eve

What problem does it solve? Building backend AI agents that persist across sessions requires managing instructions, tools, connections, and schedules as scattered configuration. This Skill guides you through the eve framework, which treats an agent as a directory of files on disk that eve compiles and runs, 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 instructions, skills, tools, connections, channels, subagents, and schedules are all files compiled by the framework. - Agent Runs Observability: Inspect runtime activity of deployed agents through the Vercel MCP server or the vercel agent-runs CLI, including traces, turns, tool calls, token usage, and subagent data. - 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 query recent runs and full traces via vercel agent-runs instead of guessing from 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 before writing any agent code.