Aevonix/FlashAlign
ReAlign models instantly, on demand. Per-request alignment for verified users and channels, or Always On. Use directly or with Hermes, OpenClaw and custom harnesses.
GitHub repository with 119 stars and 13 forks.
Language: Python
Topics: abliteration, hermes, inference, llama-cpp, llm, model-alignment, openclaw, sglang, tensorfold, vllm