codes, icd10-who, aryanjsx/Locus, krahd/mail_summariser
AI search and retrieval with XERJ · Case study: reference coding for agents