agents-go
What it is
A Go-native agent workbench that runs agents and workflows in local sandboxes with tool approval gates. It provides a single binary for local execution, an embeddable SDK for Go applications, and features for tracing, replaying, and forking agent sessions.
The problem it solves
Lack of a local-first, Go-native tool for running, sandboxing, and debugging AI agents with transparent traces and replay capabilities.
What you could use it for
- Running local AI agents with sandboxed code execution
- Debugging agent behavior via trace inspection and replay
- Building custom Go applications with an embedded agent SDK
- Managing multi-agent workflows with sub-tasks and cron triggers
Read the source ↗Back to the library →
Summary written by an AI model from the source; check the source before you rely on it.