Operational
Operational watches your product for the moments that matter, signups, payments, failed webhooks and cron jobs, and pushes the important ones to your phone as they happen. Your code sends structured events with a name and a JSON payload through a simple API, using the official Node.js or PHP SDKs or the WordPress plugin, and every event lands in a searchable feed organized by project and category. Mark an event notify and it becomes a push notification on your phone through the installable web app, while everything else waits quietly in the feed for when you actually want to look. Related events nest inside each other as contexts, so a failed checkout can carry its payment attempt, gateway response and retry history in one expandable bundle instead of forty scattered log lines. Events can carry action buttons that trigger your webhooks, letting you approve a refund, restart a job or retry a delivery from the notification itself. Teammates share projects with their own accounts, a test mode lets you rehearse integrations without polluting the real feed, and a built-in MCP server exposes your events to AI tools. 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.
Olla
One endpoint for every inference box you own: Olla is a proxy and load balancer that fronts your self-hosted LLM backends and routes each request to a healthy node. Your apps keep calling a single OpenAI-compatible address on port 40114, and Olla picks the backend by priority, response rate, and live health. When a node drops, requests retry on the next endpoint automatically and the failed node rejoins after recovery, with circuit breakers keeping bad nodes out of rotation. Multi-turn conversations stick to one backend so its KV cache stays warm across the chat. Model lists from every provider merge into one catalogue, and the same model served by several nodes appears once, ready to route anywhere. Backends with native Anthropic support receive Messages API calls untouched, and other backends get automatic translation, so Claude Code and similar tools can drive your local models. Text embeddings and rerank requests route to the host that serves them, and outbound authentication covers backends that expect API keys. The embedded Herd Dashboard shows fleet health, per-endpoint latency, and the discovered model inventory from the binary itself. The whole proxy runs in under 50 MB of RAM. 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.
Fynt
A clean alternative to n8n and Zapier that puts AI-native workflows front and center, Fynt is the MIT-licensed workflow automation platform where you drag nodes onto a React Flow canvas, wire them together with typed connections, and let a distributed BullMQ engine execute them — with every step streamed live to your browser over WebSockets so you never wonder what happened inside a run. The node library spans triggers (manual, webhook, cron scheduling), AI providers (OpenAI, Anthropic, and Gemini with structured output parsing), service integrations (GitHub webhooks, Notion databases, Slack channels, Discord bots, arbitrary HTTP endpoints), logic gates (conditional branching, filtering, data transformation), and utility nodes (delay, logging, payload mapping). The execution architecture separates concerns across three services: a Next.js 16 web application serving the React 19 workflow builder and tRPC API, a BullMQ worker processing jobs with node-level retries and checkpointing for crash-safe execution, and a dedicated WebSocket relay server broadcasting real-time run events via Redis Pub/Sub. All stored credentials are encrypted at rest using AES-256-GCM with per-credential initialization vectors. The full-stack deploys as a single Docker Compose stack (web, worker, realtime, PostgreSQL, Redis) or individually via pnpm workspaces in a Turborepo monorepo. Authentication is handled through better-auth with configurable OAuth providers. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
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.
Engraphis
Engraphis is a durable memory layer for coding agents that answers questions like what did we decide about the auth layer three weeks ago, and why, with inspectable project memory that survives across sessions and repositories instead of evaporating when a chat ends. Store a decision once and recall it later in a new session, scoped by workspace, repository, and session so one project's facts never leak into another's context. Recall blends vector, lexical, graph, and code-aware retrieval, then packs the strongest evidence into a hard context budget your agent can actually use. Every returned fact keeps its provenance attached, and the engine cites its support or abstains when the evidence is too weak to trust. Facts are never silently overwritten: bi-temporal history preserves earlier versions, and a timeline view surfaces superseded knowledge when you need to know what used to be true. Index a repository into a code-symbol graph and ask what calls a function before you change it. Conflicting or quarantined memories wait in a review queue for a human decision. 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.
Taskuary
Mail, chats, tickets, alerts, and reports stop being five inboxes to check and become one sorted rail in Taskuary, your self-hosted AI work partner. A triage pass reads each arrival and gives it one verdict: nothing to do, a sentence settles it, an agent should work it, talk it through, or it is yours. The rail groups what survives into Urgent, On you, Goals, Agents working, For later, Reports, Advisor ideas, and FYI, and a morning card recaps what changed overnight, what was learned, and today's meetings. The Assistant can walk you through the pile one task at a time, presenting each card with Next, Write reply, Send to agent, and Mark done actions. Coding jobs go to the CLI you already run (Claude Code, Codex, Gemini, Cursor, Copilot, Qwen Code, OpenCode, or Kimi Code) inside your checkout; general jobs open a conversation instead. Results return as drafts attached to the task, and nothing leaves until you approve: replies, comments, invoices, and posts all wait for your click. Disagreeing with a verdict teaches the triage, and learned memory carries your preferences into the next decision. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Nginx-Love
Hand-editing nginx configuration files to run a firewall is nobody's idea of a good afternoon, and Nginx-Love turns that chore into a dashboard. You manage domains, load balancing upstreams, and HTTPS backends through forms instead of config syntax, and the platform writes and reloads the underlying configuration for you. A ModSecurity firewall with the OWASP Core Rule Set inspects traffic to your sites, and you tune its rules from the interface rather than a text editor. Certificates arrive two ways: automated through Let's Encrypt, or uploaded manually when you bring your own. A Bot Manager fingerprints visitors with JA4 signals so you can welcome good crawlers, challenge suspicious automation, and block hostile bots by policy. Access lists filter by IP address, geography, and user agent, and multi-user roles let administrators, moderators, and viewers each see the controls appropriate to their job. Monitoring watches performance and attack patterns, sending alerts by email or Telegram when something needs attention. Configuration exports back up your setup, restores bring it back, and multi-node sync keeps a cluster of servers enforcing the same policy. 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.
CatGPT Gateway
CatGPT Gateway turns the ChatGPT or Claude account a team already pays for into an OpenAI-compatible API that ordinary tools can call. Point the OpenAI Python SDK, LangChain, or a plain curl request at the gateway and choose the browser-backed model for Claude or ChatGPT; the service opens the provider web interface in a real Chromium session, enters the prompt, waits for completion, extracts the answer, and returns standard OpenAI JSON. Streaming responses arrive over SSE, persistent session headers keep multi-turn conversations on one browser tab to avoid reloads, and a browser page pool handles concurrent requests across several tabs. Tool calling round-trips through structured prompt injection, so LangChain agents can invoke local functions and receive parsed tool calls in the normal format. Vision inputs, PDF and document attachments, and ChatGPT image generation through DALL-E pass through the same endpoint shape that existing clients already speak. A live monitor at the preview route shows every active browser tab in a double-buffered grid, with tab switching and safe tab closure for the operator. One browser login through a noVNC page persists in a Docker volume, so the API keeps serving after restarts without storing provider API keys. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
KoShelf
Your e-reader already knows everything about your reading life, and KoShelf turns that KOReader metadata into a beautiful dashboard you can browse from any browser. The library overview gathers currently reading, completed, and unread books and comics, while each item's page collects your highlights, annotations, ratings, and review notes in one place. Reading statistics chart your time and pages with customizable activity heatmaps and weekly breakdowns, and per-item statistics reveal session counts, average session length, and reading speed for every book. A monthly calendar shows what you read on each day, and the yearly recap celebrates completions with monthly summaries of finished items and hours read. Supported books open right inside KoShelf's own reader, with keyboard navigation, a progress scrubber, and inline highlight notes. Metadata entries survive even when the original document disappears, because library archives preserve covers and reading data until the source returns. With writeback enabled in server mode, you can edit annotations, ratings, status, and covers from the browser, protected by revision checks and recoverable backups so external changes are never overwritten blindly. Search by title, author, or series, filter by reading status, and download original files whenever you need them. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. EUPL-1.2 licensed.
Tunnet
One encrypted network for every machine you run: Tunnet links laptops, home servers, cloud instances, and CI runners into a private mesh that behaves like a single LAN. Each enrolled machine gets an overlay IP and a hostname, so ordinary tools like ping, curl, SSH, and the browser just work across home servers, cloud instances, and laptops. Publish an internal app to your peers with Serve, or expose a local service to the public internet with an HTTPS tunnel when you need a shareable link. Send files directly between machines without detouring through cloud drives, email attachments, or fragile copy commands. SSH access follows identity instead of scattered key files, with session recording and no bastion host to maintain. Device posture checks gate which machines may join, and subnet routes, exit nodes, and high-availability gateways extend the fabric to whole networks. Write your ACLs, groups, tags, and SSH rules as Policy as Code in Git, simulate changes offline, review semantic diffs on pull requests, and roll back revisions when a change misbehaves. The Kubernetes operator advertises cluster networks, publishes services to peers, and exposes public HTTPS endpoints through custom resources. Run the full stack yourself, control plane, dashboard, management API, relays, and audit logs included, or skip the server entirely with Direct mode for a zero-server peer-to-peer mesh. 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 and MPL-2.0 licensed.
Houndarr
Radarr, Sonarr, and their sibling apps watch RSS feeds for new releases but never go back for what your library is still missing, and Houndarr fills that gap by asking them to search in small, polite batches. It reads the wanted lists of every connected Radarr, Sonarr, Lidarr, Readarr, and Whisparr instance and sends a few search commands per cycle, so a big backlog drains over days instead of arriving as one Search All Missing burst. Each instance has its own batch size, sleep interval, hourly cap, per-item cooldown, and post-release grace period, plus an optional download-queue limit, allowed search windows such as 09:00-23:00, and tag filters that include or exclude items. Three independent passes run per instance: missing items, cutoff-unmet items below your quality profile, and upgrades for files that already meet cutoff, with the last two off until you enable them. Sonarr, Lidarr, and Readarr can search by season, artist, or author, and search order is random or oldest-first. The dashboard shows library health, recent hunts, hourly budgets, and a cooldown schedule per instance, with Run Now buttons for on-demand cycles. The Logs page records every search and skip with its reason in a filterable audit trail that copies as TSV. A key-gated widget endpoint feeds Homepage dashboards, and built-in login or reverse-proxy authentication protects the interface. 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.
Substreamer
A free, polished web client for Subsonic-compatible music servers: Substreamer is the browser-based frontend you point at your existing streaming backend to play your own library from anywhere. It speaks the Subsonic API (v1.13 and higher), which makes it compatible with the whole ecosystem that has grown around that protocol: the original Subsonic server, its forks Airsonic and Madsonic, and modern implementations like Navidrome and Ampache. That decoupling is the point - your music files, transcoding, and library indexing live on whichever server you prefer, while Substreamer provides the listening experience: browse by artist, album, and genre, build and manage playlists, search your collection, and stream on demand. This RepoCloud deployment runs the containerized web edition, so the same interface is available from any browser without installing a native app, and it pairs with the Substreamer mobile apps that made the client popular. For anyone assembling a self-hosted Spotify replacement - typically Navidrome for the backend plus a good client - Substreamer fills the client half with a clean, familiar player UI. Because it is a stateless client, the container is lightweight and low-maintenance: connect it to your server's URL and credentials, and your entire collection is streaming in minutes, with no subscription and no catalog that can disappear.
Distr
Shipping commercial software to customer-managed infrastructure demands a reliable distribution hub, and Distr provides that control plane for vendors who sell into VPCs, on-prem data centers, and air-gapped networks. Vendors define Docker Compose, Docker Swarm, or Helm applications with versions and configuration templates, then roll releases out to every customer deployment from a single vendor portal. Prebuilt deployment controllers installed in customer environments apply updates and report status, container logs, live host metrics, and alerts back, so support teams can diagnose problems without touching anyone's infrastructure. Customers get a white-labeled portal with your branding, install instructions, registry credentials, version management, and customer-initiated support bundles. A built-in OCI registry distributes Docker images, Helm charts, Zarf packages, and other artifacts with per-customer tag access, pull-through caching, and download analytics showing which customer pulls which version. Entitlements control which application versions each customer may deploy, and Ed25519-signed JWT license keys let your own software verify usage limits offline, which keeps licensing working in air-gapped sites. An OpenTofu controller provisions and reconciles BYOC cloud infrastructure, while a REST API and SDK automate onboarding, releases, and entitlements from CI pipelines. Role-based access control manages permissions across vendor and customer organizations, while the Kubernetes compatibility matrix and vulnerability scanning help validate releases before they ship. 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.
deco Studio
Roll out AI across a whole company without handing a single API key to anyone. deco Studio gives teams a shared chat workspace, and the admin keeps control of which models, tools, and data every agent can touch. Register MCP servers once from a catalog of ready-made connections, including Amplitude, Apify, Atlassian Rovo, ClickHouse, and a long list of Cloudflare services, then grant tool-level access by organization, role, or agent. Tokens stay in an encrypted vault, so teammates share capabilities and never credentials. Agents bundle instructions, skills, files, and approved tools, then publish as their own MCP endpoint that Cursor, Claude Desktop, or custom code can call. A built-in skills library ships with dozens of reusable playbooks, and Memory keeps facts the whole organization should remember. Model choice stays open through OpenRouter, Anthropic, OpenAI, Google Gemini, or any OpenAI-compatible server, and engineers can link a Claude Code or Codex session they already use. Projects group agents and connections around a goal, with Monitor dashboards for orders, visitors, logs, and deploys, and an Execute board for tasks and epics. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
PocketRisu
Your AI characters deserve a home that is actually yours: PocketRisu is a private roleplay chat server where your stories, personas, and worlds live on hardware you control instead of someone else's cloud. Create characters or import them from the wider RisuAI ecosystem, including character cards, modules, lorebooks, and presets, then chat from your computer, tablet, or phone against the same single server. Conversations keep generating on the server even when your screen locks or the connection drops, and reconnecting restores the finished reply instead of a lost message. Switch between OpenAI, Claude, Gemini, DeepInfra, OpenRouter, Ollama, and more, set separate auxiliary models for background tasks, and shape behavior with presets, regex scripts, and plugins. Lorebooks and long-term memory features help long stories stay consistent, automatic translation smooths cross-language roleplay, and text-to-speech plus embedded images, audio, and video make scenes richer. Everything, from characters and chats to inlay images, sits in one SQLite database on your server, so backup and restore are a server-side job rather than a browser export ritual. A built-in dashboard shows disk use per character and module, reclaims snapshot space, and keeps the database optimized, while multilingual interface options welcome players in Korean, English, Japanese, Chinese, and beyond. 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.
Pizza Bot
Start an AI task, close the tab, and come back to finished work waiting in an inbox. Pizza Bot keeps agents running when you navigate away or disconnect, sorting results into Unread for completed work and Action for approvals that need your decision. Conversations can be grouped into folders, pinned, searched, and forwarded from any message, without hiding matching items from the global queues. Schedules run a prompt on a cron expression with a time zone, and webhooks start a run from an external alert. A shared pool of Markdown memories carries your preferences into every conversation. Skills package step-by-step playbooks with scoped tools, and plugins bundle skills with MCP servers, so a request can be handed to a specialist subagent whose progress shows in an Activity panel. Connect Amazon Bedrock, Anthropic, Google Gemini, OpenAI, OpenRouter, Requesty, Opper, or Ollama, or point OpenAI at any compatible endpoint. Local folders are visible to the agent only after you grant them, read-only by default. Open it in the browser from one container behind a bearer token, or use the desktop app or terminal client against 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. Apache-2.0 licensed.
Hexis
Hexis gives every AI agent in your company one governed brain: skills, tool manuals, and knowledge stored as files in a git repository you own. Engineers and non-technical teammates browse the same workspace to load plugins, read company context, and propose improvements without touching git themselves. A proposed change shows its exact diff to the owners of the files it touches, and it ships only when they approve, on the branch rules you set. Agents propose too: one that hits a broken skill mid-task can suggest the fix as a change request and wait for a person to decide. Claude Code, Cursor, Cline, Codex, and ChatGPT connect over MCP and discover skills by search at call time, so the context window stays lean. Each agent acts with its user's own permissions, resolved per file, and the credentials behind tools stay in an encrypted vault the agent never holds. Roles and folder-level grants decide who sees what, and your team signs in behind your own SSO. Every save is a commit, so history, blame, and revert come free, and the knowledge base can start from the bundled template in minutes. 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.
SkySend
Only the person holding the link can open what you share with SkySend, a self-hosted file and note sharing service that encrypts everything in the browser before it leaves your device. Sending a contract? Drop in the file, several files, or a whole folder, and share the link. Need documents from a client? Send an upload link instead, and whatever comes back is encrypted for you alone. Handing over a password or an SSH key? Write it into a note that burns after reading. Notes can mix text, Markdown, generated passwords, and highlighted code in a single page. Every share can expire by time, stop after a set number of downloads or views, and carry an optional password as a second lock. The command-line client uploads, downloads, and reads notes with the same encryption, and its full-screen mode shows each link as a QR code. No accounts are needed: My Links keeps your shares in the browser, and optional OIDC sign-in limits who may create them. Encrypted uploads sit on local disk or any S3-compatible bucket, and the interface offers 13 languages and three themes. 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.