e-volv

AI Agents

Workflowsremembercontextacrossruns

Persistent memory tools let agents recall conventions, recurring issues, and decisions.

Agents automatically read and write to a scoped memory layer. Use it to store architecture decisions, style guides, incident post-mortems, and anything else that should persist between executions.

  • memory_write, memory_read, and memory_search auto-injected into every run
  • Scoped per workflow so knowledge stays isolated
  • Surfaces the right context before the agent acts