Dev
GitHub repos gaining traction - what high-signal users are starring and what's climbing the board, captured daily and enriched from GitHub. Raw material for spotting new tech and patterns worth building on.
3,195
repos tracked
105
surfaced this week
193
created < 30d
Python
top language
49 repos
-
LLM inference in C/C++
-
A high-throughput and memory-efficient inference and serving engine for LLMs
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
Pi coding agent extension: llama.cpp provider with dynamic model + context window discovery
-
llama.cpp's official website
-
Semantic search in one SQLite file. No model, no server at query time.
-
VS Code extension for LLM-assisted code/text completion
-
Search your computer by what's in your files: photos, PDFs, documents, recordings, videos and code. On-device on Mac, Windows and Linux, built on Google DeepMind's EmbeddingGemma 2.
-
Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
-
Windows Llama App Companion
-
llama.cpp's official website
-
A cosy home for your LLMs.
-
LLM inference in C/C++
-
LLM inference in C/C++
-
llama.cpp's official website
-
LLM inference in C/C++
-
LLM inference in C/C++
-
Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)
-
A multi-framework neural network compiler lowering PyTorch, JAX, Flax, and Keras models to portable, high-performance GGML execution
-
ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.
-
Build and install script for llama.app
-
Vim plugin for LLM-assisted code/text completion
-
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
-
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
-
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
-
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
-
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
-
LLM inference in C/C++
-
LLM inference in C/C++
-
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
-
SOTA Open Source TTS
-
PyTorch native quantization for training and inference
-
Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots.
-
Finetune Llama 4, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory! 🦥
-
Port of Facebook's LLaMA model in C/C++
-
Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. Windows, iOS testflight! Android, Linux waitlist open! A local Wispr Flow alternative. Follow https://x.com/fluidvoiceapp for more
-
Foundation Models API for llama.cpp
-
Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights.
-
[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
-
TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.
-
LLM inference in C/C++
-
Throwaway staging: validate CUDA 13.3 prebuilt build leg
-
Port of Facebook's LLaMA model in C/C++
-
LLM inference in C/C++
-
LLM inference in C/C++
-
Fun-ASR speech recognition models, with native Hugging Face Transformers support for Fun-ASR-Nano and separate FunASR, vLLM and llama.cpp deployment paths.
-
LLM inference in C/C++
-
A fast, helpful, and open-source document parser