正在加载 / Loading
正在加载 / Loading
Based on verifiable star growth, commits, releases, and maintenance evidence. Missing data stays visible as unknown.
581 projects · Page 14/30
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Score: 75 · Trending · Updated: 2026-10-15 · 7d — · 30d —Latest substantive commit observed 18 days ago; pushed_at is not used as a substitute.
Story Creation AI Agent for novel, scripts, translation, interactive games, and IP content
Score: 75 · Trending · Updated: 2026-10-24 · 7d — · 30d —Latest substantive commit observed 10 days ago; pushed_at is not used as a substitute.
A fast and flexible implementation of Rigid Body Dynamics algorithms and their analytical derivatives
Score: 75 · Trending · Updated: 2026-10-28 · 7d — · 30d —Latest substantive commit observed 5 days ago; pushed_at is not used as a substitute.
Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.
Score: 75 · Trending · Updated: 2026-11-02 · 7d — · 30d —Latest substantive commit observed 0 days ago; pushed_at is not used as a substitute.
🎬 Evidence-led Seedance 2.5 / 2.0 prompt library: 840+ cases traced to original posts, 490+ cross-model retest runs, 27 copy-ready templates, 79 installable AI-video Skills. Synced daily from goodcase.ai. EN / 中文 / 日本語.
Score: 75 · Emerging · Updated: 2026-11-03 · 7d — · 30d —Latest substantive commit observed 0 days ago; pushed_at is not used as a substitute.
Play a finished motion-graphics ad in sync with the rough drafts it grew from, and export the breakdown as MP4.
Score: 75 · Emerging · Updated: 2026-10-30 · 7d — · 30d —Latest substantive commit observed 4 days ago; pushed_at is not used as a substitute.
multilspy is a lsp client library in Python intended to be used to build applications around language servers.
Score: 75 · Trending · Updated: 2026-10-13 · 7d — · 30d —Latest substantive commit observed 20 days ago; pushed_at is not used as a substitute.
DeepSeek Harness 本地视频制作与设计插件：多轨剪辑、模板与设计体系、原生预览画布和真实文件导出
Score: 75 · Emerging · Updated: 2026-10-25 · 7d — · 30d —Latest substantive commit observed 8 days ago; pushed_at is not used as a substitute.
Click tags in your language, get the English prompt Midjourney, FLUX, GPT-Image & Veo actually expect — 한국어 العربية Русский हिन्दी ไทย ｜ 英文提示词不用自己写：点中文标签，自动拼好模型认的那一套
Score: 75 · Trending · Updated: 2026-10-07 · 7d — · 30d —Latest substantive commit observed 27 days ago; pushed_at is not used as a substitute.
100+ curated Seedance 2.5 prompts with real video previews, plus an installable Agent Skill that optimizes prompts, creates storyboards, and generates videos via Seedance models.
Score: 75 · Trending · Updated: 2026-11-03 · 7d — · 30d —Latest substantive commit observed 0 days ago; pushed_at is not used as a substitute.
An open-source, agent-native platform for multimodal AI generation, built on DeepSeek Harness. Every interaction lives in agent conversations and an infinite canvas, unifying creation, generation, and editing.
Score: 75 · Emerging · Updated: 2026-10-30 · 7d — · 30d —Latest substantive commit observed 4 days ago; pushed_at is not used as a substitute.
A no-code RAG server that keeps answers in sync with your documents. Works with 8 vector databases. Built on Pathway.
Score: 74 · Trending · Updated: 2026-11-02 · 7d — · 30d —Latest substantive commit observed 0 days ago; pushed_at is not used as a substitute.
Unrestricted Open-source alternative to AI video platforms — Free AI image & video generation studio with 600+ models (Flux, Midjourney, Kling, Sora, Veo). No content filters. Self-hosted, MIT licensed.
Score: 74 · Trending · Updated: 2026-11-03 · 7d — · 30d —Latest substantive commit observed 0 days ago; pushed_at is not used as a substitute.
Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits.
Score: 74 · Trending · Updated: 2026-10-28 · 7d — · 30d —Latest substantive commit observed 6 days ago; pushed_at is not used as a substitute.
Desktop Companion for Hermes Agent
Score: 74 · Trending · Updated: 2026-10-13 · 7d — · 30d —Latest substantive commit observed 20 days ago; pushed_at is not used as a substitute.
Java 1-25 Parser and Abstract Syntax Tree for Java with advanced analysis functionalities.
Score: 74 · Trending · Updated: 2026-11-02 · 7d — · 30d —Latest substantive commit observed 0 days ago; pushed_at is not used as a substitute.
The most autonomous AI agent framework: runs unattended on GitHub Actions, self-healing skills, drives Claude Code, Grok, Codex & more. No approval loops. Configure once, forget forever.
Score: 74 · Trending · Updated: 2026-11-02 · 7d — · 30d —Latest substantive commit observed 0 days ago; pushed_at is not used as a substitute.
🍟 麦当劳中国官方 MCP 智能助手技能：把 35 个原子工具编排成 4 条业务流 —— 活动推送 · 联名关注 · 最优惠点餐 · 多人群点聚合账单。算价用 calculate-price 真算，下单必二次确认。｜McDonald's China MCP agent skill: campaigns, collab watch, best-value ordering, group bill splitting.
Score: 74 · Emerging · Updated: 2026-10-27 · 7d — · 30d —Latest substantive commit observed 6 days ago; pushed_at is not used as a substitute.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Score: 73 · Trending · Updated: 2026-10-31 · 7d — · 30d —Latest substantive commit observed 3 days ago; pushed_at is not used as a substitute.
LLM Frontend for Power Users.
Score: 73 · Trending · Updated: 2026-09-14 · 7d — · 30d —Latest substantive commit observed 49 days ago; pushed_at is not used as a substitute.