Nathan Schmid

What an agent can do with the glassbeetle corpus

Open-Glassbeetle/glassbeetle: A local-first AI agent platform for connecting and orchestrating multiple AI models through API keys, with support for both cloud-based and

• Look up how glassbeetle implements ai, ai-agents, ai-coding, with answers cited to file and line.
• Reuse a worked example: the commit “add OpenAI model adapter with full completion and streaming sup…” (6 files · TypeScript).
• Answer from glassbeetle's real TypeScript source instead of memory (AI, prompts and agents).

• How does glassbeetle implement ai?
• What does apps/api do in glassbeetle?

Search the GitHub repository Open-Glassbeetle/glassbeetle with XERJ (https://hub.xerj.org/corpus/open-glassbeetle--glassbeetle).
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/Open-Glassbeetle/glassbeetle glassbeetle && git -C glassbeetle checkout 354101cd6c666ad46f5822034a7aaa21684d5648
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./glassbeetle --url http://127.0.0.1:9200 --prefix glassbeetle --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 open-glassbeetle--glassbeetle · AI, prompts and agents
Related corpora: dunorth595--ai-agent-chat, dunorth595--ai-agent-memory, AltanS/collie, dmvieira/appacadabra
AI search and retrieval with XERJ · Case study: reference coding for agents