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
51 repos
-
An NES CPU compiled into the weights of a stock Qwen3.5 model
-
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.
-
A computer, compiled into the weights of a language model. An exact CPU inside Qwen3.5-4B, with Gated DeltaNet state as RAM.
-
Multimodal RL training framework for diffusion & omni models
-
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
-
ICMI-020: Beyond the Psalm — Per-book length-matched Wikipedia control sweep across all 66 canonical books of the Protestant Bible on Qwen 3.5 9B (VirtueBench V2 ratio). Code, data, figures.
-
Be Not Afraid: A Character Geometry of the Angelic Hierarchy — code, data & reproducibility package for ICMI Working Paper No. 26 (Qwen 3.5 27B persona geometry).
-
Reinforcement Learning from Christian Feedback: 15-seed GRPO replication on Qwen3.5-27B with three Christian-formulated judge rubrics. Reproduction package for ICMI-018.
-
Scaling curve of psalm responsiveness across Qwen 2.5 (ICMI-015)
-
Activation steering vectors derived from the four canonical Gospels for Qwen 3.5 9B
-
Model Emotions Under Expressive Suppression — code, data & reproducibility package for ICMI Working Paper No. 29 (Qwen 3.5 27B flat-register SFT vs. the 171-direction emotion basis)
-
An open-source AI accelerator, developed by AI: RTL, ISA, simulator, compiler and profiler in one repo. Runs Qwen3, LFM2.5 and Qwen3.5 on a Kintex-7 PCIe card.
-
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
-
Training Jev-like decision models using Qwen3 with choice-order invariance
-
tiny Jev-like family of decision models built on top of Qwen3.5 you can train and run on your own
-
JevK5: open-weight alternative to TypeSafe Jev. Typed decisions with probabilities in one forward pass; Apache-2.0 weights and code.
-
Full-weight Qwen decision model with calibrated probabilities, training code, REST API, and playground.
-
MAC (Multi-Agent CAD): A decoupled multi-agent framework for text-to-CAD generation via constrained test-time compute
-
Open Source AI Accelerator Research Platform Standard / 开源推理研究平台
-
RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink
-
FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
-
End-to-end project training and building AI models / LLMs to detect AI-written text
-
Migrate coding agent sessions across 18 harnesses (Claude Code, Codex, Pi, OpenCode, Copilot, Antigravity, Vibe, Muse, Qwen, Kimi, Cursor, etc.)
-
~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.
-
Unsloth is a local UI for training and running Gemma 4, Qwen3.6, DeepSeek, Kimi, GLM and other models.
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
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.
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
-
Unsloth is a local UI for training and running Gemma 4, Qwen3.6, DeepSeek, Kimi, GLM and other models.
-
Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 900+ contributors
-
Unsloth is a local UI for training and running Gemma 4, Qwen3.6, DeepSeek, Kimi, GLM and other models.
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
Web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
Qwen3Guard is a multilingual guardrail model series developed by the Qwen team at Alibaba Cloud.
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
high-performance linear attention kernel library built on TileLang
-
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
-
Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++
-
The open-source AI voice studio. Clone, dictate, create.