Quickstart
Cycles is a runtime authority for autonomous agents — it enforces hard budget and action limits before an agent runs an LLM call, a tool, or any side-effecting operation. This section takes you from zero to a working integration.
New to Cycles?
Start with What is Cycles? for a 5-minute orientation, then run through the end-to-end tutorial to see reserve / commit / release in practice.
Add Cycles to an existing application
| Stack | Guide |
|---|---|
| Python | Python client |
| TypeScript | TypeScript client |
| Rust | Rust client |
| Java / Spring Boot | Spring Boot starter |
| MCP host (Claude, Cursor, Windsurf) | MCP server quickstart |
Use an AI coding assistant to integrate
Add Cycles with Claude or Codex — Claude Code, Cursor, GitHub Copilot, etc. can wire Cycles into an existing app from natural-language instructions.
Deploy self-hosted Cycles
Cycles is Apache 2.0 and self-hosted — there is no managed cloud. Run it on your own infrastructure.
- Architecture overview — how the runtime server, admin API, dashboard, and events service fit together.
- Deploy the full stack — server + admin + dashboard + events.
- Self-host the runtime server — the protocol-conforming server alone.
- Deploy the events service — webhook delivery and signed audit events.
- Deploy the admin dashboard — UI for tenants, budgets, and audit.
Connect AI tools via MCP
Claude Desktop · Claude Code · Cursor · Windsurf · MCP server over HTTP
Plan your rollout
- Add hard budget limits to Spring AI — the reservation pattern walked through end-to-end.
- Choose a first rollout — tenant budgets, run budgets, or model-call guardrails as a starting point.
Next
- How-To Guides — recipes for integrations, budget patterns, operations, and troubleshooting.
- Cycles Protocol — the open specification for runtime budget authority.
- Why Cycles — the case for runtime authority over autonomous systems.