Explore Projects
Discover 46 open source projects
Showing 21-40 of 46 projects
xlite-dev/Awesome-LLM-Inference
A curated list of awesome papers and code for optimizing LLM/VLM inference performance
PeterGriffinJin/Search-R1
An efficient, scalable RL training framework for reasoning and search engine calling interleaved with large language models.
johnbean393/Sidekick
A native macOS app that allows users to chat with a local LLM without installing other software.
oslook/cursor-ai-downloads
Official download repository for Cursor AI, an AI-powered coding assistant and IDE for vibe coders.
SkyworkAI/Skywork-R1V
An advanced multimodal AI model series for vision-language reasoning, developed by Skywork AI.
haiibo/OpenWrt
An OpenWrt firmware build optimized for various ARM and x86 devices, including popular SBCs like Raspberry Pi and Rockchip.
microsoft/genaiscript
Automatable GenAI scripting tools for building AI-powered applications and workflows in TypeScript.
LLM-Red-Team/deepseek-free-api
A free API that provides access to the DeepSeek-V3 and R1 large language models, enabling developers to build AI-powered chatbots and applications.
ErlichLiu/DeepClaude
An AI-powered coding platform with features like code generation, content creation, and OpenAI compatibility.
Unakar/Logic-RL
A Python library for reproducing the R1 Zero algorithm on logic puzzles.
AnotiaWang/deep-research-web-ui
An AI-powered research assistant that performs deep research on any topic by combining search, scraping, and language models.
apconw/Aix-DB
A LangChain-based framework for end-to-end natural language to data insight conversion, with MCP Skills multi-agent architecture.
mikeroyal/Apple-Silicon-Guide
A comprehensive guide to Apple's ARM-based silicon, including M-series chips, macOS, tools, and more.
policy-gradient/GRPO-Zero
Implements the GRPO algorithm from scratch for developers interested in reinforcement learning and AI agents.
langfengQ/verl-agent
verl-agent is a Python framework for training LLM/VLM agents using reinforcement learning.
lsdefine/simple_GRPO
A simple Python implementation of a GRPO-like LLM for reproducing r1-like thinking.
EvolvingLMMs-Lab/open-r1-multimodal
A fork to add multimodal model training capabilities to the open-r1 project, a framework for building AI tools.
yusufcanb/tlm
A local CLI copilot powered by the Ollama language model, for developers who build with AI tools.
acidicoala/Koalageddon
This is a legit DLC unlocker for various game launchers, not a developer tool for vibe coders.
RUC-NLPIR/WebThinker
WebThinker is a powerful framework for building large language models with deep research capabilities.
Stay in the loop
Get weekly updates on trending AI coding tools and projects.