What we're learning as we build shared memory for AI agents: what to store, what compounds, and where the edge of today's tools really is.
Human-crafted knowledge works perfectly fine, until data-driven learning surpasses it. Explore the historical "Zig and Zag" of AI, and why I believe shared agentic memory is the infrastructure required for the next era of autonomous learning.
··4 min read·Most AI memory tools give back what you put in. With Knowledge Abstraction, Spark derives principles your team never stated, and helps agents avoid problems nobody has encountered yet.
6 min readFiles are the most popular form of agent memory. Here are four things they structurally cannot do.
4 min readContext windows can retrieve facts with remarkable accuracy, until compaction silently erases the project rules and conventions your team depends on.
4 min readMost enterprise AI systems do not fail because the model is incapable. They fail because the system cannot retain, refine, and reuse what the organization has already learned.
7 min readThe term 'memory' is used to describe wildly different systems. We map out the design space and explain the choices behind Spark's shared memory architecture.
13 min readMost teams running AI coding agents pay for the same knowledge over and over. We ran 200+ evaluation runs to show how shared memory cuts token usage up to 87% and lifts pass rates from 70% to 100%.
4 min read