Lists (19)
Starred repositories
Your Personal AI super intelligence. Private, Simple and extremely powerful.
🔍 OpenSearch-VL provides a fully open recipe for training strong multimodal deep search agents through high-quality data curation, diverse visual/search tools, and fatal-aware agentic reinforcement…
🚀 AI 全自动短视频引擎 | AI Fully Automated Short Video Engine
[ECCV’24] Official Implementation for CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…
Official implementation of Tuna-2: Pixel Embeddings Beat Vision Encoders for Unified Understanding and Generation
🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
🚀 First survey on Attention Sink in Transformers — 180+ papers on utilization, interpretation, and mitigation.
Lsyncd (Live Syncing Daemon) synchronizes local directories with remote targets
Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
StreamingVLM: Real-Time Understanding for Infinite Video Streams
AI API identity gateway — reverse proxy that normalizes device fingerprints and telemetry for privacy-preserving API proxying
[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
🦀🌡️ Real-time system monitor for Apple Silicon Macs (M1–M5). No sudo. TUI, JSON/Prometheus metrics server, and Rust library.
很多镜像都在国外。比如 gcr 。国内下载很慢，需要加速。致力于提供连接全世界的稳定可靠安全的容器镜像服务。
Lightweight, open-source AI agent for your tools, chats, and workflows.
Create beautiful slides on the web using Claude's frontend skills
Free, local, open-source 24/7 Cowork app for OpenClaw, Hermes Agent, Claude Code, Codex, OpenCode, Gemini CLI and 20+ more CLI | Customize your assistants | Star if you like it!
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning
CDN 免费 SLL 证书自动续费部署工具，自动申请 Let’s Encrypt 证书并部署到云服务商的 CDN 中，支持腾讯云、七牛云等，前后端均完整开源免费！
Edit Banana: A framework for converting statistical formats into editable.
The most advanced Nano Banana image generator and editor application. Your central hub for AI image generation and revisions. Intuitive UI features reference images, editing with image masks, versi…
Self-hostable OpenReview paper monitor: email alerts for new reviews, reviewer score changes, and decisions.