# smg-project/smg

> Engine-agnostic LLM gateway in Rust that routes requests across self-hosted inference engines (vLLM, SGLang, TensorRT-LLM) and cloud providers behind one OpenAI/Anthropic-compatible API.

- Magnitude: 1.5 out of 10 — Steady
- Stars: 628 total · +5 stars measured 2026-10-19, 10:41–13:09 UTC, ≈ 9 by evening
- Star trust: star growth looks organic
- Category: DevOps & infrastructure · Language: Rust · License: Apache-2.0 · Created: 2025-11-22 · Last push: 2026-10-19
- GitHub: https://github.com/smg-project/smg · Homepage: https://lightseek.org/smg · Page: https://gitnova.dev/en/r/smg-project/smg

## Useful for

- Balance traffic across multiple vLLM or SGLang workers with cache-aware routing
- Expose one OpenAI-compatible endpoint in front of OpenAI, Anthropic and Gemini
- Add API-key auth, rate limiting and Prometheus metrics to existing inference engines

## Why it’s here

- Star-counter measurements on 2026-10-19 (UTC), 10:41–13:09: 623 → 628 stars (+5). This is the change over that interval.
- Estimated end-of-day forecast: about +9 stars, using observed gains and the previous day.
- GitHub Trending Rust today: #3, +8 stars.

## 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: 195
- Issues and pull requests: 3,972
- Watchers: 4
- Average over the last week: 8 per day
- Usual pace: 2 per day
- Stars in the last hour (measured): 1
- Latest release: v1.13.0 (2026-10-15)

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

2026-09-20 … 2026-10-19: 2, 1, 4, 1, 0, 0, 0, 1, 2, 5, 0, 1, 2, 0, 2, 1, 1, 5, 2, 2, 0, 3, 4, 2, 5, 7, 21, 7, 7, 5

## Spotted in now

- GitHub Trending Rust today: #3, +8 stars

## Similar by description

1. **higress-group/higress** — 1.1 · Steady · DevOps & infrastructure · Go · +2 stars measured 2026-10-19, 00:13–13:11 UTC, ≈ 4 by evening
   Cloud-native API gateway built on Istio and Envoy, extendable with Wasm plugins, providing AI gateway, MCP server hosting, ingress controller and microservice gateway features.
   Full card: https://gitnova.dev/en/r/higress-group/higress.md
2. **QuantumNous/new-api** — 3.5 · Steady · Language models · Go · +75 stars measured 2026-10-19, 00:08–13:00 UTC, ≈ 123 by evening
   Self-hosted AI gateway that aggregates multiple LLM providers behind a unified OpenAI-, Claude-, or Gemini-compatible API with routing, access, and cost management.
   Full card: https://gitnova.dev/en/r/QuantumNous/new-api.md
3. **llm-d/llm-d-router** — 1.1 · Quiet · DevOps & infrastructure · Go · +1 star measured 2026-10-19, 00:12–13:11 UTC, ≈ 2 by evening
   Intelligent entry point for LLM inference traffic in Kubernetes: load- and prefix-cache-aware routing, request prioritization, and flow control. Runs in Standalone mode with Envoy or via the Kubernetes Gateway API.
   Full card: https://gitnova.dev/en/r/llm-d/llm-d-router.md
4. **diegosouzapw/OmniRoute** — 4.5 · Steady · AI agents · TypeScript · +185 stars measured 2026-10-19, 00:07–13:00 UTC, ≈ 354 by evening
   Gateway to 359 AI providers (150+ free) and 1200+ models through one OpenAI-compatible endpoint with quota-aware auto-fallback and token compression.
   Full card: https://gitnova.dev/en/r/diegosouzapw/OmniRoute.md
5. **maximhq/bifrost** — 2.3 · Steady · Language models · Go · +16 stars measured 2026-10-19, 00:09–13:05 UTC, ≈ 28 by evening
   High-performance Go AI gateway that unifies 23+ LLM providers (OpenAI, Anthropic, Bedrock, etc.) behind a single OpenAI-compatible API with fallbacks, load balancing, and semantic caching.
   Full card: https://gitnova.dev/en/r/maximhq/bifrost.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 2026-10-19 13:14 UTC, updated every 30 minutes.