Show HN: How to build and self-host a code review agent

Hey HN,

I've had a side-project that I've slowly ticked away at over the last year called Tilde. Tilde is a harness SDK platform - I've tried to take the best things of OpenClaw, Hermes & other harnesses and decompose them and make them available as cloud API building blocks.

You can use Tilde to create AI agents for your use case, fast and self-host the agent's yourself.

The documentation (and attached blog post) leave a lot to be desired in terms of technical documentation but hopefully the attached git repo does a good job of showcasing the API.

https://github.com/trytilde/examples

▲

hqr 2 days ago | parent | next [-]

There is an mcp server named Reticle to verify agent's coding work. You should take a look at that too, will be helpful to make your architecture even more better.

	▲	solsol94 2 days ago \| parent \| next [-]
		Awesome! I’ll take a look, thanks
	▲	genshro 2 days ago \| parent \| prev [-]
		Thank you ill try :>

▲

vivzkestrel 2 days ago | parent | prev [-]

i would love to see how to build one that uses open source models instead of anthropic or openai

▲

lukasco a day ago | parent [-]

Do you mean using open source models via something like OpenRouter, or do you mean self-hosting the models?

That self-hosting bit is definitely something I'm interested in, but it still seems very fiddly (in general).

I've had good results just plugging in models into Claude Code, however (though not self-hosted).

	▲	vivzkestrel a day ago \| parent [-]
		- well to be honest i was gonna say something like lm-studio but yea self hosting counts - basically anything that is not frontier lab