FairyClaw: An Open-Source Async Agent Runtime for Long-Running, Event-Driven Server Deployments

Show and Tell
1

Hello everyone! :waving_hand:

We’re excited to share our new open-source project, FairyClaw.

No more bloated SKILL.md files eating your context window. Structured code replaces prose — cheaper and more accurate. :rocket:

Meet FairyClaw — an open-source async agent runtime for long-running server deployments:

  • Restructured Skill paradigm: instead of verbose markdown instructions flooding the context, Skills are declared as structured steps in manifest.json — deterministic playbooks that cut token usage while making tool selection and execution order semantically precise

  • Single-step Planner: one inference per wakeup, event-driven continuation — no monolithic loops, tasks resume naturally after interruption

  • Capability Groups: tools, skills, and hooks declared as pluggable units, routed semantically — structured decisions replace unbounded tool name guessing

  • Sub-Agent barrier aggregation: delegate to parallel sub-agents, results flow back automatically when all finish

  • Dual-process architecture: Gateway (user-facing, OneBot/HTTP) + Business (runtime + Planner) — clean separation, production-ready server deployment out of the box

  • Built from scratch. No LangChain dependency.

We believe this is just the start for token-efficient, semantically precise agentic systems! :rocket:

Code: GitHub - PKULab1806/FairyClaw · GitHub

Thanks for reading! We’d love for you to check it out and share any thoughts or feedback.

1 Like