Pad
Your coding agents finish a session, close the laptop, and forget everything; Pad is where the project remembers. It holds the tasks, plans, bugs, ideas, and decisions in one workspace that you drive from a browser while your agents drive it from the terminal, so the next session, human or machine, picks up exactly where the last one stopped. You plan on boards, lists, and tables with drag-and-drop status columns, rich item pages, comment threads, and a dashboard that answers what needs attention and what to do next. Your agents read the queue, claim items, leave checkpoints, link their pull requests, and mark work fixed with the fixing PR attached. Conventions teach them the house rules once, like running tests before calling a task done, and playbooks hand them repeatable multi-step workflows they can invoke by name. Every change is versioned with its author, a person or a named agent, and new items appear in the browser the moment an agent creates them in the terminal. The same workspace is reachable three ways: the web interface, the pad CLI, and a bundled MCP server with a natural-language skill that plugs into Claude Code, Cursor, Codex, Windsurf, OpenCode, Copilot, Amazon Q, and Junie. 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.
Trina AX
Trina AX is a self-hosted AI workspace where your team chats with real Claude Code and Codex agents that work from your company's own folders, so answers arrive in your formats, with your figures, in your house style. Picture the first morning of a new hire: she asks for a client proposal, and the draft that comes back already reads like the team lead wrote it, because the agent found the same templates and numbers everyone else uses. Admins stock shared, group, and project folders once; everyone else just opens a browser chat on desktop or phone and asks. Nothing leaks sideways in the process, since every file an agent opens is permission-checked as the person asking, and a folder someone cannot see does not exist for their agent in answers, search, previews, or trash. The know-how that makes answers sound right becomes SKILL.md playbooks, governed like ordinary files, and the agent asks a person before editing one. Agents can run up to 150 tool rounds per answer, search the web, spawn sub-agents, and follow scheduled tasks, while admins read an activity log of files touched, never the private conversations themselves. Bring the company Claude or OpenAI account, set per-person usage limits, or route through an Anthropic-compatible gateway to models such as DeepSeek, Kimi, or GLM. 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.
JT-IPAM
Spreadsheets and sticky notes stop scaling the day your network grows past a rack or two, so JT-IPAM keeps every address, subnet, and device in one searchable system of record. Track subnets and individual IPs with their hostnames, MAC addresses, and owners, then reconcile what you documented against what scan agents actually find through ICMP, ARP, reverse DNS, and SNMP collection from routers and switches. Connect the DNS servers you already run, from PowerDNS and BIND 9 to Windows DNS and Technitium, and flag records that have no matching address in IPAM. Pull devices and virtual machines in from LibreNMS, Zabbix, Proxmox VE, ESXi, Hyper-V, and OpenStack so monitoring and address records stop drifting apart. Draw floor plans and rack elevations, trace a cable across multiple hops, and open an SSH terminal, SFTP browser, or RDP desktop to a device straight from its address page. Route new address requests through configurable multi-stage approval workflows, distribute certificates to web servers and firewalls from central encrypted storage, and keep a full audit trail of every change and console session. 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.
Subarr
Subarr is the coordination, measurement, and quality layer for Whisper subtitle generation, sitting between Bazarr, Sonarr, Radarr, and subgen to decide what gets transcribed, in what order, and whether the result is any good. Its Coverage walk scans your whole library and scores every subtitle gap with a reason: no track, embedded-only, Bazarr-wanted, audio mislabeled, or low quality. Queue a file, a folder, or an entire series from the Library tab and watch it move through probing, transcribing, and write-back on the dashboard. The Review queue plays you the actual dialogue, picked out by voice-activity detection, so you can verify a subtitle really matches the audio language before it lands. It flags files whose default audio track is not the original language and swaps tracks in place, heading off the double-translation trap. A provider leaderboard records which subtitle sources actually deliver for your library, and the Tuning Lab lets you tune Whisper recipes against your own media. Rules and scheduled walks keep the work flowing, with Tautulli now-playing signals boosting whatever you are about to watch. Finished subtitles are written next to your media, and your Plex or Jellyfin library refreshes the moment one lands. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Cupdate
Cupdate keeps a watchful eye on every container image you run, reporting which ones are outdated or vulnerable while deliberately never touching the update button itself. Point it at a Kubernetes cluster, a Docker socket, or Podman hosts (local or remote, one or several) and it inventories every image in use with no configuration to write. Each image is matched against its registry to find the newest available version, and the dashboard shows the gap between what you deployed and what you could be running, with release notes inline so the decision to upgrade takes seconds instead of a changelog hunt. Vulnerability data is layered on top from four sources: Docker Scout for Docker Hub images, Clair for participating Quay images, GitHub Advisories for images tied to repositories, and osv.dev correlation for images shipping SBOMs. A dependency graph explains why each image exists in your stack by showing which workloads pull it, which ends the "can I delete this?" guessing game. Subscribe to the RSS feed to hear about new releases passively, query the REST API to drive scripts that update compose files or kustomizations, or surface outdated and vulnerable counts in a Homepage dashboard widget. Prometheus metrics and traces are available when you want the watcher itself watched. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
SendPortal
SendPortal is a self-hosted email marketing platform for building subscriber lists, sending campaigns, and tracking exactly what happens to every message after it leaves your server. Grow the list three ways: add contacts one by one, import them in bulk from CSV, or push them through the API, which creates or updates subscribers by email address and attaches tags. Tags and custom segments organize audiences, sending product updates to power users and sale announcements to everyone else. A campaign pairs a subject line, which can insert first name, last name, and email placeholders, with an optional HTML template holding content, unsubscribe, and browser view placeholders. Automatic CSS inlining at dispatch keeps designed emails rendering properly in inboxes that ignore style sheets. Send a test email to yourself before anything goes out, then choose immediate delivery or schedule the campaign for later. Pick Queue Draft to review messages before they leave, or Send Automatically when the audience and content are already right. Open and click tracking, bounce records, and unsubscribe events then flow back through provider webhooks into per campaign reports and a searchable message log. Run several brands or clients side by side in separate workspaces inside one interface. Delivery runs through Amazon SES, Postmark, SendGrid, Mailgun, Mailjet, or your own SMTP server, so deliverability stays with providers built for it. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Skiff
Skiff is a self-hosted SSH manager that remembers every command you ran on your servers and exactly what it printed, so the fix you found at 2 a.m. last March takes seconds to find again. Open a host's history beside its terminal, or search commands and captured output across every host, filter to just the failed attempts, and expand an entry to see its full output. When you edit a small text file, Skiff reads it over SFTP and keeps the before-and-after diff and both versions, so you can see what changed instead of guessing. Useful entries pin to a host's notes, save as reusable snippets, or go back into the terminal with Run again, where you review and press Enter yourself. The browser is only a viewer: sessions live in the Skiff server process, so closing a tab or losing Wi-Fi does not kill your work, and you reattach with recent scrollback intact. Hosts organize into nested folders with favorites and full-text search, existing SSH configs import in one paste, and host keys pin on first connect with a loud warning if one ever changes. Credentials sit in an encrypted vault that locks itself after an idle timeout, team mode shares one vault with per-user logins, and there is no cloud account, telemetry, or agent to install on any target server. 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.
Piwigo
With over 3,800 GitHub stars and continuous development since 2002 spanning 24 years of active maintenance through version 16.4.0 released in May 2026, Piwigo has proven itself as one of the most battle-tested self-hosted photo gallery platforms available, trusted by professional photographers managing 150,000+ high-resolution images alongside small teams sharing event photos. The PHP backend with MySQL or MariaDB storage serves a responsive web interface that organizes photos into hierarchical albums with nested sub-albums, tag-based categorization, and smart albums generated dynamically from search criteria. Batch management tools handle bulk uploads, metadata editing, tag assignment, and album moves across thousands of images simultaneously. User permission controls define access at the album level with configurable public, private, and group-restricted visibility, while guest access allows public galleries without authentication. Image processing via ImageMagick or PHP GD generates multiple thumbnail sizes, watermarks, and responsive derivatives automatically. The plugin ecosystem with over 200 community-built extensions adds functionality from EXIF metadata display and GPS mapping to social sharing, download controls, and Lightroom synchronization for desktop workflow integration. The REST Web API with personal API key authentication enables programmatic album creation, photo uploads, and metadata queries from external applications. Mobile apps for iOS and Android provide on-the-go upload and browsing capability. Docker deployment via the official container or traditional LAMP installation on any hosting provider. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-2.0 licensed.
Insights LM
Insights LM gives you a NotebookLM-style research assistant that runs on your own infrastructure and answers strictly from the documents you feed it. Build a notebook for a project, drop in PDFs, pasted text, website links, and audio files, then ask questions in plain language and get answers grounded in those sources rather than the open internet. Every answer carries citations you can click to jump straight to the passage it came from, so verifying a claim takes seconds instead of a fresh search. Findings worth keeping become notes saved alongside the notebook, building a private knowledge base that grows with your research. When reading is too slow, generate an audio overview and listen to two hosts discuss your material like a podcast episode, perfect for absorbing a long report on a walk. Teams use it to interrogate internal documentation, onboard new hires against company knowledge, and brief themselves before meetings without uploading confidential files to a third-party service. Because the whole stack is yours, you choose which AI models do the reading, including local models for fully private work. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Garcon
Garcon gives developers one browser workspace for running several coding agents at once, steering their work live, and turning reviewed changes into commits. Tile up to four resizable windows, move chats between them, and place live sessions on durable canvases that show delegated children, handoffs and parentage. Turn that activity into a tag-driven delivery board, or create tickets first and open chats from them with the project, priority, assignee and discussion already attached. Queue instructions, reorder them, answer agent questions, approve tool calls, pause work, interrupt a run or stop it without losing the transcript. Exchange labelled messages between chats, delegate bounded tasks to child agents, and bring final results back into the parent conversation. Browse and edit files, open terminals, inspect reasoning and tool calls, then stage individual lines, hunks, files or folders before committing and pushing. Search transcripts, save filters, pin or archive chats, export Markdown or XML, schedule prompts for later, and review token use and estimated API cost by day, agent and model. Connect trusted remote executors when work belongs on another machine, and open the same workspace from a phone when an agent needs a decision away from your desk. 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.
AKB
Achieving 98.4% Recall@5 on LongMemEval-S without a reranker, AKB is the agent-native knowledge infrastructure giving Claude Code, Cursor, Windsurf, and any MCP-aware agent persistent organizational memory — a drop-in replacement for Confluence or Notion where AI agents read and write directly rather than scraping human-formatted pages. Documents are stored as Markdown with YAML frontmatter in Git bare repositories (full version history, branching, diff), while PostgreSQL 16 serves as source of truth for chunk text, metadata, and BM25 vocabulary, with dense embeddings handled by a pluggable vector store (pgvector default, Qdrant optional, or managed Seahorse). Agents interact through 20+ MCP tools — akb_put, akb_search, akb_browse, akb_relations, akb_sql, akb_edit, akb_history — performing hybrid dense plus BM25 search fused via Reciprocal Rank Fusion in one call. The URI graph (depends_on, related_to, implements relations) lets agents traverse knowledge connections without external graph databases. Multi-tenant vault isolation is enforced at the PostgreSQL ACL level with per-user roles and SET LOCAL ROLE for SQL sandboxing. Event fanout streams structured events to Redis Streams for external consumers (synthesis bots, digest agents, audit trails), and a hash-chained append-only audit log integrates with enterprise SIEMs. Ships with agent plugins for Claude Code and Codex (session capture, wiki ingest, lifecycle hooks), Kubernetes kustomize manifests, and Open Knowledge Format export. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. BSL 1.1 licensed (free under 100 seats, auto-converts to Apache 2.0 after four years).
PlikShare
Sending a client a big file should not mean renting seats on someone else's cloud, and PlikShare turns your own server into a file sharing platform with unlimited users, unlimited workspaces, and no per-seat pricing. Its central idea is the box: a controlled gateway between your folders and the outside world, where you invite collaborators, mint anonymous links, and decide who may upload, download, preview, or drop files into an upload-only inbox. Quick share links carry custom slugs, expiry dates, passwords, and download caps, and every box can embed into another website as a live widget whose permissions update the moment you change them. Storage is your choice per workspace, from the server's own disk to S3, Cloudflare R2, Backblaze B2, Azure Blob, Google Cloud Storage, or any S3-compatible server, and each storage picks one of three encryption modes, including full encryption where names and contents are sealed with keys derived from each user's password. Bulk uploads arrive as a single zip that rebuilds its folder structure on landing, bulk downloads assemble from an explorer tree, and previews cover video, audio, PDFs, Markdown with diagrams, and even the inside of zip archives. Single sign-on through multiple OIDC providers, granular admin roles, an optional MCP server for scoped AI agents, and OCR or chat integrations round out a platform that stays lean on a small server. 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.
Bludit
Bludit is a flat-file content management system that runs your website or blog from plain JSON files, giving you a complete admin panel and publishing workflow with no database anywhere in the stack. Writing feels familiar whichever way you work: draft posts and pages in the Markdown editor, switch to the WYSIWYG editor when you want to see the page as you build it, or drop into HTML for exact control. Cover images, galleries, and uploads live in the media manager, and categories and tags keep a growing archive browsable. Built-in SEO tools handle titles, meta descriptions, and friendly URLs, so pages come out ready for search engines and social previews without another plugin hunt. When the look needs to change, the official theme directory restyles the whole site from the admin area, and the plugin directory adds galleries, contact forms, and analytics the same way. Moving day is a copy command: the entire site, content and settings included, is a folder of files you can duplicate, back up, or carry to another server. Because every page renders from files with no database round trips, modest hardware serves pages quickly. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Elasticvue
Elasticvue is a graphical interface for Elasticsearch where you can inspect cluster health, browse indices, search and edit documents, and send REST queries. Start on the Home tab, which summarizes status, nodes, shards, indices, document counts, and disk usage. Nodes shows load, CPU, RAM, heap, and disk for each member, and Shards lays out every primary and replica in a grid with a switch for shard allocation. Indices handles creation, aliases, templates, and bulk actions. Search runs query string searches across an index pattern, opens any hit in a JSON editor for updates or deletion, and downloads results as JSON. Rest sends any request from tabbed editors with history, saved queries, and examples, while Snapshots manages repositories and backups. Version 1.16 adds user and role management for Elasticsearch clusters. Secured clusters connect with basic authentication, API keys, or AWS IAM credentials, and the Docker image preloads cluster definitions from an environment variable or a mounted JSON file. Elasticvue supports every Elasticsearch version, even end-of-life releases, and speaks English, Chinese, French, Russian, Japanese, and Italian. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Tasks.md
Your task list should outlive the app that displays it: Tasks.md turns a folder of plain Markdown files into a kanban board, so the board is a view of your notes rather than a database holding them hostage. Every lane you create becomes a directory and every card a Markdown file inside it, which means the whole board stays readable in any text editor, greppable from a terminal, and friendly to the note tools you already use. You write card bodies in a proper Markdown editor, organize work with tags and due dates, and drag cards between lanes as priorities change. Sub-folders open as their own projects with separate lanes, so one installation quietly serves a work board, a home board, and a writing board side by side. Light and dark themes follow your operating system, three bundled color schemes (Adwaita, Nord, and Catppuccin) set the mood, and a custom stylesheet hook recolors everything else. The board installs as a PWA for an app-like window, speaks multiple languages detected from the browser, and slots under a subpath reverse proxy when it shares a domain. One Docker container on port 8080 serves the whole thing. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
phpMyFAQ
Publish the answers your team keeps repeating as a multilingual, searchable FAQ with phpMyFAQ, a knowledge base whose admin area handles writing, review, and permissions. Organize entries in nested categories that you rearrange by drag and drop, attach files, add tags and related FAQs, and let visitors leave comments. A WYSIWYG editor with an image manager writes each answer, a wiki-style revision history restores earlier versions, and a news system posts announcements. Full-text search covers every language, and optional Elasticsearch or OpenSearch backends handle larger collections. The interface covers more than 40 languages with right-to-left layouts, automatic content negotiation, and translated categories and entries. Privileges work per user and per group, so an editor can change an entry without being allowed to delete it, and categories can be limited to chosen readers. Sign in through LDAP, Active Directory, or Microsoft Entra ID, protect accounts with two-factor authentication, or try experimental passkeys. The dashboard charts 30 days of visits, lists inactive FAQs, and checks installed files against published hashes. Export entries to PDF, publish a dynamic sitemap, back up your content, and filter spam with built-in protections. Dark, light, and high-contrast themes keep the public site comfortable to read. Scripts and AI assistants reach the knowledge base through a REST API with an OpenAPI specification or an experimental MCP server, and plugins extend it. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MPL-2.0 licensed.
LogicalDOC
LogicalDOC is a document management system that gives a company one controlled home for its files instead of letting contracts, invoices, and procedures scatter across drives and inboxes. Staff store any kind of document in a repository organized on multiple levels, then find it again through advanced search that reaches inside document content, not just filenames. Colleagues collaborate on the same documents and projects while version control keeps the history straight, so nobody works from last quarter's draft by accident. Administrators define roles for different users, set access control and user quotas, and choose the security level for each area, with detailed activity logs showing who opened, changed, or shared what. Automations handle the routine flow of documents through the business, and the web services API lets an ERP or other systems integrate document management into existing processes. Information can be collected from any digital source, knowledge gets reused instead of recreated, and mobile apps for phones and tablets keep the repository reachable away from the desk. The official Docker image and Tomcat bundles make the Community Edition straightforward to run on your own infrastructure. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. LGPL-3.0 licensed.
APIPark
One gateway, every AI model: APIPark gives your applications a single, consistent API for OpenAI, Anthropic, Google Gemini, DeepSeek, and 100+ other models, and gives your team a portal to publish and share whatever gets built on top. Standardized request and response formats mean swapping a provider or rewriting a prompt never touches client code. Pair a model with a prompt template and it becomes a ready-made API for sentiment analysis or translation, listed in the developer portal with its own readme and generated API docs. Model Fallback swaps in the highest-priority available model when one misbehaves. API key balancing spreads traffic across several keys for the same provider. Already have REST services? Import an OpenAPI document, file the service under a category and tags, and let consumers subscribe, with optional manual review before anyone gets access. Any service can be switched on as an MCP tool that AI assistants can discover and call, and local open-source models can be deployed and exposed the same way. Usage charts follow requests, traffic, and tokens per service and consumer. Request logs flow out to files, HTTP endpoints, Kafka, NSQ, or Syslog. 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.