3 projects
ggufpacker
Check that a GGUF quant derives bit-exactly from its claimed base model; pack quant ladders as recipes and regenerate every file bit-exact.
toolrails
Valid tool calls from any local model. A drop-in OpenAI-compatible proxy for Ollama that guarantees well-formed tool calls and restores tool_choice.
overllm
Catch the LLM/AI calls you didn't need. A fast, deterministic linter that flags LLM API calls where plain code is simpler, cheaper, and more reliable.
