incoai/splash

splash

✅ Recently maintained

A local inference engine for Apple silicon, built around the model.

2,043Stars
196Forks
+1777-day stars

C++ · Apache-2.0 · Last push 2026-10-31

Official repository & installation ↗
apple-siliconcoding-agentsllm-inferencemacosmetalspeculative-decoding

GitValue · Value evidence

Unscored · Evidence coverage 0%

Provisional rubric; documentation and runtime testing are separate. Missing evidence does not imply low value.

Star history

2026-09-142026-11-03
View historical data
DateStars
2026-10-051,217
2026-10-061,239
2026-10-071,272
2026-10-081,297
2026-10-091,325
2026-10-101,346
2026-10-111,368
2026-10-121,399
2026-10-131,418
2026-10-141,438
2026-10-151,472
2026-10-161,499
2026-10-171,510
2026-10-181,539
2026-10-191,562
2026-10-201,615
2026-10-211,708
2026-10-221,740
2026-10-231,776
2026-10-241,790
2026-10-251,820
2026-10-261,852
2026-10-271,891
2026-10-281,915
2026-10-291,945
2026-10-301,976
2026-10-311,991
2026-11-012,012
2026-11-022,016
2026-11-032,043

Get the project

git clone https://github.com/incoai/splash.git

Cloning downloads the source. For dependencies and installation, follow the project README.

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.

nanobot

Lightweight swarm intelligence experimental platform for micro-agents.

★ 49,776omlx

LLM inference server for Apple Silicon with continuous batching and SSD caching, managed from the macOS menu bar.

★ 23,304