Stars
你给一个故事，它还你一套能直接拿去出图、出视频的上美影短剧制作文档。** "上美影"= 上海美术电影制片厂，就是《大闹天宫》《天书奇谭》《九色鹿》那种复古手绘动画的味道——概括的造型、手工感的线条、大片平涂的矿物颜料色。
Open source alternatives to paid SaaS apps: Notion, Slack, Auth0, Vercel and more. Curated list with licenses and GitHub stars.
Metis is a coding agent that boosts AI/LLM coding performance by 50% QQ群: 801193315
A persistent, Git-versioned map of your whole codebase and database schema that coding agents read before they touch anything. Local-first MCP server + CLI in Go: a governed repository index of cod…
Yet Another Unity UI: a fast, Flexbox-based UI system on GameObjects.
Build your own network of agents from Claude Code, Codex and Pi: persistent teams with roles, shared context and owned work.
Open-source, self-hosted AI agent workspace and alternative to OpenAI Dots, Meta Muse, Grok Bot, Instinct, Manus Cue, Claude Cowork, and ChatGPT agent. MIT-licensed; includes chat, connectors, appr…
Find code by asking what it does. A CLI for coding agents that uses Jev to discover relevant files and source context.
A personal agent with a browser, terminal, files, and work that keeps going built with CopilotKit and AG-UI.
本项目是一款 **2D 战棋策略角色扮演游戏原型**，参考了《火焰纹章》的战棋玩法与策略深度，独立实现了完整的 SRPG 基础框架。
本项目是一款 **2.5D 回合制角色扮演游戏原型**，参考了《歧路旅人》的探索与战斗风格，玩家可在 3D 场景+2D Sprite 的世界中进行探索，并进入回合制战斗。
killop / layer-images
Forked from loverelic0-wq/layer-imagesTurn flat images into coordinate-faithful PNG layers and validated PSD files with SAM2 + GPT reconstruction
killop / image-to-slice
Forked from 50kg/image-to-sliceAI 拆图、被遮挡背景补齐、人工校准、导入可编辑 Figma 图层、导出 HTML/CSS
Turn layered PSDs into editable Live2D models — automatic rigging, mesh/deformer generation, physics, animation, and .cmo3/ .moc3 export.
A full retained fly-connectome simulation with experimental memory and guarded Coinbase AgentKit trading actions.
Where terminal agents work together. Claude Code, Codex, Copilot CLI and pi on the same task, in one mission, each keeping its own TUI in a real terminal.
Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be se…
MiniCPM5: SOTA on-device LLMs, small yet powerful.
本项目采用 CC BY-NC-SA 协议，禁止任何商业化行为，任何衍生项目必须保留本项目地址并以相同协议开源
Agent-driven creation of editable, tastefully crafted visual artifacts.
glm-5.3-flash-vision RAG：三个 GLM 视觉技能总览 > 同一套"让 AI 看懂资料"的技术，嫁接到智谱 **GLM-5.3-Flash** 视觉大模型上， > 做成了三件趁手的工具：**看懂 PDF**、**看懂视频**、**把带货视频变成提示词
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.
Prompt as Code | GPT Image 2 / 2.5 提示词与案例库，530+ 个案例、20+ 套工业级模板与可复用 Skills，新增 2.5 同提示词对比专区，附完整提示词与生成记录，持续更新。
Desktop workspace for Pi, OMP, and Prime Agent
The open-source CapCut alternative