diegosouzapw/OmniRoute
koala73/worldmonitor
stablyai/orca
earendil-works/pi
safishamsi/graphify Collection
LLM Inference Engines
The LLM Inference Engines collection tracks 15 curated open-source projects, 12 of them live on TrendingRepo right now — ranked by a cross-source momentum score blending GitHub star velocity with mentions on Hacker News, X, Bluesky, Product Hunt and Dev.to.
Live · top 15 repos · sorted by momentum across 24H
LIVE · 21m| # | Repository | Stars | 24h | 7d | 30d | Trend | Mentions | Actions |
|---|---|---|---|---|---|---|---|---|
| 01 |  open-webui/open-webui User-friendly AI Interface (Supports Ollama, OpenAI API, ...) | 146.7K | +76+0.1% | +830+0.6% | +4K+2.8% |     live on Hacker News | ||
| 02 |  ollama/ollama Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. | 176.9K | +109+0.1% | +469+0.3% | +2.4K+1.3% |  live on Hacker News | ||
| 03 |  kvcache-ai/ktransformers A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations | 19K | +11+0.1% | +1K+5.8% | +1.7K+9.8% | live on X / Twitter | ||
| 04 |  ggml-org/llama.cpp LLM inference in C/C++ | 121.6K | +12+0.0% | +676+0.6% | +3.7K+3.1% | live on Hacker News | ||
| 05 |  vllm-project/vllm A high-throughput and memory-efficient inference and serving engine for LLMs | 87.1K | +10+0.0% | +516+0.6% | +2.9K+3.5% | live on X / Twitter | ||
| 06 |  mudler/LocalAI LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required. | 47.8K | +66+0.1% | +205+0.4% | +734+1.6% | live on X / Twitter | ||
| 07 |  EricLBuehler/mistral.rs Fast, flexible LLM inference | 7.5K | +6+0.1% | +29+0.4% | +166+2.3% | live on X / Twitter | ||
| 08 |  sgl-project/sglang SGLang is a high-performance serving framework for large language models and multimodal models. | 30.7K | +2+0.0% | +258+0.8% | +1.2K+4.1% | live on Dev.to | ||
| 09 |  mlc-ai/web-llm High-performance In-browser LLM Inference Engine | 18.5K | +5+0.0% | +44+0.2% | +187+1.0% | live on X / Twitter | ||
| 10 |  nomic-ai/gpt4all GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use. | 77.4K | +2+0.0% | +14+0.0% | +114+0.1% | live on Dev.to | ||
| 11 |  lm-sys/FastChat An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena. | 39.5K | -1-0.0% | +10+0.0% | +59+0.1% | | ||
| 12 |  huggingface/text-generation-inference Large Language Model Text Generation Inference | 10.9K | — | +7+0.1% | +26+0.2% | | ||
| 13 | jmorganca/ollama-js No description published. | 0 | — | — | — | | ||
| 14 | Mozilla-Ocho/llamafile No description published. | 0 | — | — | — | | ||
| 15 | oobabooga/text-generation-webui No description published. | 0 | — | — | — | |