The Agentica SDK gives you a Python framework for building AI agents with the @agentic decorator or spawn() function. You get typed return values, conversation persistence, tool passing through scope parameters, and built-in MCP integration for external tools. The decorator pattern is clean for turning functions into agents, while spawn() gives you more control over premises and system prompts. Token tracking and streaming are first-class features, and the error handling is granular enough to catch rate limits versus content filtering. It's opinionated about logging (stdout plus files by default) but you can configure it per-agent or globally. If you're building agents that need to coordinate with each other or wrap existing Python SDKs with agentic behavior, this handles the orchestration layer without forcing you into a heavyweight framework.
npx -y skills add parcadei/continuous-claude-v3 --skill agentica-sdk --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
juliusbrussee/caveman
mattpocock/skills
shadcn/improve
obra/superpowers
forrestchang/andrej-karpathy-skills
vercel-labs/skills