We're building and deploying agents faster than normal SaaS because there are so many frameworks. I talked to teams seeing weird problems with their agents after they are in production.
Tool failure, backend latency, hallucinations, known prompt injection etc.
Sharing EvalMonkey, so you can test the agent and save the frustration later when tracking a single trace.
Comes with CLI for Claude Code/Cursor as well.
I'm curious about the token usage when it scans across multiple repositories to finding similar methods. As our code grows so fast, is it sustainable ?
Are you saying that the partner program takes time and not worth integrating ? I was planning to gather data of users via LinkedIn oauth, haven't started it, but happy to hear your experience
I really like tracking things. And with recent changes in agentic coding, these harnesses are missed. Though I was exploring Traycer AI for the use case, would you say this GitHub repo provides same stuff for free ?