# tbphp/gpt-load

> Self-hosted AI gateway that unifies multiple channels and credentials (API keys and subscriptions) behind a single entry point with scheduling, failover, and request logs.

- Magnitude: 1.1 out of 10 — Steady
- Stars: 7,172 total · +1 star measured 2026-10-27, 00:41–10:16 UTC, ≈ 3 by evening
- Star trust: star growth looks organic
- Category: DevOps & infrastructure · Language: Go · License: MIT · Created: 2025-06-06 · Last push: 2026-10-27
- GitHub: https://github.com/tbphp/gpt-load · Homepage: https://www.gpt-load.com · Page: https://gitnova.dev/en/r/tbphp/gpt-load

## Useful for

- Route OpenAI, Anthropic, and Gemini through one base URL and AccessKey
- Configure scheduling and cooldown across multiple API keys of one provider
- Track token usage and cost estimates per group in the web UI

## Why it’s here

- Star-counter measurements on 2026-10-27 (UTC), 00:41–10:16: 7171 → 7172 stars (+1). This is the change over that interval.
- Estimated end-of-day forecast: about +3 stars, using observed gains and the previous day.
- Recent forks include notable developers: @mvanhorn (5,750 followers).

## Star trust

Star growth looks organic.

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

## Numbers

- Forks: 796
- Issues and pull requests: 906
- Watchers: 17
- Average over the last week: 4 per day
- Usual pace: 10 per day
- Stars in the last hour (measured): 0
- Latest release: v1.4.14 (2026-10-27)

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

2026-09-30 … 2026-10-29: 7, 8, 9, 2, 6, 5, 2, 9, 6, 14, 8, 4, 6, 5, 13, 34, 15, 4, 8, 3, 9, 8, 3, 3, 1, 3, 4, 1, None, None

## Magnitude by day, last 14 days

10-02 1.4, 10-03 1.3, 10-16 2.2, 10-17 2.0, 10-18 1.3, 10-19 1.6, 10-20 1.4, 10-21 1.7, 10-22 1.8, 10-23 1.2, 10-24 1.3, 10-25 0.8, 10-26 1.3, 10-27 1.1

---

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 2026-10-27 10:19 UTC, updated every 30 minutes.