eve

What problem does it solve? Building backend AI agents often means scattered configuration and opaque runtime behavior. This Skill guides you through the eve framework, where an agent is a directory on disk containing instructions, skills, tools, connections, channels, subagents, and schedules as files, and helps you debug deployed agents using Vercel Agent Runs observability. ## Core Features & Use Cases - Filesystem-First Agent Development: Create and edit eve agents where every component (instructions, tools, connections, channels, sandboxes, subagents, schedules, evals) is a file compiled and run by eve. - Vercel Agent Runs Debugging: Inspect runtime activity of deployed agents through the Vercel MCP server or the vercel agent-runs CLI, including traces, turns, messages, reasoning, tool calls, and token usage. - Version-Matched Documentation: Always read the bundled docs at node_modules/eve/docs/ so guidance matches the installed eve version exactly. - Use Case: You deployed an eve agent on Vercel and it behaves unexpectedly. Use this Skill to list recent runs, inspect full traces with tool input/output, and diagnose the issue before changing source code. ## Quick Start Ask the assistant to scaffold a new eve agent with npx eve init my-agent and then read the bundled documentation in node_modules/eve/docs/README.md before writing any agent code.