我们致力于探索、分享和推荐最新的实用技术栈、开源项目、框架和实用工具。每天都有新鲜的开源资讯等待你的发现！ 前言概述 如果你同时用过 Claude Code、Codex、Gemini CLI 这几个 AI 编程命令行工具，大概率经历过这种事：早上想用 A 服务商的 Claude 渠道，下午想切到 B 服务商的 Codex，晚上又想试试 Gemini 官方。每切一次，就要翻一遍 ~/.claude/ ...

SAN FRANCISCO—At its Code with Claude developer conference on Wednesday, Anthropic announced a deal with SpaceX to utilize the entire compute capacity of the latter’s data center in Memphis, Tennessee ...

Anthropic has now announced a major boost to its Claude Code usage limits after announced a new partnership with Elon Musk’s ...

Claude subscription billing changes June 15 as Anthropic moves Agent SDK and claude -p to a separate per-user credit of $20 ...

天下苦 Anthropic 久矣。 就在今天，Anthropic 一度偷偷地将 Claude Code 从 Pro 套餐页面移除，引发开发者广泛不满。数小时后，官网页面回滚，负责人称本次仅为小范围测试。但本次事件传递出的信号十分明确：高消耗的 AI 编程代理正逼迫平台重写订阅规则，Claude Code ...

Developers relying on Anthropic’s Claude Code command-line tool are discovering that their Pro plan usage limits deplete far more quickly than they anticipated, creating friction for power users who ...

If an agent is inefficient and burns through tokens, it simply drains the user's new $20 to $200 Agent SDK credit budget faster, rather than exceeding the value of Anthropic's fixed monthly ...

Paid Claude plans get a dedicated monthly programmatic credit for Agent SDK, claude -p, Claude Code GitHub Actions. Subscription interactive credits no longer cover programmatic use; programmatic ...

Anthropic has partnered with SpaceX and secured major compute deals to expand infrastructure capacity, enabling higher usage ...

Are you a subscriber to Anthropic's Claude Pro ($20 monthly) or Max ($100-$200 monthly) plans and use its Claude AI models and products to power third-party AI agents like OpenClaw? If so, you're in ...

Anthropic has published an unusually concrete account of how its own engineers use Skills in Claude Code, the company’s command-line coding agent, in a June 3 post on the Claude blog written by ...

Tokens are the basic unit of AI usage, but the consumption is becoming a distorted metric. Incentivizing maximum use of tokens only measures what an engineer spends on AI instead of what they produce ...