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.
2,235
repos tracked
175
surfaced this week
194
created < 30d
Python
top language
41 repos
-
🚀 The fast, Pythonic way to build MCP servers and clients.
-
A high-throughput and memory-efficient inference and serving engine for LLMs
-
A library of experiments using frontier LLMs/VLMs for robotics tasks, currently focusing on GPT-6 Astra.
-
Implement a reasoning LLM in PyTorch from scratch, step by step
-
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
-
A high-throughput and memory-efficient inference and serving engine for LLMs
-
A high-throughput and memory-efficient inference and serving engine for LLMs
-
RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink
-
[SIGMOD'27] Easy Data Preparation with latest LLMs-based Operators and Pipelines.
-
Assorted useful tools, almost entirely generated using LLMs
-
Data model and surgery toolkit for dialogs and notebooks
-
A MCP server that gives LLMs direct access to the AT Protocol ecosystem, enabling seamless interaction with Bluesky and other AT Protocol-based social networks.
-
Access large language models from the command-line
-
List of papers on hallucination detection in LLMs.
-
End-to-end project training and building AI models / LLMs to detect AI-written text
-
LLM Architecture Gallery source data
-
An open source agent microharness featuring persistent agency and recursive LLMs. Of bash, by bash, for bash; it's shells all the way down.
-
structured outputs for llms
-
~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, 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.
-
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
-
Automatic evals for LLMs
-
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
-
A cosy home for your LLMs.
-
Ongoing research project for code&math LLMs
-
Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
-
Mellea is a library for writing generative programs.
-
Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots.
-
Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUs
-
Finetune Llama 4, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory! 🦥
-
Transform developer documentation to clean Markdown
-
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. ACM Computing Surveys, 2026.
-
★ 132 prinz-ai/prinzbenchprinzbench is a private benchmark that ranks LLMs based on their ability to conduct legal research and analysis and locate obscure publicly available information online.
-
Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production patterns.
-
TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.
-
Arctic Training and Inference Platform
-
VirtueBench V2: Multi-dimensional virtue evaluation benchmark for LLMs with tripartite and Ignatian temptation models
-
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends