Projects reportedly brings one agent per project to Claude Code

@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!

@bchernyProjects are how I write a lot of my code these days. Really excited for everyone to try the new experience! Rolling out now

@_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!

@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!

@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!

@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 quickly

@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/

@emollickCaveats: I take no money from the AI labs, and pay for my own accounts, but during early access there is no limit on tokens so I can’t speak to costs. Also, I have published peer reviewed work in history but am only an interested amateur on the topics the AI selected.

@bchernyProjects have changed not only how I interact with Claude but how I code. I stopped managing sessions. I just send thoughts as they come, Claude splits them into threads, and the project remembers how I work. It's where I do a ton of my coding now. [screenshot: my actual prompts for claude code cli yesterday]

Projects reportedly brings one agent per project to Claude Code

TLDR

Useful links

Combined views

Projects reportedly brings one agent per project to Claude Code

Useful links

9 Sources

Combined views

Useful links

Useful links

Sentiment

Summary

Useful Links

Related Videos

TLDR

Sentiment

9 Sources

Sentiment

Summary

Useful Links

Related Videos

Sentiment

Useful Links

Related Videos