TYtyre·Aug 28, 2026
Looks like first PR is June 24th: https://github.com/experientiallabs/experiential/pull/1
So, two months. Still impressive!
In Show HN: We built open OpenRouter that turns usage into a better modelexperientiallabs
experiential
Python2026–2026
experientiallabs / experiential
experiential
Experiential is the open source, zero markup gateway for BYOK, self-hosted and 1000+ marketplace models. It learns from your traffic to cut costs, recommend better models, and train a specialized model you own.
2Distinct people
2Mentions
0Explicit recommenders
16.8KGitHub stars
What to know before exploring
What it is
Experiential is the open source, zero markup gateway for BYOK, self-hosted and 1000+ marketplace models. It learns from your traffic to cut costs, recommend better models, and train a specialized model you own.
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:56:07 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by hour2 dated mentions
Observed mentions: 2026-08-27 21:18:35 UTC to 2026-08-28 05:23:10 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Aug 27, 21:00 | 2026-08-27 21:00:00 UTC | 2026-08-27 22:00:00 UTC | 1 | 1 | 0 |
| Aug 27, 22:00 | 2026-08-27 22:00:00 UTC | 2026-08-27 23:00:00 UTC | 0 | 0 | 0 |
| Aug 27, 23:00 | 2026-08-27 23:00:00 UTC | 2026-08-28 00:00:00 UTC | 0 | 0 | 0 |
| Aug 28, 00:00 | 2026-08-28 00:00:00 UTC | 2026-08-28 01:00:00 UTC | 0 | 0 | 0 |
| Aug 28, 01:00 | 2026-08-28 01:00:00 UTC | 2026-08-28 02:00:00 UTC | 0 | 0 | 0 |
| Aug 28, 02:00 | 2026-08-28 02:00:00 UTC | 2026-08-28 03:00:00 UTC | 0 | 0 | 0 |
| Aug 28, 03:00 | 2026-08-28 03:00:00 UTC | 2026-08-28 04:00:00 UTC | 0 | 0 | 0 |
| Aug 28, 04:00 | 2026-08-28 04:00:00 UTC | 2026-08-28 05:00:00 UTC | 0 | 0 | 0 |
| Aug 28, 05:00 | 2026-08-28 05:00:00 UTC | 2026-08-28 06:00:00 UTC | 1 | 0 | 1 |
What Hacker News says
2 sourcesShow HN: We built open OpenRouter that turns usage into a better model
Hi HN, we built an open source model gateway. It's a single place to manage our own self hosted, frontier, and open source models in one place.
It’s is rust native, built for concurrency, and implements all the config quirks across models and providers (streaming formats, tool calls, model parameters, rate limits, and different error behavior).
The gateway adds under 1 ms for BYOK requests and under 2 ms when Experiential supplies the provider key. It has every major inference provider, and 1000+ models refreshed daily via a codex agent that opens a PR.
Compared to other similar projects we’re open source, take no markup, allow you to mix local models with a marketplace, and use your traffic to (opt in) train you a model. Simple routing doesn’t warrant a 10% token markup.
The way we do this is given standardized OTel traces, we mine repre
Read the rest
sentative real tasks, use text world models to simulate rollouts for various models, apply an LLM judge, and fit a nearest neighbor classifier on top of an embedding of a prompt to decide the optimal model for each request. Usually this can map out a better pareto curve on cost/quality than just calling single models but it’s not perfect.
Using these simulations we can also do things like suggesting cache hit optimizations, new model suggestions, and training models.
It’s open source, so you can deploy it on your own infrastructure, use our hosted version with 0 markup, or read how we design for maximum availability on our website.