lemonade-sdk/lemonade

lemonade

✅ Recently maintained

Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

6,084Stars
551Forks
+817-day stars

C++ · Apache-2.0 · Last push 2026-11-03

Official repository & installation ↗
amdllamallmllm-inferencelocal-servermistralnpuonnxruntimeqwenopenai-api

GitValue · Value evidence

Unscored · Evidence coverage 0%

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

Star history

2025-09-292026-11-03
View historical data
DateStars
2026-10-055,814
2026-10-065,817
2026-10-075,825
2026-10-085,831
2026-10-095,840
2026-10-105,851
2026-10-115,860
2026-10-125,866
2026-10-135,878
2026-10-145,898
2026-10-155,904
2026-10-165,911
2026-10-175,916
2026-10-185,925
2026-10-195,933
2026-10-205,946
2026-10-215,960
2026-10-225,970
2026-10-235,977
2026-10-245,984
2026-10-255,994
2026-10-266,000
2026-10-276,007
2026-10-286,017
2026-10-296,019
2026-10-306,029
2026-10-316,032
2026-11-016,036
2026-11-026,064
2026-11-036,084

Get the project

git clone https://github.com/lemonade-sdk/lemonade.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.

★ 49,776ollama

Run DeepSeek, Qwen, Gemma and other LLMs locally with one command, plus model management and an API.

★ 185,745vllm

High-throughput, memory-efficient LLM inference and serving engine that lets developers deploy models faster without building serving infrastructure.

★ 96,180