Claude Projects comes to Claude Code: one agent per project manages memory and spins off parallel subagents

trq212 · x · 2026-09-18

Anthropic announced that Projects now run from a single conversation in Claude Code (beta for select Pro/Max users in cloud sessions, rolling out to all users): you describe the work, and Claude directs parallel threads that keep going after you close your laptop. User trq212 adds hands-on context: each project gets one primary agent that manages memory and spawns subagents, can act proactively or on a schedule — a much nicer model than juggling multiple sessions.

Related event: Anthropic Rebuilds Claude Projects Around Parallel Threads(22 posts)→

Original post →

More from coding & agent

coding & agent channel →