> This page is also available as Markdown: append .md to its URL. The full index of Sikaru docs is at https://docs.sikaru.ai/llms.txt. Code examples use only operations from the public API reference at https://docs.sikaru.ai/api-reference.

# Get started

## Docs

- [Build, run, and improve agents with Sikaru](https://docs.sikaru.ai/get-started/overview.md): Sikaru is a managed agent runtime. You define an agent and send it work; Sikaru runs it and returns results, events, and execution evidence.
- [Core concepts](https://docs.sikaru.ai/get-started/core-concepts.md): Learn how organizations, projects, agents, releases, sessions, runs, and related resources fit together, and which IDs your application should keep.
- [Run your first agent](https://docs.sikaru.ai/get-started/quickstart.md): Create a support agent, ask it to summarize a case, and read its result. About ten minutes, with no external tools or model credentials.
- [The agent lifecycle](https://docs.sikaru.ai/get-started/agent-lifecycle.md): Follow one piece of work from sign-in to answer, including sessions, context, tool execution, steering, results, objectives, and how memory and evaluated improvements help later work.
- [Authentication](https://docs.sikaru.ai/get-started/authentication.md): Authenticate your backend with a project API key, choose the permissions each task needs, and diagnose 401, 403, and 404 responses.
- [Use Sikaru with AI agents](https://docs.sikaru.ai/get-started/use-with-ai-agents.md): Give Claude Code, Codex, Cursor, or any coding agent the Sikaru docs, the API schema, and the agent-authoring skill.