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.
More from coding & agent
- Dev builds 3D universe explorer with 20 galaxies, 767 planets using Codex GPT-6.1 Sol — OpenAIDevs · 2026-11-02
- ChatGPT, Claude and Perplexity's fetchers don't run JavaScript, leaving client-rendered sites invisible to AI — gaganghotra_ · 2026-11-02
- SGLang boosts multimodal inference >10% by replacing GPU memory bookkeeping with a dict lookup — charles_irl · 2026-11-02
- kivi: hold Fn, talk, and it types polished text anywhere on your Mac — itsOmSarraf_ · 2026-11-02
- A base LLM plus 11 lines of code is all you need for a decision model — helloiamleonie · 2026-11-02
- Fix codebase structure before asking AI agents to write tests, says engineer — arpit_bhayani · 2026-11-02