Mrugank Dake

What an agent can do with the proxenos corpus

mindemory/proxenos: A free, open-source agent that keeps your own records private on your computer and drafts the next step for you. Built first for people…

• Look up how proxenos implements ai-agents, healthtech, local-first, with answers cited to file and line.
• Reuse a worked example: the commit “Searchable memory, recall, a corrected network and Google readers” (61 files · Python, TypeScript).
• Answer from proxenos's real Python source instead of memory (AI, prompts and agents).

• Where does proxenos handle “Searchable memory, recall, a corrected network and Google readers”?
• How does proxenos implement ai-agents?
• What does src/twin do in proxenos?

Search the GitHub repository mindemory/proxenos with XERJ (https://hub.xerj.org/corpus/mindemory--proxenos).
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/mindemory/proxenos proxenos && git -C proxenos checkout dafeb29f56f19731eea9fbc3d6f99b9f22c2af99
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./proxenos --url http://127.0.0.1:9200 --prefix proxenos --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 mindemory--proxenos · AI, prompts and agents
Related corpora: dunorth595--ai-agent-memory, dunorth595--ai-agent-chat, Amz34/zeroegress, jicine1360-prog/autorcode
AI search and retrieval with XERJ · Case study: reference coding for agents