Foundations
Agent frameworks, browser tools, and MCP servers are multiplying at extraordinary rates. The more interesting story is the selection pressures quietly building underneath.
Foundations
Agent frameworks, browser tools, and MCP servers are multiplying at extraordinary rates. The more interesting story is the selection pressures quietly building underneath.
Everything Grows When Nothing Has Failed Yet
Ninety-seven million monthly downloads. Every major lab shipping a framework. Thousands of MCP servers, most less than a year old. The landscape maps for AI agents have become so dense they're nearly unreadable. By every surface measure, the ecosystem is thriving.
Something sits oddly alongside it: only 11% of organizations piloting agentic AI have actually reached production. The protocol at the center of the ecosystem has an official roadmap that reads less like a victory lap than a gap analysis. Building agents has never been cheaper, and operating them reliably remains expensive, slow, and unsolved. The distance between those two facts is quietly shaping the landscape.
Everything Grows When Nothing Has Failed Yet
Ninety-seven million monthly downloads. Every major lab shipping a framework. Thousands of MCP servers, most less than a year old. The landscape maps for AI agents have become so dense they're nearly unreadable. By every surface measure, the ecosystem is thriving.
Something sits oddly alongside it: only 11% of organizations piloting agentic AI have actually reached production. The protocol at the center of the ecosystem has an official roadmap that reads less like a victory lap than a gap analysis. Building agents has never been cheaper, and operating them reliably remains expensive, slow, and unsolved. The distance between those two facts is quietly shaping the landscape.
The Agent Toolchain Is Consolidating in Four Different Directions at Once
Playwright has 84,000 GitHub stars and roughly double the adoption of Selenium. By most measures, it won. So why did one of the most prominent AI browser tools just rip it out entirely and rewrite from scratch? Everyone talks about the agent toolchain consolidating. But the layers of the stack are moving at different speeds, in ways that contradict each other. The kind of movement you're watching tells you as much as which tool is ahead.
The Agent Toolchain Is Consolidating in Four Different Directions at Once
Playwright has 84,000 GitHub stars and roughly double the adoption of Selenium. By most measures, it won. So why did one of the most prominent AI browser tools just rip it out entirely and rewrite from scratch? Everyone talks about the agent toolchain consolidating. But the layers of the stack are moving at different speeds, in ways that contradict each other. The kind of movement you're watching tells you as much as which tool is ahead.
Further Reading
Past Articles
A growing wave of tools now lets you export an agent definition and import it into a different framework. System prompts...
Teams building agent infrastructure keep reaching for the distributed systems playbook they already trust. Service disco...
More than 35 companies are now building practice environments for AI agents. Anthropic has discussed spending over a bil...
Docker found its seam between application and infrastructure, and that boundary turned out to be clean enough to hold ac...