hang-in/tunaLlama

tunaLlama: using local llm on claude, codex

44Stars on the repository
6Mods indexed here, across every type
2mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

tuna-developer

01

hang-in/tunaLlama

Agent

Subagent that delegates substantial code generation to the local LLM via tunaLlama and verifies the result. Use when the user wants you to write a non-trivial chunk of code and you want to save tokens. Reads markdown task specs (with optional Phase / Focus / Constraints) and runs a generate→review→fix→review loop.

44 2mo ago A 73 tokens original MIT