标签：可自托管

Open-source AI gateway you run yourself. One endpoint for 40+ providers, with virtual keys, budgets, and usage tracking.

pi coding agent in a technicolor web trenchcoat

Markdown filesystem for agents and teams.

Own the flow: one open-source AI platform for your knowledge, models and channels – web, WhatsApp, email, Outlook, Nextcloud & ownCloud. Local and cloud models side by side, with the cost on every answer.

♾️ Private Agent Fleet with Spec Coding. Each agent gets their own GPU-accelerated desktop. Run Claude, Codex, Gemini and open models on a full private AI Stack ♾️

A self-hosted platform to use HandBrake on your headless devices via a bespoke web interface. Harness the processing power of multiple devices to work on a single queue.

Open-source database & workspace for AI agents — structured data, durable knowledge, reusable skills, runnable apps, and human review on the writes that matter. Local-first and self-hostable.

The open source Meme Search Engine and Finder. Free and built to self-host locally with Python, Ruby, and Docker.

Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context.

Run Hermes Agent and OpenClaw on the same WeChat account

Self-hosted AI Agents Platform for AI Native companies. Claude Code, Codex, Gemini, OpenCode agents. Apache 2.0.

LAN-only remote desktop based on RustDesk

😋 AI-powered, Lightweight RSS Reader. Supports: GitHub Pages | Vercel | Alibaba Cloud ESA Pages | Docker

IPTV reverse proxy for M3U/M3U8 playlists and Xtream Codes accounts, with HLS. One binary or Docker container.

Straightforward realtime kanban boards management for intuitive task tracking. 4ga Boards features an elegant dark mode, collapsible todo lists, and multitasking tools to supercharge your team's productivity.

Open-source LLM gateway in Rust. One endpoint for OpenAI, Anthropic, Gemini and every other vendor. Any SDK, any model, any tool.

Open-source, self-hosted AI video generator — completely free. Text to multi-scene video with narration, subtitles, and digital anchor via Web UI, powered by Agnes AI.

Low-latency remote desktop and KVM-over-IP: Sunshine/Moonlight game streaming, USB passthrough (gamepads, Wacom, MIDI), NanoKVM & Radxa IP-KVM firmware, Tailscale P2P. Windows, macOS, Linux, Android, iOS, web.

Self-hosted, secure tunnel server in Rust. Expose local HTTP/HTTPS/TCP/UDP services to the public internet via TLS-encrypted WebSocket. Open-source, pay-as-you-go managed option, MCP server for AI agents.

Alternative to Kikoeru, Neokikoeru is a high-performance streaming media server for DLsite voice works—designed to be robust, fast and user-friendly.

Streamline your workflow with Lynkr, a CLI tool that acts as an HTTP proxy for efficient code interactions using Claude Code CLI.

Enables organizations to create and deploy customizable AI agents with support for multiple LLM providers, real-time chat, voice, document training, analytics, user management, SSO authentication, and embeddable widgets. Built with React 19, Redux Toolkit, Radix UI, and Tailwind CSS.

Sportarr - Sports PVR for usenet and torrents. Like Sonarr & Radarr but for sports events.

Open-source, self-hosted GitBook & Confluence alternative: a WYSIWYG editor over Markdown in your own Git repo, with a documentation portal

开源自托管笔记与私有知识库，支持 Markdown/富文本、AI 写作、思维导图、任务管理、全文搜索、多级笔记本和 Docker 一键部署。

NixOS Media Server Configuration

HunterCode · Community Edition · 腾讯 WorkBuddy 金融版的开源本地替代方案 · open-source, local alternative to Tencent WorkBuddy Finance Edition · 多智能体投研终端 A股/港股/美股 · 推理在你机器上跑 · 仓位不出你硬盘 · BYOK · Apache 2.0 · docker compose 自托管

Self-hosted AI agent OS. Your memory, chat, agents, and files stay on hardware you own, offline by default, cloud by choice. Offline AI memory (taOSmd), self-hosted multi-framework group chat, a full web desktop + app store, and auto-clustering across the consumer hardware you already have (Orange/Raspberry Pi, Mac mini, gaming PC).

Glass Keep is Keep Notes alternative using Glass design. Docker Server, Tauri Clients and PWA

Drivebase is a cloud-agnostic file management platform for people and teams using multiple storage providers. 🚀

A skill for AI agents: search the web with SearXNG, browse with Camofox, bypass protections with CloakBrowser. Anti-hallucination by design. Self-hosted, free, unlimited.

Run the DeepSeek Harness AI agent natively on Android — no root, no Termux, extension center included | 手机本地运行 DeepSeek Agent，免 Root 免 Termux

🏔️ The AI-native RSS reader

Self-hosted personalized AI in a mirror.

Autonomous AI dev-team bot

🕷️ The fastest open-source AI Gateway and LLM Gateway — one binary with built-in console to route, secure, budget and observe every LLM call across OpenAI, Anthropic, Gemini, Bedrock and more.

AI Agent Identity and Access Management and Inference Firewall

Self-hosted AI API gateway for Claude Code, Codex and Gemini: pool API keys and subscription accounts behind one endpoint with failover, protocol conversion and cost tracking.

Xiryn — the open-source personal agent. Does everything Muse, Grok Bot and Dots do, on your own computer: each agent gets its own Linux desktop in Docker, any model with your keys, an encrypted vault, and control from Telegram.

🦉 Free open-source notetaking app with real-time sync 🔄⚡️🚀

The self-hostable alternative to Cloudinary

Give your agents the power to publish reviewable HTML documents. Self-hosted server + CLI + remote MCP; agents push, humans review with comments and versions.

News reader with tags, scoring, and LLM

Open-source casting suite (alpha) — browse on your phone, play on the big screen: Android TV, Apple TV, desktop or DLNA TVs. Local-network, no account. MPL-2.0.

Self-hosted media streaming server designed as an alternative to Plex, allowing you to monitor and manage your movie and TV show files on a headless server.

The open-source Devin alternative. Run Claude Code, Codex or OpenCode in isolated cloud workspaces you can self-host.

A minimalist file-manager with streaming capabilities

An Open-source, self-hosted AI model hub with Hugging Face compatibility, accelerating vLLM/SGLang performance.

Your own private cloud in one executable. Share files, collaborate on code, and manage users without complex setup.

Self-hosted AI gateway for private RAG, natural-language data access, and tool-calling agents.