Rankings

An agent-first linter for Tailwind design systems. Write design system rules that agents can verify.

Quickly install signed iOS and Android builds on real devices over the internet without waiting for Testlight or Play Beta.

A lightweight, self-hosted AI subscription pool for teams.

2026 年编程导航 AI 编程实战新项目，基于 React 19 + FastAPI + LangChain + LangGraph + Konva 的 AI 修图智能体，支持自然语言驱动修图、21 种编辑工具、文生图、智能抠图、图层拆分、区域编辑、多步计划。覆盖 AI Agent 架构、SSE 实时推送、异步任务队列、Canvas 画布引擎。用一套教程掌握 AI Agent 全栈开发，不到一周学完，给你的简历增加竞争力

Installe ET cable automatiquement une stack media *arr : cles API echangees, indexeurs synchronises, profils de qualite TRaSH poses. Assistant TUI, page d'acces et d'administration.

A Claude skill that turns brainstorming into an interactive mind map of inverted assumptions — no answers, no ranking, just provocations.

PocketBase SDK for Unreal Engine with Blueprint and C++ APIs for records, authentication, files, realtime, batch operations, and admin tooling.

Open-source platform for deploying and running functions behind your own Infra.

GeoGuessr cheat, hack and auto guess bot. ATLAS reads the street view on your screen and names the location in about three seconds. Around 81 percent country accuracy in real games, 111 countries. Windows, Steam, Chrome, Firefox, macOS, iPhone and Android on one licence key.

打开干扰类 App 前，先呼吸十秒。自建的 One Sec 替代品，跑在 Cloudflare 免费额度上。A self-hosted One Sec alternative: breathe before the app opens.

Continual learning infra for self-improving agents

AI makes things up when it reads a binary. Reverify checks its every claim against the real bytes, so you see what's actually true — AI-assisted reverse engineering you can trust. LLM proposes, deterministic tools verify. MCP server + CLI.

The open-source AI coworker for your team: agents with their own cloud computer, your tools and context, handing back finished work websites, decks, spreadsheets, reports, PRs. Runs Claude Code, Codex, OpenCode on your subscription.

Self-hosted email suite: React webmail, admin console, and a pluggable single-binary Go mail engine. Docker Compose deployment.

Self-hosted, chat-shaped clipboard and file ferry for devices on one trusted LAN: a single Go server with an embedded web app, plus native iOS and Android clients.

墨枢是一个面向中文长篇网文作者的 AI 小说写作工作台，支持作品大纲、章纲、人物与世界观设定库、时间线、RAG 检索、一致性守卫、自然化审查、AI 辅助续写、团队协作、用量计费，以及面向漫剧改编的静态分镜管理。前端采用 Vue 3，后端采用 FastAPI，支持 PostgreSQL/pgvector、Redis、Docker 自部署和 Cloudflare Workers 预览。

自动签到面板 — New API 类型中转站的每日签到，HTTP 优先，浏览器兜底。桌面版 / 容器 / 控制台三种运行方式。

记忆桥 MemoryBridge — 跨设备、跨平台的 AI 共享记忆层 | Cross-device and cross-platform shared memory for AI (CDSMP implementation)

Self-hosted companion server for Pictaria Frame, powered by your Immich library.

Vicoa is the ADE for running a team of coding agents from any device. Desktop, mobile, VPS, open-source, self-hostable.

Open-source software for building a neobank. Product screens, a 181-operation banking API, a double-entry ledger and a canonical stablecoin FX engine. MIT licensed, self-hostable, runs on Node or Cloudflare Workers.

Open-source, local-first AI workspace that tracks tokens & spend across Claude Code, Codex, Cursor and more — and turns every session into reusable Skills and long-term memory. / 开源、本地优先的 AI 工作台：自动统计 Claude Code、Codex、Cursor 等工具的 Token 用量与花费，并把每次 AI 会话沉淀为可复用的 Skills 和长期记忆。

AI product management skills and plugin for Claude Code, Cowork, Codex & other AI agents: evidence-tagged PRDs, specs, requirements, RICE prioritization, backlog and roadmap scoring, product strategy, GTM launch plans, release verification, benchmark packs, UX/UI design prompts for web + mobile apps. Every claim sourced or labelled unsourced.

De-AI writing skill for any Agent Skills-compatible agent (77+ via the Skills CLI), with native plugins for Claude Code, Codex, Grok Build, and Antigravity. Narrative-architecture repair for fiction, venue-matched rules for professional prose. Based on StoryScope (arXiv:2604.03136).

Open-source multi-provider AI gateway for Claude Code and other coding agents, with model routing, streaming, tools, reasoning, fallbacks, and local model support

DevOps secrets base: lightweight, self-hosted secrets manager in a single file

GLM-5.3-Flash EXL3 (320B MoE) on 2x NVIDIA DGX Spark — production serving kit, 1M context, 97%+ multi-session prefix caching, DFlash2 spec decode

Durable local inference for Oh My Pi: NInfer + Qwen3.8 27B on one RTX 3090/4090/5090, with restart-resumable OpenAI Responses state.

Distill your knowledge, memories, and decisions into an open-source, inspectable AI Agent Twin.

Production-ready Codex-compatible account-pool gateway with seamless failover, full-session recovery, native quota headers, WebSocket/HTTP bridge, and observability.