Anthropic began enforcing its terms against third-party clients using Claude Code subscriptions, forcing alternative harnesses like opencode to rework authentication (its issue thread became the debate's ground zero). A defining platform-risk moment for the open-harness ecosystem: the model provider owns the login, the harness does not.
Anthropic announces plans to donate MCP to a neutral foundation, with new registry, auth and sandbox specs — cementing MCP as vendor-neutral infrastructure for the entire agent ecosystem.
Anthropic makes Claude Code generally available and holds its first developer conference — with Claude Code for web, enterprise features, and hooks/MCP improvements central to agent workflows.
Anthropic open-sources the SDK behind Claude Code — the agent loop, tool use, subagents, memory and hooks — letting developers build their own Claude-powered agents on production rails.
Anthropic open-sources MCP, a standard for connecting AI assistants to data and tools. Within a year it was adopted by OpenAI, Google, Microsoft and most of the agent ecosystem — becoming the de-facto tool-connect layer of agent harnesses.