- Seoul, Republic of Korea
-
23:06
(UTC +09:00) - injaeryou.dev
- in/injaeryou
- https://huggingface.co/injaeryou
Highlights
Lists (27)
Sort Name ascending (A-Z)
AI/Audio
AI/Benchmark
AI/Coding
AI/Diffusion
AI/Efficiency
AI/FE
AI/Fine-tuning
AI/Harness
AI/Kernel
AI/LLM
AI/Local
AI/Ontology
AI/RL
AI/Vision
Dev/Alternatives
Dev/BE
Dev/Compiler
Dev/Git
Dev/Testing
Dev/Tools
Learn
Platform/Mac
Platform/VM
Platform/Windows
Research
Research/CSI
Robotics
Stars
An RSI-Native LLM Serving Engine for Live, Compositional, and Safe Self-Improvement
maxxing the ability to run different LLMs on the smallest devices possible
Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost…
OpenShell is the safe, private runtime for autonomous AI agents.
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
Official implementation of LittleBit (NeurIPS 2025) and its follow-up LittleBit-2 (ICML 2026)
AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.
Chrome DevTools for coding agents
AWS Emulator is a local emulator of the AWS APIs.
DeepSeek Harness: Everything is a Plugin.
Towards a More Autonomous Agent System
EvoSkill — An open-source framework that automatically discovers and synthesizes reusable agent skills from failed trajectories to improve coding agent performance.
Auto Ontology is a Python framework for building semantic, graph-based reasoning layers over data. It enables deterministic query generation, better context retrieval, and more explainable AI for L…
Turn your coding agents into research agents
📰 Must-read papers on KV Cache Compression (constantly updating 🤗).
The offical repo for "Dream-RSI: Recursive Self-Improvement through Evolving Worlds"
Official Project Page for KL-Regularized Policy Optimization (KLPO) (https://arxiv.org/abs/2610.08963)
Awesome LLM compression research papers and tools.
Official Project Page for Recurrent Looped Transformer (RLT) (https://arxiv.org/abs/2610.07591)
Keep-or-Drop Adaptive Tokenizer for Compact Video Representation
A skill to stop your coding agent from burying the answer. ADHD-friendly output.
🧠 两小时从 0 训出你的 64M 大模型。Train your own 64M LLM from scratch in 2 hours.
A Super AI Lab with massive AI Doctors as Assistants. Best IDE for Research via AI Power.
Unlocking Lossless Speedups in LLMs via Discrete Diffusion
Awesome list for LLM quantization