Anthropic announced a redesigned beta Projects experience for Claude Code featuring a coordinator that directs parallel agent threads using shared memory and…
2 editorial reports · 2 verified social mentions. The most authoritative report leads while later evidence completes the story.
I trusted the Stats tab enough to build my own tracker on its method. Then I recounted from the raw ~/.claude/projects files: the Stats number is about double, because Claude Code writes one transcript row per content block and each row repeats the whole call's usage. The Usage tab next to it dedupes correctly (1,647 requests vs 4,430 rows in the original bug report), and so does `claude -p --output-format json`. Anthropic's own docs say to dedupe on message id. Reported on GitHub five times since August 2025 (#6805, #87303, #90991, #91775, and #94224 for the desktop app on Sunday). No human reply. Billing and limits are server-side, so nobody is overcharged; it's the number you use to judge what the plan gave you, and to compare with other vendors. Script (read-only, stdlib only, prints p
Open mention📰 Claude Code relaunches Projects to manage multiple AI agents in the cloud The revamped projects feature in Claude Code allows users to run multiple agents under the same roof, with a shared memory, goals, and library of files and artifacts. Similar to Grok Bot and other ... 📰 Source: The Verge 🔗 Link: https://www.theverge.com/ai-artificial-intelligence/997134/anthropic-claude-code-projects # AI # ArtificialIntelligence
Open mention