I added this open-source tool to my local AI stack, and my local LLM finally has persistent memory

AnythingLLM, a free open-source frontend from Mintplex Labs, adds persistent memory to local LLM setups. It runs as a chat interface on top of local model runners like LM Studio, Jan AI, or llama.cpp. Its key feature is an automatic background process that extracts facts from recent conversations and re-injects them as memories into future sessions. Memories can be scoped to a single workspace or applied globally. Manual memory entries are also supported. Setup requires pointing AnythingLLM at a running model instance, with some configuration differences from native runner presets.