# experientiallabs/experiential

> Open-source gateway and router for agent LLM workflows: one OpenAI-compatible API over hosted, BYOK and local models with access and budget control, plus training a custom router or model from your traffic.

- Magnitude: 2.8 out of 10 — Steady
- Stars: 13,687 total · +0 stars measured 2026-10-29, 00:05–05:44 UTC, ≈ 121 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: Apache-2.0 · Created: 2026-06-24 · Last push: 2026-10-29
- GitHub: https://github.com/experientiallabs/experiential · Homepage: https://experientiallabs.ai · Page: https://gitnova.dev/en/r/experientiallabs/experiential

## Useful for

- Run a local OpenAI-compatible gateway and point Claude Code or Cursor requests at it
- Restrict which agents and users can use which models and cap their spend
- Build a router from your OTel traces and fine-tune a model for quality, speed and cost

## Why it’s here

- Star-counter measurements on 2026-10-29 (UTC), 00:05–05:44: 13802 → 13687 stars (-115). This is the change over that interval.
- Estimated end-of-day forecast: about +121 stars, using observed gains and the previous day.
- Interest is fading: the two-day pace is 54% of the previous week and a half.
- About 6 forks a day — people are taking the code.

## Star trust

Star growth looks organic.
- Hardly anyone watches for updates: 15 watchers for 13,687 stars.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 278
- Issues and pull requests: 1,275
- Watchers: 15
- Average over the last week: 493 per day
- Usual pace: 92 per day
- Stars in the last hour (measured): 10
- Latest release: v0.7.223 (2026-10-28)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: 77, 128, 363, 656, 331, 287, 188, 128, 141, 197, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 70, 227, 240, 465, 1183, 785, 431, 252, 212, 0

## Magnitude by day, last 14 days

10-06 3.4, 10-07 3.0, 10-08 2.7, 10-09 3.0, 10-10 3.0, 10-21 2.1, 10-22 3.6, 10-23 3.8, 10-24 4.8, 10-25 5.4, 10-26 5.0, 10-27 4.1, 10-28 3.4, 10-29 2.9

## Similar by description

1. **eliasbiondo/antirion** — 1.9 · Peaking · DevOps & infrastructure · Rust · +10 stars measured 2026-10-29, 00:08–05:47 UTC, ≈ 38 by evening
   Open-source AI gateway in Rust: a single binary with a built-in console that routes, secures, budgets and observes LLM calls across OpenAI, Anthropic, Gemini, Bedrock and more.
   Full card: https://gitnova.dev/en/r/eliasbiondo/antirion.md
2. **mozilla-ai/otari** — 1.2 · Steady · Language models · Python · +1 star measured 2026-10-29, 00:11–05:49 UTC, ≈ 6 by evening
   A self-hosted OpenAI-compatible gateway to 40+ LLM providers: one endpoint, virtual keys, budgets, and usage tracking. It sits between apps and providers, checks budgets before dispatch, and records usage afterwards.
   Full card: https://gitnova.dev/en/r/mozilla-ai/otari.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-29 05:52 UTC, updated every 30 minutes.