Lists (2)
Starred repositories
Native macOS app: drop a long video → auto-cut viral shorts, captioned for TikTok/Reels/YouTube, reframed to vertical, and scheduled. 100% on-device (Gemma 4 12B + WhisperKit + MLX).
A comprehensive book on neural networks and large language models in NLP
Terminal pixel-art office for AI coding agents
AI agent workspace with Code and Write modes built into your application.
Pure Rust + CUDA LLM inference engine
AgentRQ: Human-in-loop realtime conversational task manager for AI Agents.
OpenAgents - AI Agent Networks for Open Collaboration
🚀 Ultra Recipe for Training Long-Horizon Search Agents - matching frontier AI's search capability with a 20B model
AI PPT赛道终结者，史上最最最强 PPT Skill！！！ 使用GPT生成豪华的图片格式PPT，然后转换为完全可编辑的PPTX文件。
KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.
Power efficient dashboard for Kindle 4 NT devices
Turn an old Kindle into a real-time Claude Code heads-up display. Zero cloud. Zero cost. Zero dependencies. One file.
OfficeCLI is the first and best Office suite purpose-built for AI agents to read, edit, and automate Word, Excel, and PowerPoint files. Free, open-source, single binary, no Office installation requ…
What if you had all the data in the world?
⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA
Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
Open CLI for integrating AI search, recommendation, and conversational retrieval into agent systems and business systems
DFlash: Block Diffusion for Flash Speculative Decoding
Offline optimization of your disaggregated Dynamo graph
Tile-Based Runtime for Ultra-Low-Latency LLM Inference
Fast and memory-efficient classical machine learning operators
openma - open-source, self-hosted implementation of Claude's Managed Agents API. Drop-in compatible. Runs on Cloudflare Workers + Durable Objects or Node.js. Apache 2.0.