{"slug": "show-hn-rebuno-an-open-source-runtime-for-production-agents", "title": "Show HN: Rebuno - An open-source runtime for production agents", "summary": "Rebuno, an open-source execution runtime for operating AI agents in production, has been released under the MIT license and is free to self-host. Rebuno runs agents as HTTP services, dispatches work through signed webhooks, keeps execution state in Postgres, and evaluates per-agent YAML policies on each step to allow, deny, or hold tool and model calls for human approval, recording policy decisions and step outcomes in one append-only event log. The project ships Python and TypeScript SDKs plus examples using LangChain, CrewAI, Pydantic AI, Vercel AI SDK, and Mastra.", "body_md": "I have been building Rebuno, an open-source execution runtime for operating AI agents in production. It manages execution state and guardrails across agents built with different frameworks.\n\nAgents run as HTTP services. Rebuno dispatches work through signed webhooks and keeps execution state in Postgres. Agents submit tool and model calls to Rebuno as steps before executing them.\n\nFor each new step, Rebuno evaluates per-agent YAML policies, independently of the model's prompt. It can allow the call, deny it, or hold it for human approval. The agent executes permitted calls and reports their outcomes. Policy decisions and step outcomes are both recorded in one append-only event log.\n\nAfter an interruption, the agent starts its handler from the top. Steps with recorded outcomes return those outcomes instead of executing again. A crash can also leave a tool with no recorded outcome. Tools marked safe_to_retry run again, and tools marked at_most_once fail as indeterminate. How the agent handles an indeterminate step is up to its implementation.\n\nThere are Python and TypeScript SDKs, and the repo includes examples using LangChain, CrewAI, Pydantic AI, Vercel AI SDK, and Mastra.\n\nRebuno is free to self-host and released under the MIT licensed.\n\nI'd be interested in hearing how others are running or operating agents in production.\n\nBlog post with diagrams: [https://rebuno.io/blog/introducing-rebuno](https://rebuno.io/blog/introducing-rebuno)\n\nGetting started: [https://docs.rebuno.io/getting-started](https://docs.rebuno.io/getting-started)\n\nComments URL: [https://news.ycombinator.com/item?id=49699591](https://news.ycombinator.com/item?id=49699591)\n\nPoints: 1\n\n# Comments: 0", "url": "https://wpnews.pro/news/show-hn-rebuno-an-open-source-runtime-for-production-agents", "canonical_source": "https://github.com/rebuno/rebuno", "published_at": "2026-09-14 16:29:39+00:00", "updated_at": "2026-09-14 16:56:56.566711+00:00", "lang": "en", "topics": ["ai-agents", "ai-infrastructure", "ai-tools", "developer-tools", "ai-safety"], "entities": ["Rebuno", "Postgres", "LangChain", "CrewAI", "Pydantic AI", "Vercel AI SDK", "Mastra"], "alternates": {"html": "https://wpnews.pro/news/show-hn-rebuno-an-open-source-runtime-for-production-agents", "markdown": "https://wpnews.pro/news/show-hn-rebuno-an-open-source-runtime-for-production-agents.md", "text": "https://wpnews.pro/news/show-hn-rebuno-an-open-source-runtime-for-production-agents.txt", "jsonld": "https://wpnews.pro/news/show-hn-rebuno-an-open-source-runtime-for-production-agents.jsonld"}}