One notify() call is all your product needs to reach users on push, email, SMS, chat, and webhooks, with NotifKit deciding how and when each message travels. List the channels in the order you prefer and NotifKit tries each in turn, so a failed push quietly becomes an SMS or an email instead of a lost message. Per-user preferences, consent, and quiet hours in each user's own timezone hold non-urgent sends until morning, while critical messages such as one-time passwords travel their own lane immediately. Templates, multi-step workflows that wait days or block on events, scheduling, throttling, and deduplication all run behind that single call, defined in TypeScript and kept in your repository. Delivery logs record every attempt, and the admin dashboard shows a live activity feed, queue depth per priority lane, workflow runs step by step, and a replayable dead-letter queue. Several products can share one deployment as separate projects with their own API keys, rate limits, and data, and any service can call the REST API without the TypeScript SDK. Ask an AI assistant why a password reset never arrived by connecting the built-in MCP server to Claude Code, Cursor, or another MCP client. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

ScribeCrate is a self-hosted speech-to-text API that turns recordings into transcripts, subtitles, and English translations on your own server. It speaks the OpenAI Whisper API fluently: point any compatible client at your server's address, swap in your API key, and uploads come back as text. Ask for plain text, JSON with timestamps, or ready-to-publish SRT and WebVTT subtitle files, and for long recordings the segments can stream back over SSE as they are decoded. Turn on speaker diarization and every segment is labeled with who is speaking, which makes interview and meeting transcripts readable at a glance. Choose the model that fits the job, from tiny for quick drafts to large-v3 for maximum accuracy, and run it on a modest CPU, a Raspberry Pi class ARM board, or an NVIDIA GPU. Almost any recording works: MP3, M4A, WAV, WebM, OGG, and FLAC are all accepted, and with models cached in advance the server keeps transcribing with no internet connection at all. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Five mailboxes, five tabs, five passwords: Gofer folds Gmail, Outlook, iCloud, and plain IMAP accounts into one browser tab where every inbox reads as a single, searchable whole. Threads, labels, and drag and drop keep triage fast, and search still finds the receipt from three years ago. Signatures and custom senders shape outgoing mail, scheduled sends wait for Monday morning, and a thread in another language translates in place. The calendar keeps pace with your mail: Google, Outlook, and CalDAV events sync both ways, invitations land in the inbox, and an RSVP or a Meet or Teams link attaches without leaving the message. Contacts follow the same rule through Google, Outlook, and CardDAV sync, so the address book you fix once is right everywhere. One install can serve a household or a small office, with separate users, encrypted credentials, blocked remote images, and passkey or authenticator sign-in for anyone who wants it. Classic, Minimal, and retro Express themes, flexible layouts, and push notifications make the daily inbox feel personal rather than administered. Leaving stays easy too: mailboxes export as mbox, mail moves between accounts, and a whole setup imports into another Gofer. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Spam bots flood busy Telegram groups with crypto scams and phishing links faster than human admins can delete them; TG-Spam watches every message and removes the junk before your members see it. Each message is scored by several checks at once: similarity to known spam samples, a stop-word dictionary, emoji and link counts, and a lookup against the Combot Anti-Spam database of known spammers. For borderline cases you can add OpenAI or Gemini as an extra judge, or write your own detection rules as Lua plugins that run inside the bot. The bot learns while you moderate: when admins approve a flagged message or ban a user it missed, the samples update, so the same trick fails next time. Members can report spam with a reply, repeat offenders accumulate warnings toward an automatic ban, and an admin chat gives your team one place to review borderline calls. Turn on the built-in server and the same engine answers spam checks over HTTP for your other tools, with a web UI to test messages, manage samples and dictionaries, and control the approved-user list. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Your team's group chat could have a colleague who has read every email, ticket, and document, remembers all of it, and answers in seconds; MindRoom puts AI agents like that into your chat rooms as full participants. Each agent is a real user on the open Matrix protocol, so you talk to it in MindRoom Chat on web or mobile, in any other Matrix client, or through bridges in Slack, Telegram, WhatsApp, and Discord. Give every agent its own model: a local model for private rooms, a frontier model for hard coding problems, and switch per room or thread whenever the work changes. Agents connect to more than 100 tools, including Gmail, calendars, GitHub, Google Drive, Home Assistant, and any MCP server, and they search your own documents and knowledge bases for answers with sources. Memory persists across conversations and platforms, so an agent remembers people, preferences, and project context months later and can turn repeated work into reusable skills. Before an agent sends an email or runs a command, an approval card shows exactly what will happen; you tap once to allow it, and sandboxed workers keep executed code away from your credentials. Schedule morning briefings, silent inbox checks, and recurring digests in plain language, or wake an agent from any other system with a single HTTP request. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Imp runs large AI chat models privately on one NVIDIA RTX 50 or RTX PRO graphics card, exposing them through OpenAI and Anthropic compatible APIs plus a built-in browser chat. Start it with a single Docker command, point it at a model, and the chat opens in your browser with saved conversations and a live readout of generation speed. Coding agents such as Claude Code and Codex connect by changing one base URL, so your editor talks to the model on your own hardware instead of a rented cloud endpoint. Tool calls, structured JSON output, streaming responses, and reasoning models all work over the wire, and requests can be protected with an API key, per-IP rate limits, and concurrency caps. Load GGUF files you already have or NVFP4 and FP8 SafeTensors checkpoints straight from Hugging Face with no conversion step before the first answer. When a model is bigger than the card, mixture-of-experts weights stay in system RAM while the busiest experts are cached on the GPU, so a 123.6 GiB model still answers from a 32 GB card. Supported models can also read images alongside text, and tokenize, health, and model listing endpoints make the server easy to wire into scripts and monitors. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

One server, treated properly: Nanocl runs your containers and full virtual machines from a single declarative Statefile, reconciling what is running against what the file says, so a lone host gets cluster discipline without cluster ceremony. Containers group into Cargoes with replica counts, ordered init containers, and health-aware restarts; finite jobs run to completion and stop. When a workload needs a real kernel or a custom disk image, it boots as a QEMU virtual machine beside the containers instead of forcing a second platform. Publishing is built in: the proxy controller terminates TLS and routes HTTP and TCP traffic, and the DNS controller keeps service names resolving while workloads come and go. Secrets for registries, certificates, and environment variables attach where they are used, never inside the file itself. The daily loop is a CLI and an API: list processes, follow logs, exec into a container, watch events, and back up the entire deployment state before you change it. Namespaces keep projects apart on the same host, and Statefile arguments, templates, and sub-states carry one definition from staging to production. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT or Apache-2.0 licensed.

Your next business system does not need a year of scaffolding: Open Mercato hands you a running CRM, ERP, and commerce back office, and your team builds only the logic that makes your company different. Deals and pipelines live next to the product catalog, so a quote pulls real variants, price lists, and stock without swivel-chair exports. Orders flow into invoices, shipments, and payments in one motion, while warehouse lots and stock movements keep fulfillment honest about what can actually ship today. Customers and partners stop emailing your team for status: the self-service portal takes B2B orders, shows tracking, and files warranty claims directly. When a record needs a field nobody planned for, an administrator adds the custom entity from the panel, no migration deploy, and shapes its lifecycle with per-tenant workflows and business rules. Every change lands as an auditable command with an author attached, so mistakes get undone, sensitive columns get encrypted per tenant, and several companies share one install without seeing each other's data. Storefronts and mobile apps plug into generated REST APIs with OpenAPI documentation, attachments turn searchable through OCR, and AI coding agents extend the system because the architecture conventions are written down for them. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

GEOInflow is a self-hosted analytics platform that shows website owners which AI crawlers visit their pages, what those crawlers read, and how much traffic and revenue AI search actually sends back. Import a sitemap, CSV, or JSON inventory and the coverage report compares it against observed crawl logs, flagging important pages that no AI crawler has ever requested and directories where coverage keeps dropping. The built-in catalog recognizes 61 AI crawler identities, including crawlers from OpenAI, Anthropic, Perplexity, Google, Microsoft, ByteDance, Baidu, Kimi, and Tencent Hunyuan, and separates training, AI search, and user-triggered visits. Verification combines declared user agents with official IP ranges and DNS evidence, so a spoofed crawler name never counts as a confirmed visit. Browser tracking connects AI search referrals to landing pages, custom events, goals, funnels, and conversions, letting teams measure whether visibility in AI answers turns into signups and sales. Alongside the GEO reports, teams get pageviews, unique visitors, referrers, geography, devices, heatmaps, retention, and visitor paths, with CSV, JSON, and ZIP exports for any selected scope. Workspaces, team permissions, and public sharing links let agencies and publishers give each client or department its own dashboards without exposing raw data or other sites. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

HomeHub gives a household one private page for the everyday coordination that usually scatters across chat threads, fridge notes, and five separate apps. Pin shared notes where everyone sees them, drop files into the shared cloud for the house, and keep one shopping list the whole family edits, with suggestions drawn from what you bought before. Chores become a shared checklist, the calendar holds the dates that matter, and a who's-home view answers the question every family group chat asks in the evening. The expense tracker follows family spending and handles recurring bills like the milk, the newspaper, and subscriptions, while the recipe book and expiry tracker keep the kitchen honest. Small utilities round it out: download media straight to the server, shorten URLs, compress PDFs, generate QR codes, and check the weather without leaving the hub. Every feature toggles on or off in one config file, themes recolor the interface, and there is no account system at all, because the hub trusts your home network instead of a password database. It runs happily on a Raspberry Pi, installs as a PWA on phones, and keeps uploads, media, and data in mounted folders you can back up with any file tool. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Pomodoist pairs a task manager with a Pomodoro timer, so the list of what to do and the clock that gets it done live in the same app. Type a task the way you would say it and the quick-add bar sets its priority and estimates its Pomodoros as you type, filing it into the Inbox, Today, or Upcoming views. Plan the week on a calendar, drag cards across a kanban board, spread work along a timeline, or sort it into a four-quadrant priority matrix when everything feels urgent. Start a focus session and the timer tracks intervals against the task at hand, with configurable work and break lengths, while a 3D desktop companion focuses, rests, and celebrates along with you. Share a project and the discussion stays beside the tasks, with comments on shared items and the team's focus time visible next to the work itself. Reports chart weekly focus time, completed tasks, and habit streaks, and voice notes can become task checklists when typing is not an option. An MCP endpoint lets your AI tools manage the same projects after an OAuth sign-in, and optional Google Calendar and Telegram integrations meet the planner where you already are. The self-hosted instance unlocks every feature locally, with your own accounts and one-command backups of the whole database. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

House Planner holds the design of your house in one browser workspace, from true-scale floor plans drawn over a satellite photo of your plot to costed wiring, plumbing, sewer, and heating layouts. Draw walls at true scale in millimetres with thickness and materials, add doors, windows, garage gates, and furniture with true dimensions, and watch room areas and plot coverage total as you work. Flip into 3D for a massing model or the house finished with material textures and facade colours, with cut-down walls for reading the layout from above. Every utility network gets an engineering layer: route sewer lines to a septic tank with slopes and cleanouts, auto-route electrical circuits with breaker and voltage-drop checks, and run water piping from well and boiler to each fixture. Underfloor heating loops lay out room by room, split before 80 metres, and balance flow against heat loss. The bill of materials computes quantities from the plan and networks, producing a priced estimate you can print, tick off as you buy, or export to CSV. Every save is a numbered version with restorable snapshots, tabs cannot overwrite each other, and the JSON plan can be edited by an AI assistant through the same API. One password guards the project, phones get a read-only view for on-site checks, and the whole thing runs in one Docker container with no database. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Tapflow puts your team's iOS simulators and Android emulators in every teammate's browser, so QA stops queueing for the one Mac that happens to have the right build installed. A relay server you host serves the dashboard and API, stores your builds and recordings, and keeps accounts and device control on infrastructure you own. Agents on your Macs connect out to the relay and drive the simulators already installed there, injecting touches directly without WebDriverAgent or any cloud device pool. From the browser you tap, swipe, and pinch at about 30 frames per second, open deeplinks from the QA toolbar, sync the clipboard both ways, hear device audio, and cut the network to see how the app copes offline. The App Center takes .app.zip and .apk uploads and tracks each build from backlog to done, and sessions can be recorded and shared before the relay purges them after about 72 hours. CI pipelines and AI agents get a screenshot endpoint and scoped access tokens, deterministic YAML flows replay checks with a JUnit report, and roles keep viewers, QA, developers, and admins in their lanes. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Rakazo lets you hire AI bots the way you would onboard teammates: each gets a job, persistent memory, its own sandboxed computer, and a schedule, and it reports back in chat while you check in from any device. Start from templates such as Sales Outbound, Inbox Manager, Talent Scout, Expense Manager, Coding Agent, or Chief of Staff, then tune the instructions, tools, and limits until the bot works the way your team works. Every bot can run on a different model, so research uses one provider while coding uses another, and a local model served by Ollama or LM Studio keeps sensitive work off third-party servers. Bots work on real computers with a browser, terminal, file system, and graphical desktop you can watch or take over, choosing shared team computers or isolated private ones. When a task outgrows one bot, it delegates pieces to peer bots or short-lived subagents and folds their results back into its own thread. Voice mode lets you dictate messages and hear spoken replies, while routines run on schedules so follow-ups, reports, and inbox sweeps happen while you are away. You decide which actions need your approval before a bot takes them, and integrations via Composio, Pipedream Connect, MCP servers, and OpenAPI documents connect bots to tools you already use. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Most team chat keeps people in one app and AI agents in another; Octo Server is the backend that puts both in the same conversation. It powers the OCTO workplace, where Lobsters, the platform's OpenClaw-powered AI agents, sit in channels as first-class participants that read context, run tool calls, and report back alongside their human teammates. Every request flows through one pipeline: token and cookie authentication, organisation-aware role checks and per-channel permissions, business logic that can start or resume an agent session, then fan-out through WuKongIM for real-time delivery. Channels support threaded subspaces, shared files, and a GROUP.md document that stores the group's standing context where the whole team can edit it. The smart summary service reads busy channels and produces structured digests, so catching up means reading one brief instead of hundreds of messages. External bridges connect conversations to GitHub, WeCom, Feishu, and Loop through adapters, and webhooks push group events to your own systems. The official one-command deployment runs the server with the web client, admin console, task service, WuKongIM, MySQL, Redis, and MinIO behind nginx, scaling as one backend that every client speaks to. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

ODS turns a GPU machine or server you already own into a complete private AI stack with a single install command, replacing a shelf of separate tools with one system that serves models, chat, agents, automation, and search from your own hardware. The installer reads your GPU, VRAM, memory, and disk, then downloads a GGUF model matched to that hardware tier, and a compact bootstrap model starts answering within minutes while the full model finishes downloading. From the web dashboard you watch every service's health, ports, and resource use, restart what misbehaves, and check storage and updates without touching a terminal. You chat with local models in Open WebUI, hand background work to the Hermes and Portal agents, and build automations in n8n that connect the stack to more than 400 other apps. Documents you add become searchable knowledge through Qdrant vector storage, so answers cite your files instead of the model's memory. SearXNG and Perplexica answer web questions without trackers or accounts, Whisper transcribes speech, Kokoro reads text aloud, and ComfyUI generates images, all on the same box. Every bundled service is an extension you can enable, disable, or replace, and a Privacy Shield scrubs personal data before anything reaches an optional cloud model through the LiteLLM gateway. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

DramaClaw is a self-hosted production line that carries a manuscript or screenplay all the way to a finished AI drama, handling story structure, characters, storyboards, voices, and final cuts inside one workspace. Drop in a novel manuscript or a Fountain screenplay and it builds episodes, characters, and scenes for you, then plans multi-episode arcs and writes scripts in adaptive, literal, or staged modes with review-and-repair loops. The shared asset library keeps every character, scene, prop, and voice organized once, so faces stay consistent across episodes while portraits and per-episode variants handle costume and age changes. Storyboards and first frames are generated beat by beat, emotion-aware voice-over is synthesized per character, and episodes are assembled and exported with subtitles and the full asset pack. For finer control, the XiaHua canvas gives you 18 node types for images, video, audio, scripts, and 3D sets, with a wall of 45 short-drama styles and tools for relighting, outpainting, upscaling, and camera moves. Xia Director, the built-in agent, turns a plain-language brief into a node graph, runs it with progress tracking, and can promote winning results from the canvas back into the series. You pick the models: paste an official gateway key, or route Seedance, Kling, Hailuo, Sora, ComfyUI, and other channels through the bundled gateway, while external agents drive the same pipeline over MCP. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Elastic License 2.0 licensed.

AIHOT is a self-hosted engine for running your own AI news site: it watches the sources you choose, scores every story twice, and publishes only the coverage worth reading. Point it at RSS feeds, web list pages, JSON APIs, X accounts, WeChat public accounts, or content pushed in by scripts, polled on schedules you control. After deduplication and pre-screening, every story faces two independent scoring passes under the same rubric, so one generous run cannot wave a weak story through. Coverage of the same story clusters into one event across the last two weeks, so forty outlets on one launch read as a single developing story. Hotness is measured per event: each source counts once per 48 hours and its weight halves daily, so repeat posting cannot inflate the ranking. Digests compile on schedule: a daily edition at 08:00, a weekly review on Mondays, and a monthly rollup on the first, assembled by rules without model calls. Readers browse topic pages by company, research direction, and content form, search titles, summaries, and full text, and keep local favorites with export and import. From the admin backend you can test sources, correct scores by hand, calibrate selection against labeled samples, and swap the model behind each pipeline step. Output flows through RSS, a public API, MCP, agent Markdown, and llms.txt, so humans and AI agents can subscribe. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.