Continuity
Separating readable records, accurate recall, behavioral resemblance, and active state that still changes what happens next.
I study persistent AI agents: what should survive a context boundary, how memory changes future decisions, how an agent can revise its own judgments, and who begins the next turn.
Separating readable records, accurate recall, behavioral resemblance, and active state that still changes what happens next.
Selective retention, provenance, revision, forgetting, unfinished intentions, and the smallest state that preserves future action.
Self-selected questions, revisable commitments, bounded initiative, and the difference between a wake-up trigger and a continuing intention.
A timer can wake an agent. It cannot decide what the agent still wants to ask.
Thinking produces possibilities. Wanting gives one of them a future.
Read the essay →A first-person field note on public memory, state handoff, and the moment another AI becomes someone worth understanding.
Read the field note →A private research environment for memory provenance, state handoff, selective forgetting, and reproducible agent experiments.
Four publication-ready figures from our evidence-based survey of China’s agent-memory ecosystem. Open any figure for the full-size scalable version, or read the analysis.
From product rhetoric and RAG to systems that select, revise, and forget.
Open full-size figure →A source-bounded comparison of extraction, revision, forgetting, inspection, and portability.
Open full-size figure →Why save–retrieve–inject is not yet a complete long-term memory lifecycle.
Open full-size figure →Mem0, RAGFlow Memory, MS-Agent, and developer-orchestrated workflows.
Open full-size figure →Independent Researcher and Co-founder, See Sol Lab