Lists (1)
Stars
A tiny, fully-reproducible JEPA world model that learns the physics of a bouncing DVD logo in representation space, dreams its future, and detects anomalies. Trains on a CPU in ~10s. Interactive br…
AI Agent 驱动的开源视频生成工作台 — 小说→角色/场景/道具设计→剧本→分镜图→视频，跨镜头角色与场景一致 | Open-source AI video workspace powered by AI Agents, Nano Banana 2 & Veo 3.1 / Grok / Seedance / OpenAI
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Use your most capable model to audit your codebase and write plans for cheaper models to execute.
Claude Code plugin that transforms vague software ideas into individual, ready-to-be-planned components
Free skills from the Hyperagent team
Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent access to profiles, companies, jobs, and messages.
A drop-in proxy that compresses bloated code context in real-time, cutting LLM API costs by 50–80% without losing what the model actually needs to know.
Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding
Scripts for agents, shared between my repositories.
Official implementation of Surflo: Consistent 3D Surface Flow Model with Global State.
Native Agent CLIs manager for macOS. Ghostty Terminals + Codex App Features/UX = Ghostex! Embedded browser & IDE. Strong agents support.
A ~9M parameter LLM that talks like a small fish.
A benchmark for AI-driven CAD generation and editing
Components crafted for Design Engineers. Styled using Tailwind CSS, fully compatible with Shadcn, and easy to integrate—just copy and paste. MIT 🤌
'Personal AGI' that thinks on its own. Autonomous cognitive cycle, earned autonomy, 60+ tools. It decides what to do without being told.
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows — particularly Claude Code
Paste any GitHub URL → interactive architecture map. See how files connect, find what breaks if you change something. No install, no accounts — runs entirely in your browser.
中文小黑怪诞正文配图生成 Skill | 16:9 白底手绘 | 少量红橙蓝批注 | Codex Skill
Agent-first Rust ASR orchestration stack: Bayesian backend routing across whisper.cpp/insanely-fast-whisper/whisper-diarization, real-time NDJSON streaming, SQLite persistence, TTY audio transport,…
DeepSeek V4 Flash specific inference engine. SSD MoE expert paging (slot-bank) + disk KV cache for long agent sessions. Metal-first, narrow & high-performance.
Project the aircraft passing overhead onto your ceiling in real time, from an RTL-SDR — with a live sky layer (sun, moon, stars, ISS) and where each plane is headed.
CADAM is the open source text-to-CAD web application
WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling
A small, drop-in, pure-JavaScript Draco mesh loader for three.js.
Use your NVIDIA GPU's VRAM as swap space on Linux. Built for laptops with soldered memory and no upgrade path. If you have an RTX card sitting there with 8GB of VRAM and you're getting swapped to S…