ClaudeDevs

Live now at claude.ai/code and on mobile. Tell us what you think.

Work across web and CLI. Start a session on the web or mobile, then run claude --teleport to continue in your terminal with full history and the right branch ready to go.

We’ve refreshed Claude Code on the web and mobile. A few things that recently shipped 🧵

We've added support for Claude Managed Agents memory to the claude-api skill, which is built into Claude Code. Trigger the skill with: “/claude-api” Then ask about Managed Agents memory. You can also see the skill here: github.com/anthropics/ski…

Memories are portable: they can be easily exported as files and managed directly via the API for full developer control. See the docs here: platform.claude.com/docs/en/manage…

Memory is scoped to a workspace and stored as text files that persist across sessions. When a store is attached to a session, it mounts inside the container, and Claude can read and write to it.

Memory on Claude Managed Agents is now in public beta on the Claude Platform, letting agents learn and improve across different sessions.

Thanks to the entire Claude community for giving feedback and continuing to build with us. Read the full post-mortem here: anthropic.com/engineering/ap…

We’re making changes to catch these types of issues earlier, including more internal dogfooding with configs that exactly match those of our users and creating a broader set of evals and running them against isolated system prompt changes

Over the past month, some of you reported Claude Code's quality had slipped. We investigated, and published a post-mortem on the three issues we found. All are fixed in v2.1.116+ and we’ve reset usage limits for all subscribers.

New blog: Building agents that reach production systems with MCP. When should agents use direct APIs vs CLIs vs MCP? Plus patterns for building MCP servers, context-efficient clients and pairing MCP with skills. claude.com/blog/building-…

Run `claude update` to try it out. Learn more in the docs: code.claude.com/docs/en/ultrar…

New in Claude Code: /ultrareview (research preview) runs a fleet of bug-hunting agents in the cloud. Findings land in the CLI or Desktop automatically. Run it before merging critical changes—auth, data migrations, etc. Pro and Max users get 3 free reviews through 5/5.

Learn tips on how to maximize your prompt cache hit rate in @trq212's post: x.com/trq212/status/…

What is prompt caching? Learn more in @RLanceMartin's article on prompt caching in the Claude API: x.com/RLanceMartin/s…

Caching is critical for customers to lower both costs and TTFT. We’re launching a new dashboard in Claude Developer Console to increase visibility and help customers optimize their usage. Check it out here: platform.claude.com/usage/cache

Read more in the docs here: #session-recap" target="_blank" rel="nofollow noopener">code.claude.com/docs/en/intera…

Claude Code in the terminal will now show recaps when you switch focus away from the session and then come back. This should help you stay more in flow while multi-clauding.