Subscribe to a feed and Oksskolten fetches the complete text of every new article, cleans it, and files it as Markdown in a library you can read without leaving the app. About 500 cleanup patterns strip ads, navigation, and tracking, with no per-feed toggles or selectors to maintain. No feed on the site? Auto-discovery goes first, then RSS Bridge, then LLM-inferred CSS selectors, while FlareSolverr gets past bot protection. Every feed is checked on its own schedule, somewhere between every 15 minutes and every 4 hours. Inbox, Read Later, Liked, and Read views keep the queue tidy. Clip any URL as a standalone article. Likes and bookmarks feed an engagement score that shapes search ranking and recommendations. One click summarizes or translates an article through Anthropic, Gemini, OpenAI, Ollama, or vLLM, with Google Translate and DeepL as translation engines. Ask the chat questions about your archive, or point Claude Code or Codex at the built-in MCP server to use the same tools. Search forgives typos and covers every stored article. Login works with a password, a passkey, or GitHub. Pick from four layouts and fourteen color themes, import custom themes as JSON, rebind keyboard shortcuts, and keep reading offline as a progressive web app. 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.

Gmail, Outlook, and every IMAP mailbox you own share one inbox, one search box, and one calendar in plMail, a mail client you host yourself. Accounts sit side by side with sending aliases, and new mail arrives on its own through IMAP IDLE, Gmail and Outlook push, and browser notifications. Credentials are encrypted before storage. Search understands from:, subject:, label:, has:, and before:, completes as you type, and highlights matched words. Filters are nested any, all, or none trees, and each shows how many real messages match before you save it. Drag several conversations at once onto folders, labels, or inbox tabs; a label adds itself without removing the mail from your inbox. A calendar sits beside the mail, with two-way sync for Google, Microsoft, and CalDAV. Move events on the week grid, answer invitations in place, and send share and booking links. An optional language model, pointed at your own Ollama server or any OpenAI-compatible endpoint, searches by meaning, drafts replies, summarizes threads, and sorts mail into tabs once you switch it on. Attach files from and save them to Drive, OneDrive, Dropbox, Nextcloud, Immich, and Paperless-ngx. Sign in through Authentik, Keycloak, or any OpenID Connect provider, and pick from 41 themes. Android and iOS apps connect to your own 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.

Cataloging tables, topics, queues, and APIs across fragmented data stacks usually demands heavyweight enterprise governance suites, yet Marmot delivers fast full-text asset discovery and AI-ready metadata context in a single self-hosted service. Data engineering and platform teams use its 71 official plugins to automatically ingest schemas, run histories, and dependencies from Apache Kafka, Airflow, Iceberg, Superset, PostgreSQL, BigQuery, and AsyncAPI specifications without moving raw table rows or message payloads. From the web interface, analysts can run structured boolean queries, filter assets by custom tags or PII classifications, and inspect column-level schemas in seconds. Interactive upstream and downstream lineage graphs let engineers trace how events flow from message brokers into warehouse tables and BI dashboards so they can assess what breaks before renaming a column or deprecating an endpoint. Shared business glossaries, bidirectional ownership assignments, and curated data product bundles ensure every department speaks the same language and knows exactly which team maintains each pipeline. Through the built-in Model Context Protocol server, AI assistants in Cursor, Claude Desktop, and LibreChat can invoke tools like discover_data, find_ownership, and lookup_term to answer natural-language questions against live catalog metadata instead of guessing. Platform administrators can also manage catalog resources declaratively using the REST API, CLI, Terraform provider, or Pulumi integration. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Pageviews tell you someone arrived; Pug is an open-source product analytics platform that shows what people actually did next, across events, funnels, retention, and user flows. Capture events from browser, Android, Flutter, Node, Go, or Ruby SDKs into an ingestion pipeline that enriches each hit with geography, user agent, bot detection, and web attribution automatically. Identify and alias the users behind events, then open a profile to see traits, sessions, and the full activity history of a person. Build insights as trends, funnels, retention cohorts, segmentation, Sankey user flows, and top-K breakdowns, with filters and period-over-period comparison on every chart. A web analytics overview is generated from your events with visitors, sessions, pageviews, bounce rate, and traffic sources, requiring no tile wiring. The live view plots every current visitor on a real-time world map, down to the person and the event they just fired. Compose dashboards from insight and markdown tiles on a time-windowed grid that analysts rearrange without touching ingestion. Erase a person's events and profile on request to satisfy GDPR and DPDP data-subject obligations. 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.

An agent run can finish without errors and still give the wrong answer, so TraceRoot traces every model and tool call, flags the production runs that missed the mark, and helps your coding agent ship verified fixes. Each run becomes a browsable call tree with inputs, outputs, latency, and cost, searchable by session or filter. Instrument with the Python or TypeScript SDK, the agent-native CLI, or any OpenTelemetry exporter, with ready integrations for LangChain, LangGraph, OpenAI Agents SDK, CrewAI, Vercel AI SDK, Mastra, and Pydantic AI. Detectors use LLM judges to score live traffic against the behavior you define and can post alerts to Slack. Judge outputs cluster into signals, then a background coding agent reads the traces and your connected GitHub code in a sandbox and recommends changes down to the commit, file, and line. Datasets, test cases, and scored eval runs compare versions so regressions surface before a release, and dashboards of widgets chart your trace data. The CLI hands your coding agent, such as Claude Code or Codex, the traces, signals, detectors, and evals to work from. Self-hosting keeps all of that trace data on infrastructure you control. 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 (core edition).

Track website traffic and conversion funnels with sub-second precision while guaranteeing visitors total anonymity with Medama, a privacy-first web analytics platform operating without cookies, IP storage, or consent banners. Site owners embed a sub-kilobyte tracking script into web headers to record page views, session duration, referrers, screen resolutions, browser user agents, and geographic countries anonymously. Built-in caching header mechanisms determine unique daily visitors without generating persistent hashes or storing cross-site identifiers that violate privacy regulations. The web dashboard visualizes hourly traffic trends with interactive area charts and provides multi-dimensional data tables breaking down top-performing pages, search engine referrers, operating systems, and campaign UTM parameters. Developers can instrument custom click events and page attributes using simple HTML data attributes to measure conversions, document downloads, button interactions, and user subscription states. Administrators manage multiple websites from a single interface, configure curated anti-spam blocklists using Firehol and Tor exit node feeds, and monitor server CPU, memory, and disk usage in real time. Full OpenAPI specification endpoints allow teams to export analytics data directly into internal business intelligence pipelines and custom executive dashboards. 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.

TLSPROXY puts automatic Let's Encrypt TLS in front of every service on your server, so many names can share one port while each backend gets exactly the encryption treatment it needs. Terminate TLS and hand plain text to a local service. Pass raw TLS straight through when the proxy should see nothing. Or terminate and re-encrypt towards a TLS backend, with client certificates checked on the way in. QUIC and HTTP/3 connections terminate here too, and Encrypted Client Hello keeps even the handshake private. Certificates arrive and renew by themselves through http-01 and tls-alpn-01 challenges, PROXY protocol headers preserve real client addresses, and SNI routing with round-robin balancing spreads names across backends. People get in with OpenID Connect, SAML, or passkeys; the same sign-in can mint short-lived SSH user certificates, and built-in certificate authorities manage client and backend credentials for you. Static sites can be served straight from disk, TPM-backed keys keep private material in hardware, and a built-in console shows what the proxy is doing. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Work, personal, business, and school calendars at different providers double-book because no one system sees your real availability - Keeper solves that multi-calendar collision problem. Its pull-compare-push sync engine aggregates events from Google Calendar, Outlook/Office 365, iCloud, FastMail, any CalDAV server, or read-only iCal/ICS feeds, and pushes blocking events to one or many destination calendars so time slots align everywhere. The design is deliberately content-agnostic - it syncs timeslots, not titles or descriptions, so a personal appointment shows as busy time on your work calendar without leaking details. Sync logic is clean: events Keeper creates carry a traceable UID suffix, deletions propagate, and orphaned entries are purged automatically. A token-authenticated aggregated iCal feed combines selected calendars into one subscribable URL for Apple Calendar or Thunderbird. An optional MCP server gives AI agents read-only calendar access over OAuth 2.1 - list calendars and query events by date range, with no write capability. Built with Next.js and Bun under AGPL-3.0, the standalone Docker image bundles web, API, cron, worker, Redis, and PostgreSQL in one container, and self-hosting unlocks every Pro feature - unlimited calendars and one-minute sync intervals - for free.

Upload a file, get a unique download link and a separate delete link - Jirafeau has done exactly this one thing since 2008. It is plain PHP with no database, no mail server, no JavaScript framework, and no external dependencies - files and metadata live on the filesystem, which is why it runs on nearly anything and why it has outlasted most of its imitators. Uploads use the HTML5 file API, so PHP's post_max_size ceiling does not constrain file size, with live progress showing speed, percentage, and time remaining. Every upload takes options: expiration from one minute to a year to unlimited, self-destruct after first download, and password protection with configurable policy - passwords can be optional, required, or server-generated with complexity rules. Server-side encryption (modern builds use XChaCha20-Poly1305) stores files encrypted at rest with the decrypt key embedded only in the download URL, never on the server, so a compromised host cannot read the contents. Unencrypted deployments get file-level deduplication - identical files stored once with multiple links. Upload access can be gated by password lists or IP allowlists, a small admin panel manages stored files, and a CLI cleanup script handles expired files via cron. Recipients can preview supported files in-browser.

Meshlan turns your own Linux server into the control plane for a private virtual LAN that connects remote Windows devices as if they sat on the same router. Devices pair through your server, receive their certificates, and then talk directly to each other over encrypted tunnels whenever NAT allows, using dual-stack hole punching, UPnP, and STUN diagnostics to find a path. When a direct connection is impossible, traffic falls back to relays, and multiple relay nodes are chosen automatically by latency, jitter, packet loss, and health. You can publish a service that only listens on localhost, a local API, a web panel, a database, a game server, to the mesh on a custom port, with direct access or manual approval by its creator. Names stay stable while addresses change: devices answer to names like alice.mesh and services to api.alice.mesh, and an HTTPS gateway serves mesh websites without port numbers. Files move directly between devices over the encrypted link while the server only distributes metadata. The console shows the live topology with P2P and relay paths, latency, and service health, and local history keeps traffic and events for replay with a time slider. Optional AI automation keeps model keys on the server, encrypts context end to end, and asks for your confirmation before changing anything. Signed updates verify and roll back automatically when a health check fails. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Gately keeps your domain names current, forwards ports, terminates HTTPS, and blocks hostile traffic from one admin console, so a server or home network needs no pile of separate gateway tools. Dynamic DNS updates records at Cloudflare, Alibaba Cloud, Tencent Cloud, DNSPod, Huawei Cloud, Route 53, OVHcloud, Gandi, Namecheap, DuckDNS, and other providers, finding the public address over IPv4 or IPv6 by URL, network interface, or command. Port forwarding relays TCP and UDP with port ranges, failover targets, connection limits, traffic statistics, and PROXY protocol, while SNI routing lets several services share port 443. Certificates are issued and renewed through ACME with DNS-01 wildcards or HTTP-01, then pushed to other hosts over SSH. Web services add per-domain reverse proxies, redirects, and static sites with HTTP/3, WebSocket, load balancing, health checks, rate limiting, caching, and sign-in through OIDC, GitHub, Google, or TOTP-protected shared users. A WAF running the OWASP Core Rule Set and fail2ban-style jails with trap ports and nftables bans guard the edge. Manage Docker containers and Compose projects with one-click upgrades and rollback, open SSH sessions with an SFTP file manager, run ping, traceroute, and speed tests, and receive alerts in Telegram, Discord, Slack, ntfy, or email. An audit log, config history with diff and rollback, encrypted backups, scoped API tokens, and Prometheus metrics round it out. 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 database container is probably not at 98 percent memory, whatever docker stats claims, because most of that figure is reclaimable page cache; ContainerFlow subtracts the full cache and shows the memory your containers actually hold. Point it at a Docker socket and it draws the whole estate as a living map: every Compose project discovered automatically, services grouped and colour coded, and the connections between them inferred, app to database, proxy to app, worker to broker. CPU and memory refresh every three seconds, the graph flashes when a container starts, stops, or restarts, and seven days of metric history wait in a local store when you need to know what happened overnight. Click any node and a detail panel opens with live logs you can filter by stream, an inline terminal that runs commands inside the container, and buttons to start, stop, restart, rebuild, recreate, or remove it. The same panel teaches as it works, flagging containers that run with no memory limit, no CPU limit, or no restart policy, while Discord webhooks fire when a container you care about crosses a threshold you set. 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.

Ever Works transforms a single text prompt into a fully researched, written, coded, and deployed website through autonomous AI agents that operate on a configurable 15-step generation pipeline. Unlike one-shot builders, it continuously improves generated content on a schedule, keeping sites fresh without manual intervention. The platform integrates with six AI providers (OpenAI, Anthropic, Google, Groq, Mistral, Ollama) via gateways like OpenRouter and Vercel AI Gateway, while its plugin system connects ten search providers including Tavily, Brave, Exa, SerpAPI, and Perplexity for deep autonomous research. Every generation is Git-native — code and content live in your own GitHub repositories as commits, providing full version control, portability, and zero vendor lock-in. The monorepo ships a NestJS 11 REST API with JWT authentication, a Next.js 16 web dashboard for managing works, a CLI for terminal operations, an MCP server for AI agent integration, and admin tooling. Content management supports items, categories, tags, and collections, while deployment targets include Vercel and Kubernetes. Background processing runs on Trigger.dev with BullMQ scheduling, and monitoring leverages Sentry plus PostHog for error tracking and product analytics. The platform supports OAuth via GitHub and Google, subscription billing, email notifications, and AI chat conversations for natural-language interaction with your generated works. 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.

Every production incident starts the same way: someone asks "what do the logs say?" and the answer takes 45 minutes to find. LogTide collapses that search into seconds with a unified observability platform that indexes logs, traces, and metrics into a single queryable interface, backed by your choice of TimescaleDB, ClickHouse, or MongoDB. The log search interface supports full-text queries across millions of entries with filters for trace ID, session ID, project, service, hostname, and severity level, plus a live tail mode that streams new log lines as they arrive. Distributed traces render as waterfall timelines showing every span, its duration, and cross-service dependencies, while correlated logs for each trace are one click away. The metrics explorer visualizes OTLP gauge and counter data from your applications with system CPU, memory, disk, and network panels that update in near real-time. Where LogTide diverges from standard observability is its built-in SIEM engine: Sigma-compatible detection rules scan incoming logs for security threats like SQL injection, privilege escalation, lateral movement, and C2 communication, surfacing findings on a dedicated security dashboard with severity distribution, detection timelines, and affected service breakdowns. Alerting pushes notifications to Email, Slack, or Discord webhooks when thresholds trip or security rules fire. Native SDKs for Node.js, Python, Go, PHP, Kotlin, and Ruby ship logs with retry logic and circuit breakers, and the platform accepts OpenTelemetry data natively. 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.

That yogurt hiding behind the ketchup expired three weeks ago, and the flour you bought "just in case" has been sitting in the pantry since last winter. EverShelf replaces mental guesswork with a structured inventory system that tracks every item across pantry, fridge, freezer, and custom locations with precise quantities, expiry dates, and consumption patterns. Scan barcodes with your phone camera to add products instantly, or let the Gemini AI identify items from a photo and estimate shelf life based on storage location. The dashboard surfaces expired items and upcoming expirations with color-coded urgency badges, while anomaly detection flags suspicious quantities and consumption predictions that deviate from your history. Opened products get reduced shelf-life calculations; vacuum-sealed items get extended dates automatically. The recipe engine generates context-aware meal suggestions from your current inventory, prioritizing ingredients approaching expiry so nothing goes to waste; each recipe includes step-by-step cooking mode with text-to-speech narration and timer integration. A smart shopping list auto-populates when stock hits zero and syncs bidirectionally with the Bring! app, with AI-estimated prices per item and consumption forecasts showing when you will need to restock. For Home Assistant users, a native HACS integration provides 22 sensors, expiry calendars, bidirectional todo-list sync, and voice assistant support for adding items hands-free. A dedicated Kiosk mode optimizes the interface for wall-mounted tablets with BLE scale integration. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Email discussion lists - the venerable listserv pattern where one address relays to a whole group - without the notorious setup pain of Mailman or Sympa: that is Gray Duck Mail. Its architectural trick is requiring no mail server of your own: the C#/ASP.NET Core app monitors a POP3 inbox at any external email host supporting POP3/SMTP and aliasing, relays each incoming message to all list members via SMTP, and archives it for browsing in the web interface. Replies route back to the entire group automatically. The tedious parts of list management are handled by convention: dedicated aliases process join requests, subscription confirmations, and unsubscribes, while a bounce alias in the return-path catches delivery failures so dead addresses get handled instead of silently rotting. The web administration interface creates and removes lists, manages contacts, browses message archives, and imports or exports the local database for backup. GPLv3-licensed, Docker-distributed, and fully code-documented, it targets exactly the groups email still serves best - neighborhoods, schools, congregations, workplaces, and families - where one message keeping everyone in the loop beats yet another app nobody wants to install.

With over 430 GitHub stars and designed for DevOps engineers, platform teams, and homelab operators, Sencho is the self-hosted Docker Compose control plane that gives you a real operational cockpit without abandoning file-on-disk compose workflows. The web dashboard provides live CPU, memory, and disk sparklines per container, one-click start/stop/restart controls, and a Monaco-powered YAML editor with syntax highlighting, inline diff, and one-click rollback. Compose files remain the source of truth on the host filesystem. Multi-node management connects remote Sencho instances via authenticated HTTP and WebSocket proxy using long-lived API tokens, with no SSH access or exposed Docker sockets required. The Pilot Agent establishes an outbound-only WebSocket tunnel for nodes behind NAT, CGNAT, or strict firewalls. Blueprints define compose intent once and deploy it across label-targeted nodes, with drift detection keeping the fleet aligned. Fleet Federation provides cordon and pin controls for maintenance windows, while Fleet Actions execute bulk deploy, stop, and restart operations by stack label across the entire infrastructure. The security suite includes Trivy vulnerability scanning, deploy enforcement policies, SARIF and SBOM export, and Fleet Sync to replicate scan policies across replicas. Additional capabilities include 199+ one-click app templates, Git source integration, atomic deploys with auto-rollback, auto-heal, scheduled operations, webhooks, and custom S3 off-site backups to MinIO, R2, B2, or AWS. 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.

Telegram Desktop's export is a file you make once by hand; Telegram Archive is a self-hosted backup that keeps saving your chats on a schedule and in real time, then lets you read them in a viewer that looks like Telegram. After one login with the code Telegram sends you, it stores messages, photos, videos, voice notes, stickers, documents, and link previews, saving each file once even when several chats share it. A live listener captures new messages, edits, and reactions as they happen, and a daily full pass fills any gaps. Every edit keeps its earlier text as a version, and with deletion tracking switched on, deleted messages stay in the archive marked as deleted. The viewer offers folders, forum topics, archived chats, pinned messages, polls, shared media, and search across every chat, plus a What changed feed of deletions, edits, and transcripts. Voice notes can be transcribed into searchable text by a server you run or rent. Family or colleagues get logins limited to chosen chats, or a share link that opens a single chat. One archive holds several accounts, a Telegram Desktop export can be imported for older history, and twelve themes suit phones and desktops. 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-or-later licensed.