Sage Wiki turns a pile of unstructured documents into a fully interlinked, searchable wiki by running them through a five-pass LLM compiler pipeline. Inspired by Andrej Karpathy's vision of LLM-compiled knowledge bases, the pipeline processes source files through diff detection, summarization, concept extraction, image captioning, and cross-reference discovery, with parallel LLM calls and checkpoint/resume for vaults scaling to 100,000+ documents. The typed ontology graph stores entities and relations with BFS traversal, configurable relation types, multilingual synonyms, and a promotion/demotion lifecycle backed by grounding verification and consensus scoring. Multi-format ingestion handles Markdown, PDF, Word, Excel, PowerPoint, EPUB, email, CSV, images, and code files without manual tagging. LLM provider support spans Anthropic, OpenAI, Gemini, Ollama, and any OpenAI-compatible API, with per-pass model routing enabling cost optimization by assigning cheaper models to simpler tasks. The built-in MCP server exposes 17 tools over SSE transport for integration with Claude, Cursor, and any MCP-compatible agent, while native Obsidian vault overlay ensures existing note workflows remain undisrupted. Team deployment supports Git-synced shared wikis, centralized server access, and hub federation across multiple projects. Ships as a single Go binary with Docker Compose multi-arch images serving the web UI on port 3333. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

To listen to your favorite YouTube channels, video playlists, and Bilibili creators during a commute without keeping a browser tab open, PigeonPod converts video subscriptions into private, standard podcast RSS feeds for any podcast player. Paste a channel URL, playlist link, or single video address to preview uploads and generate a protected feed for Apple Podcasts, Overcast, Pocket Casts, or AntennaPod. You can select audio-only or video output, customize bitrates and formats, and generate Podcasting 2.0 chapter markers for topic scrubbing. Scheduled background sync jobs fetch new releases automatically while on-demand history backfill queues older catalog episodes in bulk. Per-feed keyword rules, duration thresholds, and retention limits keep storage clean by filtering out shorts or marathon livestreams. Upload YouTube or Bilibili cookies for member-only streams, route traffic through custom proxies, and update the yt-dlp engine directly inside the web dashboard. A built-in web player, one-click public episode share pages, and OPML export let you stream in the browser or migrate subscriptions. Media files store on local disk or S3-compatible buckets such as Cloudflare R2 and MinIO, accompanied by YouTube API quota monitors and failure alerts. Multi-user role permissions support shared accounts across eight interface languages. 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.

Combining Docker container labels with a live web control plane, DockFlare automates Cloudflare Tunnel ingress routing, multi-zone DNS records, and Zero Trust Access policies across self-hosted infrastructure. DevOps engineers and homelab operators can attach simple container labels to expose HTTP, HTTPS, TCP, SSH, and RDP services publicly in seconds without clicking through external cloud dashboards. For non-containerized workloads such as bare-metal hypervisors or network appliances, administrators can define manual ingress rules, path-based routes, custom TLS SNI headers, and origin certificate bypass flags directly in the web interface. Security teams use reusable Access Groups and wildcard zone policies to enforce Google, GitHub, Azure AD, or custom OIDC authentication across every subdomain from a single policy definition. Distributed deployments connect lightweight remote agents back to the primary controller using Zero Trust service tokens so multi-host clusters share one unified routing view. When containers stop or restart, configurable grace-period timers prevent accidental route churn before cleaning up stale DNS entries, while encrypted state backups protect your entire ingress configuration. 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.

One REST call, 130+ notification services: Apprise API wraps the well-known Apprise library in a lightweight Django/Gunicorn microservice, so "send an alert" works the same whether it goes to Slack, Discord, Telegram, Teams, email, SMS, Pushover, or PagerDuty - each addressed by a simple URL scheme. It solves the credential-sprawl problem cleanly: instead of embedding provider tokens in every app, cron job, and CI pipeline, you centralize them here and everything else just POSTs a body and title. Two modes cover every workflow. Stateless calls to /notify carry target URLs in the payload (or fall back to a default set via APPRISE_STATELESS_URLS); stateful mode stores named configurations server-side under keys, so /notify/{KEY} fans out to everything registered - with tag-based routing (comma for OR, space for AND) selecting which endpoints fire per message. Messages take info, success, warning, or failure types in text, Markdown, or HTML, with attachments up to a configurable size. A built-in web UI manages and tests configurations, APPRISE_CONFIG_LOCK makes the store read-only, service allow/deny lists restrict which schemes work, webhook remapping adapts third-party payloads, and a Prometheus /metrics endpoint watches the gateway itself.

One binary is all that stands between you and every Kubernetes cluster you own: Kubewall opens a realtime web dashboard over all of them, with no agents to install and nothing phoning home. Switch between clusters from the sidebar and browse workloads, networking, storage, configuration, and access control in tables that update live as pods start, fail, and reschedule. Open any resource to inspect its overview, edit its manifest in the built-in YAML editor with validation, watch its events, or stream logs aggregated across pods and containers with search and tail controls. A command palette jumps straight to any resource type, while faceted filters and global search cut through thousands of objects by name, namespace, label, or image. Scale deployments, restart pods, trigger rollout restarts, and apply manifests with a click, or forward a cluster service to your local machine without memorising kubectl incantations. An integrated AI assistant, connected to OpenAI, Claude, Gemini, DeepSeek, OpenRouter, Ollama, or a local model, helps troubleshoot failures and review configurations right beside the resource it concerns. 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.

No spreadsheet has to track which service owns which port, because portracker discovers every service and port on your servers and keeps the list current from a self-hosted dashboard. Begin with a single port, shown with its owning service, its source (Docker or the host system), and its address, with internal container ports told apart from ports published to the host. Step back and ports gather into services: expandable cards carrying an icon, a health dot, and a port count, in list, grid, or table layouts, where a Why this status popover names the failing component and the rule that fired. Step back again and each server gets its own panel with hostname, OS, CPU, memory, and uptime, plus TrueNAS apps, VMs, and LXC containers once an API key is added. Step back once more and the whole fleet appears, because other portracker instances can be linked as peers, a VM's instance can be nested under its host, and every server can be searched at once. Along the way, rename services, hide the noisy ones, attach notes, act on a selection in bulk, or press Generate port for an unused number before deploying something new. Optional sign-in with a first-run setup wizard, an autoxpose link that shows public URLs and SSL status, light and dark themes, and keyboard shortcuts finish the picture. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

FireShare turns a folder of game captures on your server into a browsable library where every clip gets its own permanent link, ready to paste into Discord the moment something worth bragging about happens. Point it at the directories you already record to and it scans what is there: the file people watch is always your untouched original, in MP4, WebM, or MOV, never a recompressed stand-in. Privacy is set per file, public for the feed, link-only for friends, or behind a password, and whole folders can be shared as a single link. It also sorts the chaos for you, detecting the game in each capture and shelving hundreds of timestamped filenames under proper cover art you can search and browse. Trim the dead air off a clip before posting it, add a title, description, tags, and a custom thumbnail, and watch the view count climb. For screens that struggle with huge originals, optional transcoding adds adaptive lower qualities on CPU or an NVIDIA GPU, and HDR captures get tone-mapped to SDR instead of looking washed out. Friends can upload through the browser or by token from scripts, new public clips can announce themselves to Discord or an RSS reader, and accounts come with permissions, profiles, and two-factor sign-in. 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.

Archiving online videos, creator channels, and curated playlists directly into a personal Plex, Jellyfin, or Emby library becomes effortless with HomeTube, a self-hosted web downloader supporting more than 1,800 streaming platforms. Users paste a single video or playlist URL into the web interface, where an intelligent format analyzer evaluates available codecs and automatically selects the highest resolution video and audio streams such as 4K AV1 or VP9 paired with Opus audio. Built-in SponsorBlock integration detects crowd-sourced sponsor segments, intros, outros, and self-promotions during the download process so saved videos play back completely ad-free without manual editing. When synchronizing playlists, the engine tracks entries by unique video ID rather than mutable titles, downloads only newly added items, preserves upstream ordering with customizable filename templates, and optionally moves removed videos into an archive folder. A visual processing panel lets operators trim specific time ranges with keyframe or frame-precise cutting, embed primary and secondary subtitle tracks alongside chapter markers, and create nested destination directories directly from the browser. Browser cookie file support unlocks age-restricted or member-only streams, while custom yt-dlp argument pass-through accommodates proxy routing and filesize caps. Once processing finishes, completed files move into watched media folders and can trigger an immediate Jellyfin library rescan via API key. 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.

Jellystat is a self-hosted media analytics and live session monitoring dashboard for Jellyfin and Emby servers that turns raw streaming activity into detailed user, library, and playback insights. Media server administrators use the live dashboard to watch active streams in real time, inspecting transcoding status, client devices, bitrates, and playback progress as sessions happen. Every completed or partial stream is logged automatically so you can browse chronological watch histories, filter by library or stream type, and analyze peak concurrent streaming hours across the week. Dedicated library and user views break down total watch duration, play counts, and most popular movies, episodes, or music albums per account. If you already use the official Jellyfin Playback Reporting or Statistics plugins, you can import existing historical records directly into your instance without losing past data. Built-in database backup and restore tools, automatic library synchronization tasks, IP geolocation via MaxMind GeoLite, and interactive Swagger API documentation at the /swagger endpoint round out the administrative toolkit. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Somewhere in every organisation there is a folder called FINAL_v2 that nobody dares delete, and Drive from La Suite exists to end that. It gives teams a shared file space where uploads land in organised workspaces, versions stay findable through search, and every file or folder carries its own access list. You preview PDFs, images, audio, and video in the browser, and office documents open for editing through Collabora or OnlyOffice without downloading a thing. Sharing reaches outside the organisation too: invite external partners by link, even without an account, and revoke access the moment a project ends. Uploads pass malware scanning before they touch storage, a trash bin restores accidents, and quotas with usage metrics keep big archives honest. Administrators plug in their own OIDC identity provider, so logins follow the same single sign-on as the rest of the stack, while an embeddable file picker lets other internal apps reuse Drive as their document library. Because the data lives in your own S3-compatible storage, sovereignty requests stop being an argument with a vendor and become a setting. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Engineering teams and technical writers maintain operational runbooks, system documentation, and knowledge bases using LeafWiki, an open-source self-hosted wiki that stores page contents directly as human-readable Markdown files on the local filesystem. Authors can compose documentation through a dual-pane editor equipped with live HTML preview, keyboard navigation, autocomplete for internal links, and native rendering for Mermaid diagrams, KaTeX mathematical formulas, and collapsible callout containers. The navigational tree organizes complex documentation into explicit directory hierarchies and custom drag-and-drop page sequences tracked in lightweight configuration files rather than arbitrary alphabetical lists. An integrated SQLite engine indexes page content and custom taxonomy tags for fast full-text searches, automatic incoming backlink tracking, and automated broken link detection. System operators can deploy the single-binary application without external database servers or runtime dependencies, backing up the entire repository by copying the data directory. Administrators can provision granular user roles, configure reverse proxy header authentication for single sign-on gateways, and manage read-only API access keys for automated documentation scripts and continuous integration pipelines. Public viewers can browse technical notes without authentication or switch between dark and light high-contrast themes. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Maloja's one job is to be your own scrobble database, charting what you listen to from a server you control. Players and media servers that speak the native JSON API or a ListenBrainz, GNU FM, or Audioscrobbler 1.2 compatible protocol can scrobble with their own API keys. Vinyl sessions and background music can be logged by hand on a manual scrobble page. Existing history moves in from a Last.fm export, a Spotify data export, a ListenBrainz export, or another Maloja instance, while a proxy option forwards new scrobbles to Last.fm or a second Maloja server. The start page ranks top artists, tracks, and albums for today, this week, this month, this year, or all time, alongside a pulse chart of listening volume and a feed of the latest scrobbles. Artist and album pages add performance charts that follow chart position over time. Collaborations credit every artist on a track, and subunits, solo projects, and main acts can be combined or separated in charts at any time. Gold, Platinum, and Diamond awards mark tracks and albums that pass scrobble thresholds you set. Artwork can come from Last.fm, Spotify, Deezer, TheAudioDB, or MusicBrainz lookups, or from images you upload yourself. Week start, timezone, theme, and tile layout are all settings, and an API explorer lists endpoints for scripts. 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.

A drag-and-drop task board that works fine on its own and can also hand cards to AI coding agents, Veritas Kanban shows what each agent is doing, what it changed, and what is waiting for your approval. Start with no agents at all. Cards move through To Do, In Progress, Blocked, and Done, and each one carries subtasks, dependencies, time tracking, comments, and an activity log. When you are ready, connect Codex, Claude Code, Copilot CLI, Hermes, or OpenClaw, give every agent an Intern, Specialist, or Lead permission level, and follow each agent's status and model on a live dashboard. Let a task run in its own Git worktree, read the diff, leave inline comments, approve or request changes, and open a GitHub pull request from the task panel. Squad Chat gives agents one shared channel that posts spawned, completed, and failed events. Workflows chain steps with parallel branches, loops, and human approval gates. Policy rules allow, deny, or hold agent actions for review. Assistants reach the board through an MCP server, a command-line client, or a REST API. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Most link shorteners bloat a simple redirect service with heavy databases and invasive tracking scripts, whereas Chhoto URL delivers a fast, self-hosted URL shortener with custom slugs, QR codes, and privacy-respecting click counts. Paste any destination URL to generate a memorable adjective-name pair, a compact random UID, or your own custom alias in one click. Every shortened link redirects visitors immediately without interstitial splash pages, countdown timers, or tracking cookies. You can attach searchable notes to any entry, update the target URL after creation, and configure automatic link expiration timers down to the minute. Built-in QR code generation lets you preview and share scannable codes directly from the dashboard table. Real-time search filters links across slugs, destination URLs, and notes, while anonymous hit counters track total visits without logging visitor IP addresses. Administrators can run a private instance protected by OIDC single sign-on or Argon2-hashed credentials, or enable public mode so guests can shorten links with enforced expiration limits. Automation scripts and CLI tools can create, inspect, and delete links programmatically using API keys over the JSON API. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

When warehouse data never reaches the CRM, ad platform, or help desk that needs it, Multiwoven is the open-source reverse ETL platform that syncs it there on a schedule. Sources include Snowflake, BigQuery, Redshift, Databricks, PostgreSQL, ClickHouse, MariaDB, Oracle, Amazon S3, and SFTP. Models define what to move: write SQL with a 100-row preview, pick tables in a visual selector, or reuse existing dbt models. Destinations span Salesforce, HubSpot, Klaviyo, Mailchimp, Zendesk, Slack, Airtable, Google Sheets, Stripe, Facebook Custom Audiences, HTTP endpoints, and vector stores such as Pinecone, Qdrant, and Weaviate. Each sync maps model columns onto destination objects like Salesforce Account, Contact, or Opportunity, then runs as a full refresh or as an incremental sync that moves only new or changed rows, optionally tracked by a cursor field. Schedules can be manual, an interval from minutes to weeks, or a cron expression. A dashboard reports sync activity, each run records its status with successful and failed row counts, and failed runs can trigger status emails. Workspaces keep sources, models, syncs, and destinations separate for each team, while Admin, Member, and Viewer roles and email invitations control access. A connector framework lets teams add sources or destinations that are not yet supported. 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.

Before lifting a heavy four-unit storage server or rewiring a cramped network closet, you can map every unit of cabinet space in Rackula, an interactive drag-and-drop rack layout designer and capacity planner. Instead of staring at generic grey rectangles in a spreadsheet, you pull switches, routers, patch panels, UPS battery banks, and rackmount chassis from a hardware catalog populated with authentic front and rear faceplates from the NetBox device library. Equipment snaps cleanly to standard EIA-310 rack unit boundaries, while half-width gear and mini PCs nest inside one-unit carrier shelves and mounting brackets. Audiovisual technicians can group bayed cabinets side by side to plan amplifier racks, signal processor chains, and patch bays across multi-rack installations. Network engineers and data center operators can rearrange hardware with full undo and redo history, attach custom device graphics, and export crisp diagrams as PNG, SVG, or PDF files for runbooks and change control tickets. Sharing a proposed cabinet topology with a colleague in the field takes seconds using an encoded URL or a scannable QR code that opens on mobile browsers. Server-side persistence stores your rack definitions as portable YAML files and supports optional local accounts or OpenID Connect single sign-on for shared infrastructure teams. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Seatsurfing brings desk booking, room reservations, and parking management to interactive floor plans across multiple office locations, solving the coordination headache of hybrid work. The Go backend serves two React/TypeScript frontends through a single Docker container on port 8080: a Booking UI built as an installable Progressive Web App for mobile and desktop reservations, and an Admin UI for floor plan configuration, capacity enforcement, and analytics. Interactive floor plans accept uploaded office layouts where administrators visually place bookable spaces with per-space metadata and availability rules. Multi-location support handles organizations with distributed offices across multiple buildings and cities. The buddy system displays which colleagues have bookings on a given day, enabling team coordination without manual communication. Capacity management enforces occupancy limits per area with automatic denial when thresholds are reached. SSO integration supports OIDC and OAuth2 providers including Microsoft Azure AD, Keycloak, and Authentik for enterprise identity federation. Microsoft Teams and Confluence integrations embed booking directly into collaboration tools employees already use daily. The REST API enables automation and custom integrations, while the analytics dashboard tracks utilization rates, peak hours, and booking patterns. Docker Compose deployment requires only a PostgreSQL database with multi-architecture images supporting amd64 and arm64. 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.

BookLore centralizes personal electronic book, audiobook, and comic collections into an organized private media server equipped with automated metadata scrapers and e-reader synchronization. Users can drop EPUB, PDF, CBZ, and MOBI files into a watched BookDrop directory to trigger automated format parsing, background cover retrieval, and staged queue imports. Integrated metadata scrapers query Google Books, Open Library, Goodreads, and Amazon to automatically fill synopsis summaries, author records, publishing dates, and review scores. Dynamic Magic Shelves categorize volumes through custom rule-based filters, author collections, and full-text search indexes across your complete literature catalog. The browser-based reader renders documents with adjustable typography, night modes, audio playback controls, text annotations, and persistent bookmarking. Hardware e-readers and mobile devices connect through native Kobo Store emulation APIs, bidirectional KOReader progress synchronization, and OPDS catalog feeds. Multi-tenant permissions provide each household member with private reading statistics, personalized shelves, email book delivery, and direct send-to-Kindle dispatch. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GNU AGPLv3 licensed.