Show HN: Cush – curl your shell, an HTTP tunnel for AI agentsgithub.com3 points·by esafranchik·há 3 meses·0 comments
esafranchik·há 2 meses·discussWouldn't NDCG/token results vary wildly depending on the agent's query and the number of returned items?e.g. agents often run `grep -m 5 "QUERY"` with different queries, instead of one big grep for all items.
esafranchik·há 2 meses·discussTwo follow-ups:1) How do you compare accuracy? by checking if the answer is in any of the returned grep/bm25/semble snippets?2) How do you measure token use without the agent, prompt, and tools?
esafranchik·há 2 meses·discussIs the benchmark measuring one-shot retrieval accuracy, or Coding agent response accuracy?
esafranchik·há 3 meses·discussDoes this work with any tool calls that make an HTTP request? e.g. calling `curl` directly vs writing a script to make the request, then calling it
esafranchik·há 3 meses·discussHave you noticed an relationship between recall and the number of files/memories?
e.g. agents often run `grep -m 5 "QUERY"` with different queries, instead of one big grep for all items.