26 Unix tools. One binary. Zero dependencies. · the missing coreutils for the agent era · vrk mcp - expose all 26 tools to any AI agent · curl vrk.sh/install.sh | sh - ready in 5 seconds · 26 Unix tools. One binary. Zero dependencies. · the missing coreutils for the agent era · vrk mcp - expose all 26 tools to any AI agent · curl vrk.sh/install.sh | sh - ready in 5 seconds

Cache LLM response

Avoids duplicate API calls for identical prompts - the hash keys the cache so reruns are free.

Send a prompt, get the request hash, and store the response in kv.

Pipeline

RESULT=$(cat doc.txt | vrk prompt --json)
HASH=$(echo "$RESULT" | jq -r '.request_hash')
echo "$RESULT" | jq -r '.response' | vrk kv set "cache:$HASH"

Tools used