If you don't run your own LLM proxy, how do you even know whats going on?

Re:If you don't run your own LLM proxy, how do you even know... by rao-v on Sunday October 18, 2026 @11:49PM (#50148177)

What’s the best way to pull (ie archive) and search these across a few harnesses? I remember seeing a project or two trying to standardize them, but can’t find anything that seems to be a good sensible solution

[ Parent | on HN ]

Re:If you don't run your own LLM proxy, how do you even know... by diurnalist on Sunday October 18, 2026 @11:58PM (#50148223)

I've used https://github.com/kenn-io/agentsview and found it to be quite sensible. Main friction point for me is I want it to be easier to extend.

[ Parent | on HN ]

Re:If you don't run your own LLM proxy, how do you even know... by rao-v on Monday October 19, 2026 @12:39AM (#50148434)

Thanks will check it out

[ Parent | on HN ]

Re:If you don't run your own LLM proxy, how do you even know... by throwaway27448 on Monday October 19, 2026 @12:09AM (#50148288)

Don't install a second harness. You only need one to begin with!

[ Parent | on HN ]

Re:If you don't run your own LLM proxy, how do you even know... by rao-v on Monday October 19, 2026 @12:41AM (#50148448)

I mean Claude and codex both have their uses for me and I’m one of the deranged running my own inferencing box with Qwen Next so I need pi for it.

[ Parent | on HN ]

Re:If you don't run your own LLM proxy, how do you even know... by Implicated on Monday October 19, 2026 @12:25AM (#50148362)

Ask claude to do it end to end, then write a solution that fits your needs from it's experience with you driving it.

I did exactly this - probably the single most valuable piece of software I've "written". It's the backbone of every piece of code coming out of any agent under my control (via MCP toolset).

[ Parent | on HN ]

Re:If you don't run your own LLM proxy, how do you even know... by rao-v on Monday October 19, 2026 @12:40AM (#50148439)

That’s like half a day to get to sensible useful defaults that everybody needs. Any chance you’d be up to push what you got to git?

[ Parent | on HN ]

Re:If you don't run your own LLM proxy, how do you even know... by john01dav on Monday October 19, 2026 @12:49AM (#50148490)

I think that T3 Code tries to do something like this, though I do not use it and have not used it, and I have heard good things about this.

[ Parent | on HN ]

Re:If you don't run your own LLM proxy, how do you even know... by collin128 on Monday October 19, 2026 @02:07AM (#50148923)

I've been using https://getmaestro.ai/ for 3 months now and I like it. Good founders.

[ Parent | on HN ]

Re:If you don't run your own LLM proxy, how do you even know... by rane on Monday October 19, 2026 @02:56AM (#50149201)

No archival, but simply for searching https://github.com/raine/claude-history

[ Parent | on HN ]

Re:If you don't run your own LLM proxy, how do you even know... by hetspookjee on Monday October 19, 2026 @06:07AM (#50150490)

Mlflow does it pretty nice including session gathering and optional data enrichment (eg what files were touched, what model was used, git remote). We use these session IDs for commenting on issues and stories touched by AI for context tracing.

I just wrapped around the Mlflow setup to make this simple CLI helper to set it up. Ofcourse the name suggests only Claude but it’s Codex, CC, GHCP and Agy. https://pypi.org/project/claudetracing/

https://github.com/CauchyIO/claudetracing

[ Parent | on HN ]

Re:If you don't run your own LLM proxy, how do you even know... by gbdubs on Monday October 19, 2026 @01:27PM (#50155246)

I'm the author of Pharos, a tool for just this use case! I've been using it extensively for personal use

https://grady.dev/projects/pharos/

[ Parent | on HN ]