GoKawiilAgent memory as a file format
Memoryfields - a vastly simpler way to do agent memory
[Floppy disk insertion noise] WOW - I know the corporate VLAN configuration
Many model benchmarks start from a blank context window. The tabula rasa of AI. To some extent, this makes sense, to keep the benchmarks fair.
But real agents should never start from a blank context window. They should start with as much relevant information available to the agent as possible. Your AI agents should start with memories.
Why existing agent memory systems don't seem to work
The trouble is, a lot of agent memory systems are actually pretty rubbish. I think there are roughly three popular kinds of memory system at the moment, each of them not working in their own way.
The first are ones that deliberately tie you into a specific harness - usually written by the lab that rents you that harness. Said lab desperately wants to transition out of the (highly competitive) "API business" and into the (much more lucrative) "platform business". This form of system usually works by mining information out of your conversation history, with the result that most of their memories are all about you, even though information about the world is generally much more useful.
Another kind is ludicrously complicated. I know of one prominent system that needs pgvector, a Neo4j graph database and an LLM of its own just to decide what's worth remembering. This complexity is not only difficult to administer, but, for reasons I will explain: these Big Systems confuse the models too. They also fail to scale with the model frontier as it moves forward.
The final kind is the "High Modernist" variety, which imagine an idealised, rationalist form of memory. Inevitably, this involves a graph, and sometimes logical propositions as well. This kind systematically strips information from its context and leaves it isolated and senseless to the agent (and you). How useful, after all, is a simple list of "distilled facts"?
... continue reading