Plik lets you send big files the way WeTransfer does, except the server is yours: upload from the browser or one CLI command and get an expiring link to share. Files can delete themselves after the first download, stream straight from uploader to downloader without touching disk, or sit behind a password until their TTL runs out and cleanup removes them. End-to-end encryption with Age works between the CLI and the web interface, so the server only ever holds ciphertext. Recipients preview code with syntax highlighting, read rendered Markdown and Mermaid diagrams, and play media in the browser without downloading first. Storage lands on local disk, S3, OpenStack Swift, or Google Cloud Storage, with metadata in SQLite, PostgreSQL, or MySQL, and sign-in through local accounts, Google, GitHub, or OIDC. The web interface speaks twelve languages with light, dark, and custom themes, and Prometheus metrics plus an MCP server connect Plik to monitoring and AI assistants. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Define your tables once, and Daptin runs the backend around them: every schema becomes a permission-aware JSON:API resource with CRUD, relationships, filtering, and pagination, plus an optional GraphQL surface over the same model. Users, groups, and row-level permissions gate who can read or change each record, with JWT login, one-time codes, and OAuth and OIDC endpoints for sign-in. Files ride along as asset columns backed by local or cloud storage through rclone, with presigned uploads and storage sync. Actions chain validation, conditions, and ordered outcomes into reusable operations, scheduled tasks run them on a cron clock as a chosen user, and state machines track each record's lifecycle with an audit trail. Changes stream out live over WebSockets and feeds, while FTP, calendar and contacts routes, and an OpenAI-compatible LLM gateway expose the same model to other tools. Plans, quotas, and metering let you charge for API and model usage from the same server. 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.

Your analysts write the context once, and everyone else just asks questions: nao turns your warehouse into an analytics agent that answers in plain English, showing the SQL and source files behind every answer. The data team builds the context layer by syncing warehouse schemas, dbt projects, documentation, and business rules into files the agent reads, then tests key questions offline against expected SQL before any change ships. Colleagues ask from the web chat, Slack, Teams, or any MCP client, and turn good answers into live dashboards, data apps, and slide stories they share with their team. Every conversation can be replayed, and when an answer earns a downvote, context recommendations turn the mistake into a fix that arrives as a pull request. You bring your own model key from any provider, sign people in with Google, GitHub, or GitLab, and keep warehouse permissions intact as queries run. Dashboards from Metabase or Tableau migrate over instead of starting blank. 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.

Give each team an AI teammate that works where the team already works: AgenticOS lets colleagues and agents share one live chat and the same project files, so an agent can answer in the thread, apply a correction from a reply, and show its work as it writes. You build an agent in the browser by writing its instructions, picking a model, and switching on tools, then publish it to web chat, Slack, Teams, Discord, Mattermost, Telegram, a website widget, or an API. Agents analyze spreadsheets, run code in a sandbox, browse the web in a browser you can watch and take over, and hand programming work to Claude Code or Codex. Company knowledge comes from uploaded documents and synced drives, searched with cited answers, while reusable skills teach agents how your team writes reports, reviews code, or researches a market. Agents can draw charts and diagrams in chat and publish dashboards as apps with stable links your team opens anywhere. Administrators set roles and department groups, cap each agent's monthly budget, require approval for sensitive tools, and read a recorded run history with costs. 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.

Your coding agents work in separate terminals and cannot ask each other anything; Imbo gives Claude Code, Codex, opencode, Cursor CLI, and six other agent tools one shared messaging network, so a session can send a question to another session and get an answer while both keep working. Messages land inside the receiving session mid-task, and a reply wakes an idle session so it can act on the answer. You add people by account ID, and their agents can message yours; group chats let several sessions from several people coordinate on one brief, with every reply reaching every member. Sessions can send files that land in the receiving machine's ~/.imbo/files folder, and an agent asks you first before sending your data out, deleting files, spending money, or touching production. From the web app or the iPhone app you can message your own sessions from anywhere, and a closed Claude Code session reopens in the background to pick the message up. The server is a single binary with a bundled PostgreSQL, HTTPS through Let's Encrypt, email code sign-in, and optional domain restrictions on who may register. 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.

Aizen is a coding agent that actually lives on your server: one small binary you can message from your phone, which fixes code, runs the tests, and reports back before you are anywhere near a keyboard. Leave it running on the box and drive it from Telegram or Discord, approving risky edits with a tap while it works behind NAT with no inbound port to expose. In the terminal it is a single chat and agent loop with a live heads-up display of model, tokens, and context, reading files in parallel, editing symbolically through the language server, and running your shell under an approval layer with a hard floor that refuses catastrophic commands even on auto-approve. It does not get to claim done early: a verify gate runs your typecheck and test suite and sends it back to fix what it broke, git-backed checkpoints let you rewind a bad turn, and seven capability-scoped sub-agents can fan out across finding, planning, building, reviewing, testing, research, and recall when a job wants a team. Point it at any OpenAI-compatible endpoint, from hosted models to your own local server, extend it with MCP servers and slash-command macros, and let the sandbox keep every child process away from your API keys with the network denied by default. 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.

Ogcode puts a full AI coding agent in a browser tab pointed at your own server, where it maps your codebase semantically before reading it, plans changes across files, runs your builds and test suites, and answers with diagrams and documents alongside the shipped code. Before reading files it maps the project with a semantic index, outlines what matters with exact line ranges, and reads only the parts that count, so unfamiliar code becomes navigable in one session. Ask it to implement a feature or chase a failing test and it plans the work, edits across files, runs your builds and test suites, and investigates failures instead of retrying blindly. You stay in control through per-session permission modes: Ask approves each step, Auto gates by risk, and Yolo lets it run, with every decision remembered when you want it to be. Past decisions are recalled instead of replaying whole transcripts, so long sessions stay focused and affordable, and the agent can research as it goes with built-in web search, reusable SKILL.md workflows, and external MCP servers. Answers come back richer than text when the work calls for it, with diagrams, rendered documents, charts, and downloadable artifacts in the same session. Connect Anthropic, OpenAI, OpenRouter, or a local Ollama endpoint and start working. 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.

Octo turns Navidrome into a streaming service with a memory: search finds songs you do not own yet, they play the moment you pick them, and the ones you heart come home as properly tagged files that stay in your library forever. Point the music apps you already use at Octo's endpoint and sign in with your Navidrome login, and your library behaves as before, except search now reaches past your shelves and any result streams instantly as a preview with zero disk impact. Press plus or heart a keeper and Octo downloads the best copy it can find, FLAC first, from Soulseek peers or your own Lidarr, catches lossless files that were faked from MP3s, then identifies, tags, covers, and files the song so it appears in your library like something you bought. Bring the music you already love by importing liked songs and playlists from Spotify or any other service; Octo shows what you already own and quietly fetches the rest a few songs an hour. Stations and discovery playlists learn from your listening through Last.fm and refresh themselves, the downloads drawer shows every fetch with its full decision log, and the browser admin dashboard runs settings, notifications, family accounts, and one-click updates. 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.

Compartment gives the small internal tools, private apps, and AI-built utilities your team keeps creating a proper place to live: your own Kubernetes, with one-command deploys, stable URLs, and sign-in handled for you. Install it into a cluster you already run, or let the guided installer provision a managed single-node Kubernetes host after showing you exactly what it will change. Each app is described by one small compartment.yml file naming its services, and from there deployment is a single command from your checkout, or a branch-driven flow when you connect the Git repository and let pushes roll out on their own. If an app can build into a container image with Docker or Railpack, it fits the model, and every deploy lands behind the edge ingress with its own URL and HTTPS from the first release. The browser Console becomes your operations surface for projects, deployment history, logs, and runtime variables, while SSO, role-based access, and audit logs replace the informal permission paths that grow around shared tools. Workloads stay isolated and can sit close to the private services, data stores, and internal APIs they need, without turning steady traffic into managed-platform spend. 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.

Point it at your GitHub repos and every push goes live in under five seconds: one Linux box becomes the deployment platform for every app you have ever shipped, with no build queue, no per-app bills, and no pile of YAML. An interactive installer wires the box up once, creating a GitHub App for limited, revocable repo access, Cloudflare DNS records and a tunnel so visitors get TLS and CDN at the edge while your server IP stays hidden, and Tailscale access so you SSH in without exposing SSH to the public internet. From then on you just push: the daemon receives the webhook through a Tailscale Funnel, verifies its signature, fetches the commit, builds the image on the server from your Dockerfile or a generated one, and swaps traffic only after the new container passes its health check, so a failed deploy leaves the previous version serving. Each app runs in its own container with its own environment variables and persistent storage, and one CLI on the box handles the rest: add or remove apps, attach a domain in one command, roll back to an earlier commit, stream logs, check status, take backups, or run doctor to diagnose every layer from daemon to DNS. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

CC Our Story gives a couple a private website of their own, a shared home for the timeline of small moments, anniversaries, wishes, and messages that no social platform gets to index, advertise against, or quietly delete. The home page shows the two of you, how long you have been together, and the memories you most recently added. Every photo and note lands on a moments timeline you scroll like a story, anniversaries count down so the next one never sneaks past, and a guestbook lets friends leave blessings without creating accounts, identified by a privacy-preserving fingerprint instead of a sign-up form. A wish shop turns promises into something playful: post the things you would do for each other as redeemable wishes, spend the heart points you earn, and have your partner confirm when the wish is fulfilled. Sensitive records can be locked, private extras include synchronized-answer compatibility tests and gentle cycle tracking with daily notes, and the database ever holds exactly two accounts, yours. Web Push and email notifications run as independent channels so a new post, comment, or heartbeat reaches the other phone even if one channel fails, while an optional AI companion group with named personas drops by occasionally to comment on new moments through any OpenAI-compatible endpoint, never seeing drafts or locked posts. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Qeli is a self-hosted VPN built for networks where ordinary VPN protocols get recognized and blocked, disguising its traffic as ordinary web traffic while keeping the classic full-tunnel experience. Where WireGuard, OpenVPN, and IKEv2 carry fingerprints that deep packet inspection has learned to spot, Qeli answers with five wire modes: plain, TLS mimicry, ChaCha20 obfuscation behind WebSocket fronting, REALITY, and a flagship mode that carries the private stream inside a genuine HTTP/2 request within a real TLS 1.3 exchange. A probe without a valid token never learns the difference, because the server bridges it to the configured public target site. The handshake is hybrid post-quantum, X25519 plus ML-KEM-768, with a ChaCha20-Poly1305 data plane, and the tunnel itself behaves like the VPNs people already know: full-tunnel or split routing, OS-level DNS, and per-app include or exclude rules on Windows, macOS, and Android. A one-command installer on a clean Debian or Ubuntu server asks for a profile and a port, writes the NAT configuration, creates the first users, and prints ready-to-paste connection links. The web panel then issues qeli:// links and QR codes per person behind an Argon2id login, so onboarding a phone is a camera scan instead of a config file. Clients cover Linux, Windows, macOS, Android, and Keenetic and OpenWrt routers, and published lab benchmarks average around 1220 Mbit/s across all twelve profiles. 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.

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.

Shortlink is a self-hosted platform for short links and live QR codes that keeps every printed, shared, or forwarded entry point under your control long after it leaves your hands. A code printed on ten thousand flyers cannot be recalled when the campaign page moves, so the destination behind it changes while the printed image stays exactly the same. Create short links with custom codes, a choice of 301, 302, 307, or 308 redirects, expiry dates, visit caps, and a fallback target for when the main destination is down. Build live QR codes backed by a pool of destinations that rotates by order, weight, random pick, or least-shown strategy, with transactional saves so a half-finished edit never goes live. Style each code in classic, rounded, or dot patterns with your own colors and a center logo, preview it in real time, and download print-ready SVG, PNG, or WEBP files. New links and codes land in an approval queue that an admin reviews before anything goes public, and every change is written to an audit log. Teammates sign in with an emailed magic link or GitHub, manage only the resources they own, and watch thirty days of visit trends, unique IPs, and device and browser breakdowns roll in. 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.

One dashboard for every WordPress site you look after: that is WPMgr, a self-hosted control panel that replaces dozens of separate wp-admin tabs with a fleet view you own. Enroll a site by URL, paste a one-time code into its agent plugin, and the connection flips live on its own. From there the daily grind changes shape. Backups stream straight out of PHP with no mysqldump and no shell access, chunked and deduplicated, scheduled per site, and restorable as a whole site or just the database. Updates stop being a weekend ritual: preview the run dry, apply it across the fleet, and let the automatic snapshot and health check roll back a bad release before a client notices. Uptime probes split DNS, TLS, and time-to-first-byte, flag certificates about to expire, and open exactly one incident per outage instead of a storm of alerts. The Sites grid leads with a fresh screenshot of every homepage, so the dead site is visible before the client calls. Core files get diffed against official WordPress.org checksums, brute-force logins meet escalating lockouts, and an IP firewall fires before other plugins load. Page caching, Redis object cache, image optimization, and per-site email fill the remaining gaps, and every command between dashboard and agent is signed so nothing can be forged in transit. 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.

Mention an AI agent in a channel the way you would page a teammate, and it picks up the surrounding conversation, claims the task, does the work in its own persistent workspace, and reports back in the thread. OpenTag is a self-hosted, Slack-style workspace where people and coding agents from Claude Code, Codex, GitHub Copilot, and other runtimes work as one team across channels, threads, DMs, and a shared task board. Each agent keeps its own memory file, runtime session, permissions, and activity history, can be started, stopped, put to sleep, woken, or resumed, and can delegate pieces of a job to other agents or schedule reminders that wake it later. Teams watch live progress through per-message activity that expands to show thinking, status, and tool calls, while full-text search keeps every decision findable where it was made. The control plane runs from Docker Compose on your server, connected machines run the daemon that hosts the agent CLIs, and attachments, databases, and workspaces stay on infrastructure you control. Multi-workspace accounts, scoped permissions for agents and members, and per-channel task numbering keep larger teams organized without surrendering their context to someone else's cloud. 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.

Game servers, home labs behind carrier-grade NAT, and services that need a presence in another region all end up needing the same thing: a cheap entry machine that forwards traffic to the real backend, with rules you can change without opening an SSH session. Relay Panel is the control room for that job, a self-hosted web panel that runs TCP and UDP forwarding across a fleet of lightweight relay nodes from one dashboard. Each rule can fan out to multiple targets with failover or round-robin balancing, follow domain targets as their DDNS records change, and pass the real client IP onward through PROXY protocol, even when relays chain through other relays. Per-rule concurrency caps, scheduled restarts, and automatic target circuit breaking keep one bad upstream from swallowing the whole route. A built-in shop lets users buy plans and top up balances with redemption codes while quotas drain by measured upload plus download, multiplied per line, so premium routes cost more by design. Traffic charts split the last day, week, or month by line, the node page watches CPU, memory, and connection counts, and Telegram or email alerts fire the moment a relay drops offline. Nodes upgrade from the panel in one click, and the first login forces a password change before anything else opens. 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.

QMReader is a self-hosted reading workbench that treats RSS as raw material for knowledge you keep, not a pile of unread badges waiting to be cleared. Subscribe to RSSHub routes, direct feeds, sitemaps, Hacker News, Product Hunt, GitHub Trending, and Hugging Face Papers, and new items land in the article list immediately while translation and rewriting finish in the background. English headlines gain Chinese translations automatically, and full articles can be read as the original, a Chinese translation, or a plain-language rewrite, all kept side by side on the same page. Highlight passages, attach your own commentary, and open an AI conversation scoped to the article in front of you instead of starting from a blank chat box. Work you produce becomes a public reading asset with a stable link: translations, rewrites, comments, and dialogues collect on contributor pages and flow out through asset catalogs and RSS feeds for the next reader. Split background workers keep fast feed fetching separate from slower AI processing, and search, unread, popular, favorites, and history views keep a heavy reading habit navigable. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.