Show HN: RunAgent; Multi-Framework Agent Deployment and Rust,Go,JS SDKs(+others)

[sawradip]

RunAgent eliminates the complexity of AI agent deployment across different frameworks and languages.

Today's developers face deployment nightmares with fragmented frameworks (LlamaIndex, LangChain, LangGraph, CrewAI, Letta, Agno, etc.) each requiring different deployment processes, creating unnecessary friction.

The Solution: Like MCP (Model Context Protocol), RunAgent provides a standardized approach to agent deployment. Developers simply provide a config file and their agent code - RunAgent handles the rest with REST API and WebSocket (Streaming and non streaming). Our open-source platform supports any framework through our agentic framework agnostic deployment approach, accessible via SDKs (Python, JavaScript/TypeScript, Go, Rust and many more coming soon). So our goal is the AI agents for every developer, in every language.

RunAgent is MCP for Agent Deployment.

[adewba]

What are the actual pain points you want to solve? Is this deployment part or is this agentic framework agnostic? Like my theory is if and only if you guys can pull this off just like mcp server as you told in the description, {for example I am a rust developer}. Cool to see this in here. So suppose I am building something where I need an agent. Suppose I got that agent (build by open source community) with your agent file structure, then i can use it and deploy it and then can use with rust sdk. Now this is something. Otherwise it wont create that value. But I guess it is a interesting concept.

[sawradip]

Hello,

This is Sawradip. one of the core maintainers of RunAgent.

Our team faced this problem, wherever we had to deploy agents, and use them in production application(from different language, like from C# unity games, or embedded Rust APP, or Go server backend).

* Building repetitive REST-api, and streaming mechanisms. * Cross language streaming serialisation * monitoring of Agent invocation

Specially, enabling streaming (cross-language) was a huge hassle. So, we started RunAgent. Hopefully this tool will be useful.

Thanks to the community, and want to give back some convenience.

[Radeen1]

Guys this is really a very unique approach. Just one thing I am confused about, as far as I understand, this is like vercel but for ai agent with multi agentic framework. Is it correct?

[Radeen1]

This is really cool concept. So it means it is a open source collaboration just like MCP but for deployment of agents of different frameworks right?

[tomim]

this a much needed solution!! Love the idea of a standardized approach to agent deployment:)

[Radeen1]

But question is how they are standardizing it? I understand the multi framework approach, but like if anyone is a javascript developer, he doesn't know about python. How he can write that agent file. That's a question where I am confused.