AI 开源项目榜。

[ICCV 2025 & ICCV 2025 RIWM Outstanding Paper] Aether: Geometric-Aware Unified World Modeling

Qwen3.8-Flash-Next on ONE DGX Spark (TP=1)

Recursive Language Models for efficient long-context processing. Analyze 1M+ tokens by storing context in a Python REPL while reducing LLM token usage.

All AI developers deserve to get paid. Turn your AI prototype into a paid SaaS with open-source infrastructure for usage billing, payments, attribution, affiliates, anti-abuse, and deployment.

通用、模块化的自媒体内容生产与经营 Skills / A modular, tool-agnostic self-media content skill suite

Curated, live-verified OPML collections for AI, news, research, blogs, videos, podcasts, and engineering.

A MCP (Model Context Protocol) server for interacting with dbt.

Bilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /render-html into single-file HTML, reads anywhere — plus a CV→DBLP-fact-checked academic homepage generator and hand-authored long-form blogs 🌱

[ICLR 2026]ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representation

RAI is a vendor agnostic agentic framework for Physical AI robotics, utilizing ROS 2 tools to perform complex actions, defined scenarios, free interface execution, log summaries, voice interaction and more.

Unitree Go2 simulation platform for testing navigation, decision-making and autonomous tasks. (NVIDIA Isaac/ROS2)

Edit Video with Claude Code

MatterSim: A deep learning atomistic model across elements, temperatures and pressures.

William Strunk Jr.'s Elements of Style (1918) in markdown format for AI agents

MagicTryOn is a video virtual try-on framework based on a large-scale video diffusion Transformer.

Professional deep research report generation Skill — one command, ten minutes, broker-grade deep research / 深度调研报告生成 Skill — 一条命令，十分钟出券商级深度调研报告

Claude Code skill: turn long videos into social-ready clips. Auto-find funny moments, cut, reframe to 9:16 with face-tracking, and burn opus-style captions.

L Harness — self-hosted LINE Official Account CRM: step messaging, broadcasts, forms and reservations, with MCP and TypeScript SDK. By Shudesu (野田修一).

Model Context Protocol for x64dbg & x32dbg

结合chrome-devtools-mcp的能力并加上Skill的规范，实现JSRPC+Flask+autoDecoder方案的前端JS逆向自动化分析，提升JS逆向的效率

Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours

A ROS node to perform a probabilistic 3-D/6-DOF localization system for mobile robots with 3-D LIDAR(s). It implements pointcloud based Monte Carlo localization that uses a reference pointcloud as a map.

Monty is a sensorimotor learning framework based on the thousand brains theory of the neocortex.

Composable Elixir library for LLM interactions built on Req and Finch

PyTorch implementation of Soft Actor-Critic (SAC)

Dataset and benchmark for RAG on company internal documents.

Awesome Jev: a source-backed field guide to TypeSafe's System One model, with SDKs, live demos, agent tools, and independent evaluations.

NextPlaid, ColGREP: Multi-vector search, from database to coding agents.