# incoai/splash

> A local LLM inference engine for Apple silicon, specialized per model: serves OpenAI- and Anthropic-compatible APIs to coding agents on a single Mac.

- Magnitude: 2.0 out of 10 — Steady
- Stars: 1,581 total · +20 stars measured 2026-10-20, 00:28–19:46 UTC, ≈ 24 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: C++ · License: Apache-2.0 · Created: 2026-09-18 · Last push: 2026-10-14
- GitHub: https://github.com/incoai/splash · Homepage: https://inco.ai/blog/splash/ · Page: https://gitnova.dev/en/r/incoai/splash

## Useful for

- Run a local Qwen3.8-27B server and connect a coding agent via splash opencode
- Send a request to /v1/chat/completions from a script using the OpenAI-compatible API
- Cap Metal memory usage with --max-memory when unified memory is tight

## Why it’s here

- Star-counter measurements on 2026-10-20 (UTC), 00:28–19:46: 1561 → 1581 stars (+20). This is the change over that interval.
- Estimated end-of-day forecast: about +24 stars, using observed gains and the previous day.
- The repository is 32 days old and already has 1,581 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: 153
- Issues and pull requests: 520
- Watchers: 17
- Average over the last week: 24 per day
- Usual pace: 34 per day
- Latest release: 1.3.2 (2026-10-14)

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

2026-10-05 … 2026-11-03: 34, 22, 33, 25, 28, 21, 22, 31, 19, 20, 35, 27, 11, 29, 24, 14, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

10-07 1.9, 10-08 2.0, 10-09 2.0, 10-10 1.9, 10-11 1.9, 10-12 2.0, 10-13 2.2, 10-14 1.9, 10-15 2.1, 10-16 2.2, 10-17 2.0, 10-18 1.8, 10-19 2.0, 10-20 2.0

---

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 2026-10-20 19:52 UTC, updated every 30 minutes.