Contact
Most teams reach out for one of four reasons — they all land in the same inbox, and a founder reads every one.
Why people reach out
- Piloting Cycles on a real stack. You're putting Cycles in front of a real workload — Python, TypeScript, Spring Boot, Rust, MCP — and want implementation help or a second pair of eyes on the integration.
- Hit a failure mode we haven't documented. Runaway agent, retry storm, unit mismatch, scope-derivation edge case. Tell us what broke; we'll add it to the runbook.
- Feedback on the protocol or roadmap. You've read the spec and have opinions on the error contract, permission model, or something you need in v0.1.26.
- Evaluating Cycles for production. You're comparing it to rate limiters, LLM gateways, or observability tools. We'll walk through the spec, demo the runtime, and answer integration questions.
Get in touch
One short form, same inbox for all four reasons above. Expect a reply from a human.
Found a bug or concrete technical issue?
Open a GitHub issue instead — it's faster for everyone, and it puts the fix in the public record.
Other channels
- GitHub: github.com/runcycles — code, issues, discussions
- Protocol spec: cycles-protocol — the source of truth for the wire format
- Blog: runcycles.io/blog — field notes and new posts as they ship