MakazhanAlpamys/Soup
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
Language:Python
Total stars: 6396
#python
#cli, #consumergpu, #dpo, #finetuning, #gguf, #huggingface, #llm, #llmops, #localai, #localllm, #lora, #lowvram, #machinelearning, #ollama, #peft, #python, #pytorch, #qlora, #sft, #transformers

victordibia/designing-multiagent-systems
Building LLM-Enabled Multi Agent Applications from Scratch
Language:Python
Total stars: 1268
#python
#agents, #autogen, #generativeai, #largelanguagemodels, #multiagentsystems

huawei-bayerlab/marigold-v2
Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation
Language:Python
Total stars: 635
#python

DefiLeoo/YOINK

Language:Python
Total stars: 366
#python

grqz/grqz
Trying some new stuff here
Language:Python
Total stars: 494
#python

aldegad/sprite-gen
Generate clean 2D game sprites & animation atlases — component-row pipeline: state rows, alpha cleanup, frame extraction, runtime atlases. Codex/Claude skill.
Language:Python
Total stars: 1478
#python
#2dgame, #aitools, #claudecode, #codex, #gamedev, #gamedev, #pixelart, #spritegeneration, #spritesheet

bojieli/ai-infra-book
《深入理解 AI Infra：量化分析与系统设计》（李博杰 著）开源书稿：从硬件约束和模型架构出发，量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验
Language:Python
Total stars: 2403
#python
#accelerator, #aiinfra, #aiinfrastructure, #book, #datacenternetwork, #deepseek, #distributedsystems, #gpu, #kvcache, #llm, #llminference, #llmserving, #llmtraining, #mixtureofexperts, #performanceengineering

TencentCloud/Octop
A smarter, self-hosted AI assistant — multi-user, multi-agent.
Language:Python
Total stars: 2127
#python
#agent, #agenticai, #ai, #aiagent, #aiagents, #localfirst, #longtermmemory

Human-Agent-Society/reef
Continual learning infra for self-improving agents
Language:Python
Total stars: 1667
#python
#agentinfrastructure, #aiagents, #continuallearning, #inference, #llm, #llmtraining, #reinforcementlearning, #selfimprovingagents

xzf-thu/VoiceMem
Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.
Language:Python
Total stars: 1723
#python
#ai, #aiagents, #aitools, #application, #audiostreaming, #genai, #llm, #longtermmemory, #memory, #memorymanagement, #python, #voiceagent, #voiceassistant