• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Projects reportedly brings one agent per project to Claude Code

    A user describes agents that manage memory and spin off subagents for tasks, with options to request proactive work or scheduled actions.

    Ethan MollickEM
    Boris ChernyBC
    Mike KriegerMK
    9 Sources, ,

    TLDR

    A user describes Projects as bringing Claude Tag’s architecture to Claude Code: one agent per project that manages memory and spins off subagents for tasks. They say it can be asked to act proactively or do things on a schedule, and describe the experience as nicer than using a bunch of sessions.

    Combined views

    1.2M

    9 Sources, first seen 20d ago

    Combined views

    1.2M

    9 Sources, first seen 20d ago

    8.3K likes
    20d ago
    first seen 20d ago
    8.3K likes
    730 comments
    4.5K saves
    330 reposts
    730 comments
    4.5K saves
    330 reposts

    Sentiment

    Positive70.3%29.7%Negative

    Summary

    Positive accounts welcomed Claude Projects for letting one agent coordinate specialist teams and manage shared memory across tasks, while negative accounts worried about higher costs, context drift, and losing control.

    Based on 66 sentiment-bearing replies from 64 accounts across 5 conversations.

    9 Sources

    Thariq@trq212Projects brings the architecture of Claude Tag to Claude Code. It has one agent per project that manages memory and spins off subagents for tasks. You can ask it to be proactive, to do things on a schedule, etc. It feels a lot nicer than a bunch of sessions, try it out!20d
    Boris Cherny@bchernyProjects are how I write a lot of my code these days. Really excited for everyone to try the new experience! Rolling out now20d
    cat@_catwuIn the new Projects experience, Claude coordinates all of your sessions. I've been using it every day since it lets me operate at a higher level of abstraction. I fire off a batch of tasks and move on. Claude has context on everything I'm working on and can give me an aggregated status update whenever I ask. It also has long-lived memory that evolves as I use it. We're rolling this out over the coming weeks. Let me know what you think!20d
    Chubby♨️@kimmonismusVery good release. Claude coordinate parallel tasks from one conversation, starting in Claude Code. Claude then routes the work across threads that share project memory and keep running in the cloud after you close your laptop. Now we need the Opus 5.2 release, less lazy, less verbose and we are finally back on track!20d
    Alex Volkov@altryneChief Of Staff pattern already existed, and I'm super glad it comes as a first class citizen in Claude Code. This will mean optimizations in which models are doing what!20d
    Mike Krieger@mikeykOmid and the team did great work on this one. Most of my Claude Desktop work these days is in these new-style projects and I've really enjoyed how easy it is to kick off a bunch of work while still having a coordinator Claude responding quickly20d
    Ethan Mollick@emollickWhat makes Claude Projects so interesting is that it handles teams of agents really well, you talk to a main orchestrator agent and it spins up specialists. Basically it creates an organization to solve your issue, mixing expensive and cheap agents depending on your preferences. For example, I asked Fable in Claude Projects to select famous historical mysteries that it could try to resolve. It initiated research agents, selected the mysteries based on data it could access, and spun up eighteen separate threads, each with an agent each focused on one mystery. Then each thread launched additional agents (simulating avalanches, breaking codes) before summarizing those and passing them to still more agents for write up and another set of skeptical agents to fact check. It did this over a day of work, with the central orchestrator agent organizing it all. The results were interesting if you like historical mysteries. They are also for fun and certainly not definitive or guaranteed error-free (but they are also mostly reasonable & grounded in the literature). https://historical-mysteries.netlify.app/20d

    9 Sources

    Thariq@trq212Projects brings the architecture of Claude Tag to Claude Code. It has one agent per project that manages memory and spins off subagents for tasks. You can ask it to be proactive, to do things on a schedule, etc. It feels a lot nicer than a bunch of sessions, try it out!20d
    Boris Cherny@bchernyProjects are how I write a lot of my code these days. Really excited for everyone to try the new experience! Rolling out now20d
    cat@_catwuIn the new Projects experience, Claude coordinates all of your sessions. I've been using it every day since it lets me operate at a higher level of abstraction. I fire off a batch of tasks and move on. Claude has context on everything I'm working on and can give me an aggregated status update whenever I ask. It also has long-lived memory that evolves as I use it. We're rolling this out over the coming weeks. Let me know what you think!20d
    Chubby♨️@kimmonismusVery good release. Claude coordinate parallel tasks from one conversation, starting in Claude Code. Claude then routes the work across threads that share project memory and keep running in the cloud after you close your laptop. Now we need the Opus 5.2 release, less lazy, less verbose and we are finally back on track!20d
    Alex Volkov@altryneChief Of Staff pattern already existed, and I'm super glad it comes as a first class citizen in Claude Code. This will mean optimizations in which models are doing what!20d
    Mike Krieger@mikeykOmid and the team did great work on this one. Most of my Claude Desktop work these days is in these new-style projects and I've really enjoyed how easy it is to kick off a bunch of work while still having a coordinator Claude responding quickly20d
    Ethan Mollick@emollickWhat makes Claude Projects so interesting is that it handles teams of agents really well, you talk to a main orchestrator agent and it spins up specialists. Basically it creates an organization to solve your issue, mixing expensive and cheap agents depending on your preferences. For example, I asked Fable in Claude Projects to select famous historical mysteries that it could try to resolve. It initiated research agents, selected the mysteries based on data it could access, and spun up eighteen separate threads, each with an agent each focused on one mystery. Then each thread launched additional agents (simulating avalanches, breaking codes) before summarizing those and passing them to still more agents for write up and another set of skeptical agents to fact check. It did this over a day of work, with the central orchestrator agent organizing it all. The results were interesting if you like historical mysteries. They are also for fun and certainly not definitive or guaranteed error-free (but they are also mostly reasonable & grounded in the literature). https://historical-mysteries.netlify.app/20d

    Sentiment

    Positive70.3%29.7%Negative

    Summary

    Positive accounts welcomed Claude Projects for letting one agent coordinate specialist teams and manage shared memory across tasks, while negative accounts worried about higher costs, context drift, and losing control.

    Based on 66 sentiment-bearing replies from 64 accounts across 5 conversations.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet