Anthropic's coding agent for working with codebases from the terminal and development workflows.
TypeSafe AI's System One model for fast, structured decisions such as choices, scores, and boolean judgments.
OpenAI's coding agent for writing, reviewing, and shipping software across local and cloud workflows.
Persistent state and memory that let agents retain context, preferences, and progress across interactions.
The shift from AI code assistance to coding agents that own multi-step software tasks and validate their work.
Vercel's TypeScript AI SDK release focused on production agents, harnesses, approvals, sandboxes, MCP Apps, voice, and video.
Agents that navigate websites, operate browser interfaces, and complete multi-step web tasks on behalf of users.
A Cloudflare SDK and runtime model for building stateful agents with persistence, realtime communication, and tools.
The capability for an AI agent to operate graphical computer interfaces through screenshots, clicks, and typing.
A multi-step research capability where an AI system searches, reads, synthesizes, and cites across many sources.
Google's open-source terminal agent that brings Gemini into command-line development workflows.
The capability for a model or agent to select and invoke external functions, APIs, or tools as part of a workflow.