VoltAgent is an open source TypeScript framework for building and orchestrating AI agents, with built-in observability. Escape the limitations of no-code builders and the complexity of starting from scratch.
This is brilliant @omeraplak & @necatiozmen . Looking at other agentic products (mainly coding agents) I have explored last few months, VoltAgent is bringing lots of disruptive thoughts ahead of their time. This is tremendous! ๐๐๐
Do you have plans to add features for defining custom providers for offline models run locally. For example, like for models running in LM Studio ?
Report
The pitch is perfect. I am about to start s client's project with dify or crewai
Report
Thanks for building this! Looking forward to trying out workflows when it's released
The visual observability piece is what caught my eye. I use n8n for some of my automation workflows and the ability to see what's happening at each step is invaluable. Bringing that same visibility to code-first agent frameworks is a smart move. How are you handling tracing for deeply nested agent chains?
Replies
Deez Deelz
Can we hook the framework into external observability tools?
VoltAgent: OpenSource AI Agent Framework
@ege_aytinย
Yes, you can. we already have an integration for Langfuse, and more are on the way.
I'm curious about TypeScript frameworks! ๐
VoltAgent: OpenSource AI Agent Framework
@shenjunย Then weโre officially welcome! ๐
This is brilliant @omeraplak & @necatiozmen . Looking at other agentic products (mainly coding agents) I have explored last few months, VoltAgent is bringing lots of disruptive thoughts ahead of their time. This is tremendous! ๐๐๐
Do you have plans to add features for defining custom providers for offline models run locally. For example, like for models running in LM Studio ?
The pitch is perfect. I am about to start s client's project with dify or crewai
Thanks for building this! Looking forward to trying out workflows when it's released
ClawSecure
The visual observability piece is what caught my eye. I use n8n for some of my automation workflows and the ability to see what's happening at each step is invaluable. Bringing that same visibility to code-first agent frameworks is a smart move. How are you handling tracing for deeply nested agent chains?