We built Orra after our AI agents crashed in production, costing us thousands in unnecessary LLM calls. It's a Plan Engine that sits between your AI app and execution environment, handling all the messy coordination so you can focus on your agents' core logic.<p>Key features:<p>* Works with any language or agent framework (Python, JS today, more coming)<p>* AI-powered planning with domain safety guardrails<p>* Production-grade reliability with exactly-once execution<p>* Run tools as services to reduce latency and hallucinations<p>Unlike traditional workflow systems, Orra was built specifically for the dynamic nature of AI agents. It's open source (MPL-2.0), self-hostable, and currently in Alpha.<p>Looking forward to your feedback!
Here's the launch blog post for more context: <a href="https://outgoing-icecream-a85.notion.site/The-Missing-Glue-Layer-for-Multi-Agent-Applications-1a0605f92f9c80ca83acef5402a334dd" rel="nofollow">https://outgoing-icecream-a85.notion.site/The-Missing-Glue-L...</a>