Agent Enforcer Open Beta: Enforce the Quality of Agent Code

Hi!

I’ve finally managed to synthesize my scattered scripts into Agent Enforcer.

Theoretically, it’s supposed to support Python, Kotlin, C#, and JS/TS. But personally, I’ve only tested it on Python. By the way, I have no idea what range of language versions it supports :smiling_face_with_sunglasses:

I also haven’t had the time to double-check all the rules the Enforcer uses for the supported languages. But by default, it should check the code pretty strictly.

Despite the high test coverage, the project is probably undertested manually. I’m really in need of some feedback. And overall, the tool should be extremely useful. I’ve already seen native ads on x.com for similar paid tools – but here you have a donationware orchestrator that works right out of the box. Especially if you’re too much of a “vibe coder” XD.

I’d love to hear your feedback and ideas here and on GitHub. If you share it somewhere else, I’ll be twice as happy.


P.S. It feels a bit awkward to write this, but if the tool genuinely saves you time and sanity, I’d be grateful if you’d check out the sponsorship section at the bottom of the Readme.

@condor Gemini 2.5 Pro cannot connect to the provider when Agent Enforcer is enabled as an MCP tool. It would be great if someone from the team could help with this.

1 Like

Yes the team is already looking into Gemini 2.5 Pro with MCPs.

Could you post a Request ID with privacy disabled so we can look into the details of your case?

Oh, I missed. One minute…

1 Like

About the Gemini I’m whining here:

This last post is linked to MCP? If thats the case could you add that info there there so I can send the whole thread as report.

Though I could also add it here, probably better, please let me know.

Done

1 Like

Ok filed the report, will update on the other thread about the Gemini MCP issue when I have more info.