sawradip
These are some great ideas, and will be added.
This is a fun (multi-) weekend project after discovering the Gandalf game, by Lakera, and seeing that things and techniques of beating the LLMs have progressed so much in the last year alone.
So I created Genie, hope you guys enjoy cracking the code as much as I enjoyed making it.
I created a set of SDKs for using any AI Agent from any Programming Language
Show HN: AI code reviewer with Python agent called from Rust, streaming works
Built an AI code reviewer using Letta (Python) that I can call natively from Rust applications.The interesting part: real-time streaming works perfectly across the language boundary with zero hassle using RunAgent.The agent runs in Python with persistent memory, leverages the best in house agentic memory management with Letta (Pythonic AI agent framework), and my rust code just uses it (kinda)...
This is Sawradip. one of the core maintainers of RunAgent.
Our team faced this problem, whereever 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 repeatative REST-api, and streaming mechanisms. * Cross langugae streaming serialization * monitoring of Agent invocation
Specially, enabling streaming (cross-langugae) was a huge hassle. So, we started RunAgent.Hopefully this tool will be useful.
Thanks to the community, and want to give back some convinience.
Show HN: RunAgent; Multi-Framework Agent Deployment and Rust,Go,JS SDKs(+others)
https://github.com/runagent-dev/runagent
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...