ChatterMate gives your website an AI support agent that answers customer questions from your own documentation around the clock, and hands the conversation to a human the moment it gets complicated. Feed it PDFs, help pages and URLs, and it chunks and indexes them into a knowledge base that answers with citations instead of guesses. Pick your model from OpenAI, Anthropic Claude, Google Gemini, Mistral, xAI Grok, DeepSeek or Groq with your own key, or point it at a self-hosted Ollama or vLLM endpoint. Every conversation lands in one shared inbox across nine channels, including the website widget, WhatsApp, Instagram, Messenger, Slack and email, where your team can search, filter and reassign. A drag-and-drop workflow builder designs branching flows from AI response, condition and human transfer nodes, so routine questions resolve themselves and hard ones arrive with context. Chats can raise tickets that the AI triages and investigates, writing an auditable root-cause analysis, or open a Jira ticket without leaving the conversation. The native Shopify integration answers order, shipping and product questions from live store data, and customers can attach images, PDFs and documents directly in chat. Theme the widget to your brand, require token authentication for private chats, and connect MCP tools so the agent can look up orders, issue refunds and call your APIs mid-conversation. 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.

Creative teams use Shumai to review video, images, 3D models, and documents with feedback pinned to the exact frame, on a server they control instead of a rented review cloud. Pause on any frame, draw on the picture, and leave a timecoded comment with the markup attached, then let threaded replies, mentions, and resolve states carry it to a decision. Every cut stacks into a version stack, and any two versions open side by side to compare changes. Layered PSDs and camera RAW review at full resolution, 3D models spin with comments pinned to the viewing angle, and documents page through as converted PDFs. Clients open a share link with a password and expiry date, downloads switchable, and can comment as guests with no account. Watermarks render into the media on your server rather than layering in the browser, so they stay put wherever the file travels. Comments export as Premiere Pro XML, DaVinci Resolve EDL, Final Cut Pro, or Avid files with correct drop-frame timecode for the editor. Mention the AI agent in a comment and it examines the same frame under discussion, or chat privately about a folder using your own OpenAI, Anthropic, or Gemini key. Originals live on local disk or any S3-compatible bucket, with GPU transcoding and workers that scale up for a delivery and back to zero. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Instead of burying your documents in a vector index you cannot inspect, LLM Wiki v2 files them into a Markdown wiki you can read, browse, and question. Drop text, Markdown, or PDF files anywhere on the page and each one is catalogued automatically, filed into a folder that says what it holds, and linked to the notes it relates to. Ask a question and the answer cites the exact notes it used, with clickable sources you can open, verify, and correct. New documents update the note on their subject instead of piling up as disconnected chunks, so what you teach it stays taught. A small classifier routes filing and questions through the folder tree, keeping the wiki quick and cheap as it grows, and you can browse the tree, follow see-also links, move or delete notes, and watch the tokens spent by both the model and the classifier. Connect OpenRouter, OpenAI, Gemini, a local Ollama, or any compatible endpoint, and expose the same wiki to Claude Code or Codex as long-term memory they can recall from and write to. Because every note is plain Markdown in a folder you own, the whole knowledge base can live in git beside your other files. 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.

Designed for developers on the go, Yep Anywhere turns any smartphone browser into a full-featured control center for supervising, steering, and reviewing autonomous AI coding agents. Operators can monitor live execution across multiple active projects simultaneously without sitting at a desktop terminal. Real-time reasoning feeds. Instant push alerts for permission prompts. One-tap tool approvals. Developers can unblock pending tasks mid-turn, redirect active workflows, or queue sequential follow-up prompts for automatic delivery at the next safe milestone. An integrated source control viewer displays syntax-highlighted working-tree and commit diffs, allowing reviewers to attach line-level comment bundles directly back into the agent context. Mobile voice transcription lets users dictate instructions straight into running sessions, while photo library integration makes uploading bug screenshots effortless. All agent credentials, CLI configurations, and repository data remain private on the host server without requiring third-party cloud database accounts or proprietary device pairing. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Cron ran the job, or maybe it did not; Runwisp makes the answer impossible to miss. One small binary replaces both crond and your process supervisor: list scheduled jobs and long-running services in a single runwisp.toml, and it runs the jobs on time, restarts services when they crash, and keeps every line they print. Every run leaves evidence: exit code, duration, timestamps and full stdout and stderr, searchable across a task's whole history, with CPU and memory shown next to what that task usually uses. When a run fails, the dashboard shows why, with stderr and the end reason beside the retry button, and alerts head to Slack, Discord, Telegram, ntfy, Gotify, Pushover, email or a webhook before you find out the hard way. Missed runs catch up after downtime, overlapping runs queue, skip or kill by policy, and services get restart backoff and graceful shutdown. Manual runs take typed parameters, so the dashboard generates a form with choices and defaults from your config. Long output streams live with progress bars redrawing in place, and the same history opens in a terminal UI over SSH. The config file stays the source of truth: interfaces trigger and inspect, they never edit your TOML. No database to run, no runtime to install, just the binary and its embedded storage. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-3.0 licensed.

Catalog, rate, and analyze every film you watch with Movary, a self-hosted movie tracking hub and personal cinema diary that replaces Letterboxd and Trakt. Each time a movie finishes playing on Plex, Jellyfin, Emby, or Kodi, automated webhook scrobblers record the viewing session and star rating directly into your timeline without manual logging. You can also bring over years of existing watch history by importing exports from Letterboxd, Trakt, or Netflix, and automatically cross-post newly logged reviews and ratings to Mastodon or feed Watchlist additions straight into Radarr. Customizing your personal dashboard lets you rearrange analytical widgets that break down your viewing habits by most-watched actors, directors, genres, original languages, release decades, and custom watch locations like local cinemas or home theaters. Movie metadata, posters, and ratings pulled from TMDB and IMDb are cached locally on your server, while built-in background job schedules keep artwork and cast details refreshed automatically. Multi-user account controls, TOTP two-factor authentication, granular profile visibility settings, and personal Bearer API tokens make it easy to run a private household log or a shared film club server. 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.

After the bills are covered, how much is actually safe to spend? monetr organizes an entire budgeting application around that one question. Inspired by the defunct Simple bank, it budgets paycheck by paycheck rather than month by month. Funding schedules encode when you get paid - including multiple schedules per account and a weekend-exclusion option for deposits that land early - and every expense or savings goal is tied to one. monetr then calculates how much of each recurring obligation (rent, car payment, subscriptions, on any repeat interval) to set aside from each paycheck, so a large bill never has to come out of a single check. What remains after allocations is surfaced as Free-To-Use, and a forecasting timeline projects contributions, due dates, and leftover funds forward so low-balance periods are visible before they happen. Transactions arrive either as OFX uploads from your bank or automatically through a Plaid connection using your own API credentials, keeping balances and transactions synced without manual entry. The app is mobile-friendly and installable as a PWA on desktop or phone. Self-hosting via Docker Compose is completely free, with all source code public and your financial data on your own hardware.

Stop hunting for a public mirror that still works this week: MirrorProxy puts every software source your builds depend on behind one domain you control, so GitHub releases, container images, npm and PyPI packages, and operating-system repositories all come from the same stable gateway. Point it at a source and it fetches and caches on demand, with no full mirror to store or sync, and when an upstream times out or starts rate-limiting, it fails over to the next endpoint and keeps your builds moving. Around thirty adapter types cover the everyday sprawl: Docker Hub and nine other registries, Cargo and Go modules, Maven and NuGet, Homebrew and WinGet, and more than thirty Linux and BSD distributions, plus custom static repositories you define yourself. Sharing the gateway is safe: invite users, set monthly quotas per person or team, restrict which sources each team may use, and gate access with rate limits and IP rules, while the console shows traffic trends, visitor regions, cache behavior, and the health of every source. Email and webhook alerts warn you before a quota runs out or an upstream outage drags on, and the cross-platform client switches a workstation's sources to your gateway and back. 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 server already runs your apps; PhreshOS gives it a desktop. Install the System once and every Program you add gets a window on a real browser desktop, complete with taskbar, start menu, and a plane of views you can spread work across. Close the browser and nothing stops: each Program's server keeps running on the machine, holding its data and state, and when you open the Desktop again the windows are exactly where you left them. The System handles the groundwork every small web tool normally rebuilds for itself: one sign-in for the owner, permissions that decide what each Program may reach, storage and uploads, logs, and messaging between Programs, so a new tool only brings its own logic. Everyday pieces like the file manager, Settings, and even the wallpaper are Programs too, and an appearance changes colors and motion across the whole desktop at once. The same Desktop opens in several browsers simultaneously, each with its own view and scale, and AI agents work alongside you through the same Programs and APIs you use. When you want another tool, you create it as a small web project and its window appears on your desktop. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Ollaya serves decision models that answer typed questions about a message, ticket, or document with calibrated probabilities, through a self-hosted API shaped like the hosted service it can replace. Send a state, which can be an email, a support ticket, or any JSON, plus typed choice, score, and yes or no questions, and the model answers in one forward pass in milliseconds without generating text. Pull models by name the way Ollama users already know, with run, list, ps, show, copy, and remove commands managing the local store. Downloads verify every layer against its sha256 digest, resume when interrupted, and share blobs between models so storage stays lean. Existing TypeSafe code keeps working by changing one environment variable, because the /v1/systemone and /v1/decisions endpoints are wire-identical and the official SDK sends its key the same way. The native /api adds routing information and timings, model loading and unloading, and streamed pull progress for your own tooling. Put it to work triaging inboxes, routing requests to the right model or team, screening prompts for injection and jailbreak attempts, or replacing per-token LLM classification calls with a local answer. Agents reach the same engine through the bundled MCP server, and LiteLLM, LangChain, DSPy, LlamaIndex, n8n, and Dify connect through their existing integrations. 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.

Ech0 is a self-hosted personal microblog that gives you a public timeline of short posts, links, and media on your own domain, with no ads, algorithms, or subscription in the way. Write in a Markdown editor with live preview, organize posts with tags, and let links and GitHub projects unfurl into rich cards while Bilibili and YouTube videos play inline. Attach images, audio, and video to any post, browse them in an inline gallery with built-in players, and manage uploads in a visual file manager. Visitors can like, share, and comment, you moderate from the panel with captcha protection, and RSS lets readers follow without an account. Sign in with passkeys, OAuth2, or OIDC, issue scoped access tokens, and run extra accounts under Owner, Admin, and regular roles. Media can sit on local disk or any S3-compatible bucket, and snapshots, scheduled backups, and portable capsules move the whole timeline to another instance or compile it into a static site. Ech0 Copilot recaps recent posts in one click and lets you chat with your own archive, while an MCP server, webhooks, and a documented API connect AI assistants and automations. Follow live logs in a web console, administer from a terminal UI or CLI, and install it as a PWA with dark mode and multiple languages. 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.

Started as an ExpenseOwl-inspired project, Wally grew into a lightweight, self-hosted expense tracker more capable in every direction its author touched. The backend is Python FastAPI over SQLite, which means every deployment ships a full REST API with interactive documentation at /api/docs - automating imports or wiring in external tools requires no reverse engineering, and when the optional login page is enabled you can mint scoped API keys from the Settings page for token-based integrations. The transactions view is built on AG Grid, bringing real search, column sorting, and per-column filtering to your ledger, with a footer totaling rows, income, and expenses for whatever slice you have filtered. Dashboards go beyond the usual monthly doughnut: a Change button swaps in year-scale line graphs so you can track a single category - restaurants, say - across time. Recurring transactions edit intelligently, letting you apply changes to all instances or only future ones. CSV import and export use a simple six-column format handled from Settings, the refined dark theme is genuinely easy on the eyes, and the interface is translated into more than ten languages. The whole thing runs from one small container with a single data volume.

Mail for your own domain stays on your own server with mailez, a self-hosted stack that delivers over SMTP, IMAP, and POP3 and adds a webmail, calendar, contacts, file storage, and an admin console, all started with a single command. Readers get a draggable three-pane webmail that updates itself over a push channel, merges replies into conversations, folds quoted history, and searches with from:, to:, has:attachment, and date terms. Keyboard shortcuts, a command palette, snooze, scheduled send, undo for bulk moves, and quick reply keep daily mail fast, and the interface installs as an offline-capable app with light and dark themes. Privacy-minded users add PGP signing and encryption, two-factor login, and remote-image blocking, and write server-side rules in a Sieve editor. Calendar, contacts, and Drive sit beside mail, with ICS subscriptions, vCard import, CardDAV and CalDAV sync, and share links. Phones and desktop clients configure themselves through autoconfig. Administrators manage domains, mailboxes, aliases, relays, and external mailbox fetching in one console, generate DKIM keys with a click, and follow a DNS wizard and a health page that verify MX, SPF, DMARC, DKIM, blocklists, and MTA-STS. Audit logs and role-based access keep shared servers accountable. The free community edition runs on a single node, while archiving, DLP, LDAP, ActiveSync, and AI features belong to the paid enterprise edition. 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.

Eliminating repetitive sponsor reads and dynamic mid-roll commercials before an episode even reaches your headphones, MinusPod operates as a self-hosted podcast ad-removal server and RSS feed manager. You subscribe to shows inside the web dashboard using PodcastIndex search or OPML import, and the server generates clean replacement RSS feeds compatible with Pocket Casts, Overcast, Apple Podcasts, and Audiobookshelf. When a new episode drops via scheduled polling or instant Podping notifications, the pipeline transcribes the audio locally with faster-whisper or Parakeet, or routes it through a remote transcription API. Your choice of LLM provider, including Ollama, Anthropic Claude, OpenRouter, or any OpenAI-compatible endpoint, scans overlapping transcript windows to pinpoint sponsor reads, cross-promotions, and intros. Programmatic audio analysis reinforces AI detection by measuring EBU R128 loudness jumps, Chromaprint acoustic fingerprints, show jingles, and dynamically inserted ad transitions before FFmpeg splices the audio or marks segments as skippable Podcasting 2.0 chapters. A browser-based Ad Editor lets you audition pre-cut and post-cut audio, nudge start and end timestamps, and confirm detections that train global, network, and show-specific sponsor patterns. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

DocsMint is a self-hosted knowledge workspace where your team writes documentation once and both people and AI agents retrieve it through hybrid search and a built-in MCP server. Documents live in a rich visual editor with Markdown import and export, organized by folders, categories, and tags, with sharing and version history. Search blends exact title matches, multilingual keyword search, typo-tolerant fuzzy matching, and semantic vectors, then widens results through graph relationships between documents, so a query in one language or phrasing still finds the right page. Every edit quietly refreshes the index in the background; nothing needs manual re-embedding. Agents connect through 22 MCP tools covering search, reading, creation, updates, folders, snapshots, and export, over a local stdio bridge or the HTTP endpoint on your own installation. Category-scoped API keys hand each integration only the slice of the library it may read, edit, or write, while a global key serves trusted automation. The same operations are available through the REST API, a typed TypeScript SDK, and a terminal CLI for scripts. The web application installs as a PWA with offline reading, and AI features run on your choice of an OpenRouter key or a fully local Ollama setup. 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.

When hosting multiplayer game servers for communities or friends requires container isolation and low-overhead administration, Calagopus steps in as a modern game server management panel. Server operators use it to deploy and control Minecraft, Rust, ARK, Valheim, FiveM, and any other Linux containerized workload while reusing existing Pterodactyl and Pelican eggs without modification. From the live WebSocket console, administrators monitor real-time CPU, memory, and network graphs, autocomplete saved command snippets, inspect per-layer Docker image pull progress bars, and pop the terminal out into a secondary window. Managing configuration files and modpacks happens directly in the browser through a split-pane tabbed editor featuring real-time collaborative editing, side-by-side revision diffs with one-click rollback, a visual disk usage treemap, in-place archive browsing, and VS Code workspace mounting. Database workflows are equally streamlined: you can provision MySQL, PostgreSQL, MongoDB, or Redis instances, browse and edit rows or SQLite files in a built-in data explorer, and run read-only or writable SQL queries without external database clients. Automated schedules support conditional if-else branching, regex variable extraction from console output, crash-detection triggers, and eight backup storage drivers including S3, Restic, Kopia, ZFS, Btrfs, and Proxmox Backup Server. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Public registries rate-limit your CI, log every pull, and pick the worst moment to go down; Nora replaces that dependency with a self-hosted artifact registry that hosts and caches seventeen package formats behind a single address. Point Docker, Maven, npm, pip, Cargo, and eleven other clients at one endpoint, and Nora serves your private artifacts while transparently caching upstream packages fetched from Docker Hub, Maven Central, npmjs, and crates.io. Each base image or library downloads once and is then served locally, so builds get faster, stop tripping rate limits, and survive upstream outages. Curation rules decide what is allowed to reach your builds: allowlists and blocklists filter packages by name, minimum release-age rules hold back freshly published versions, and new digests can wait in quarantine until approved. Anything you publish keeps its name: a hosted package is never silently replaced by an upstream package sharing it. Pipelines publish without stored secrets through OIDC identity from GitHub Actions and GitLab CI, and API tokens with read, write, and admin roles cover the rest. A web dashboard shows downloads, cache hit rates, storage usage, and recent activity for every registry, and audit logs plus Prometheus metrics feed your monitoring. For disconnected networks, a mirror command prefetches whatever your lockfiles name, an import tool migrates Artifactory or Nexus repositories, and backup and restore keep a spare copy. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.