OpenChoreo gives developers a complete open-source internal developer platform for Kubernetes: a self-service portal to build, deploy, and run applications without wrestling raw cluster YAML. In the portal you create a component from source code or a container image, expose it through endpoints, and promote it across environments with a few clicks. Platform engineers define the golden paths behind that simplicity: component types, traits, and workflows set the rules for how workloads are built, secured, and connected. The control plane translates each declaration into the Kubernetes resources it needs, then keeps the portal in sync with what is actually running. Built-in CI builds from source with Buildpacks and Argo Workflows, and GitOps delivery keeps every environment reconciled with the declared state. Metrics, logs, and traces surface in the same portal, organized by component and environment instead of pod names and namespaces. Role-based access control, project isolation, and traffic policies draw the boundaries between teams, and platform analytics show how the platform itself is being used. Existing Backstage portals can adopt OpenChoreo as plugins, and developers can also work through the CLI, GitOps files, or AI agents. 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.

Nerve is the web cockpit for OpenClaw, giving you one real-time screen to run an entire fleet of AI agents instead of chasing them through chat threads. Every agent keeps its own workspace, memory, identity, and skills, and you can switch between agents, browse their files, and edit memory or configuration in a tabbed editor during a live conversation. Work moves onto a kanban board where subagents pick up delegated tasks, and returned work waits in a proposal inbox for your review before it is accepted. Cron jobs run as their own sessions in a navigable session tree, so scheduled automation has logs and output you can actually inspect. Voice is a first-class input: push to talk or use a wake word, watch live transcription, and hear replies spoken back in your chosen language. Ask for a chart and the answer arrives as a real rendered chart, with diffs, file previews, and highlighted code inline in the stream. Token usage, running costs, and context pressure stay visible on every session, so long tasks never quietly drain your budget. Run it privately on localhost, reach it over your LAN behind password authentication and signed-cookie sessions, or keep access inside a Tailscale tailnet. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

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.

CELERITY Panel puts every Hysteria 2 and Xray VLESS node you run behind one clean web panel, so a fleet of proxy servers behaves like a single service. Add a node and the panel connects over SSH to install the software, certificates, and port hopping for you. Server groups map users to the nodes they may use, and load balancing spreads them by real server load. Cascade topology chains servers together, so clients connect to one node while traffic exits through another, drawn on a visual network map. Traffic rules block advertising domains and unwanted destinations or route selected traffic through custom proxies. Each user receives a subscription link that formats itself for Clash, Sing-box, Shadowrocket, and Hiddify. The dashboard watches online users, traffic volume, and node health in real time, and an in-browser SSH terminal reaches any node without leaving the panel. Programmatic control comes through scoped API keys with IP allowlists and rate limits, signed webhooks announce events as they happen, automatic backups land on S3-compatible storage, and AI assistants can operate the panel through its MCP interface. Two-factor authentication protects the admin login. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Aural runs the interview for you: describe the role in plain language, share one link, and its AI conducts the whole conversation with each candidate. The generator turns your brief into a complete interview with questions, assessment criteria, and recommended settings, or you build the flow yourself in the editor. Candidates join by chat, voice, or video, and the interviewer adapts in real time, adjusting follow-up depth, tone, and direction as answers develop. Technical rounds run inside the session with a full code editor for live programming questions and a whiteboard for sketching designs. Anti-cheating controls watch for tab switches, blocked external paste, and extra monitors, logging every event into a per-session integrity report. When the session ends, an AI report scores each question, pulls highlights, and names the areas to improve. Teams manage organizations, projects, and role-based access, invite candidates individually, in spreadsheet batches, or by parsing uploaded resumes, and rehearse with a practice mode that gives spoken feedback after every answer. Interviews speak English and Chinese, and the platform connects to the language model provider you already use. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

SpamEater gives you a disposable inbox on your own domain that burns itself down 24 hours after you create it. Type any name, or roll the dice for a random one, and mail sent to that address lands in a clean web inbox that refreshes itself every few seconds. Open a message and HTML mail renders faithfully, adapted to the dark interface, with inline images embedded and remote images blocked until you ask for them, so tracking pixels never fire behind your back. A live countdown in the corner tells you exactly how long the inbox has left, and a copy button grabs the address for the form you are about to fill. There are no accounts to create, no passwords to remember, and nothing to recover once the timer ends: the inbox, the messages, and the paper trail vanish together. Behind the scenes the service takes its own security seriously, with a web application firewall, intrusion prevention, rate limits, and mail bodies encrypted at rest. Dark and light themes switch with one toggle. Developers use it to test signup flows and password resets, and everyone else uses it to keep a real address out of reach of newsletters. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Infrastructure diagrams do not have to look like a ransom note of boxes and arrows: FossFLOW draws your network as a clean isometric map in the browser. Drag servers, routers, databases, and cloud services from the component library onto the angled grid, then link them with connectors that snap between nodes in click or drag mode. Multiplexed connectors bundle parallel links into tidy runs, rectangles and freehand annotations mark zones and notes, and text labels explain the flow. A diagram of a messy production network becomes a picture a new hire can read in one sitting. Work saves automatically every few seconds, exports to a JSON file you can keep in version control, and imports back just as easily. Run it as a shared team instance and diagrams persist on the server, filed under the project name, protected by optional basic authentication. The editor also installs as an offline-capable progressive web app, so the canvas keeps working on a plane and syncs nothing anywhere you did not send it. Documentation authors use the exported views in architecture guides, and engineers sketch proposals before touching real hardware. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

FCaptcha guards your forms with an invisible check that spots bots, headless browsers, and AI agents steering real browsers, all from a server you run yourself. Drop the widget into a signup or contact form and it quietly watches how the visitor actually behaves: pointer movement, typing cadence, scroll shape, and dozens of other signals that separate a person from a script. Vision agents that screenshot and click, and computer-use agents driving a browser through automation protocols, leave input traces the scoring engine catches. Self-declaring crawlers get flagged by name, and signed agent requests are verified cryptographically so polite, identified bots can be allowed while anonymous automation is blocked. A proof-of-work challenge adds a liveness gate behind the scenes. Humans see no puzzle at all, in any of 34 languages, and the widget meets accessibility standards for screen-reader and keyboard-only visitors. Your backend verifies each token through the same siteverify contract that Turnstile, reCAPTCHA, and hCaptcha use, so switching providers is a change of address rather than a rewrite. No cookies are set, no visitor data travels to a third party, and nothing phones home. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Your team's documents sit in folders nobody can search, and the answer to a simple question hides on page 40 of a PDF someone saved last year. Pharos ingests PDFs, scans, Word documents, presentations, and spreadsheets into a local knowledge base, then answers questions against that library with citations traced back to the exact page. Hybrid retrieval finds the passages that matter, and every answer carries its evidence so readers can verify the claim in the source. Access control decides visibility per person: an API key resolves to an identity with a tenant and group memberships, retrieval filters hard to only the documents that identity may see, and a document with no permissions attached stays invisible to everyone. Two doors lead into the same library. The HTTP API runs a closed question-answering pipeline that retrieves, grounds, and answers in one call, and coding agents connect through MCP to decide for themselves when to retrieve, how to rewrite a query, and when a question needs multiple hops. A resident daemon keeps the search index and models warm, so every session shares one backend instead of reloading heavy resources. The deployment scales from one machine to replicated application tiers behind a load balancer. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Turn your happiest customers into a tracked referral channel, with rewards, payouts, and fraud checks handled in one place. A small JavaScript snippet on your site records which referrer drove each new customer, and personalized landing pages greet visitors with the name of the friend who invited them. You design reward structures per program, mixing one-off bonuses, recurring commissions, or loyalty incentives, then decide how money moves. Manual approval queues every reward for review, or automatic rules validate and disperse payments on a schedule you set. Referrers get their own portal showing referral links, conversion counts, and reward balances, and affiliates work from a dedicated partner portal with the same visibility. Nudges automatically remind quiet referrers to share again, and fraud monitoring flags suspicious activity before it turns into payouts. Engagement analytics chart program performance across referrers, campaigns, and time, and a sandbox testing environment rehearses the whole flow before real customers arrive. Google sign-in and email delivery through Resend slot in through environment settings, and the Docker Compose deployment brings up the portal, database, and seed data in one command. 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.

OpenCharts puts a full trading terminal in your browser, with candlestick charts, drawing tools, indicators, and a paper-trading account funded with one hundred thousand dollars. You switch between eight timeframes from one minute to one week, overlay volume, bid and ask lines, and a bar countdown, then add SMA, EMA, RSI, MACD, Bollinger Bands, ATR, Stochastic, or VWAP studies from the toolbar. The drawing rail covers trend lines, rays, channels, Fibonacci retracement and extension, shapes, and text, with magnet snapping to price levels and an object tree that manages every annotation. Position tools calculate risk, reward-to-risk ratio, and position size against live account equity as you drag them across the chart. Market, limit, and stop orders rest in the book, trigger on price ticks, and honor take-profit and stop-loss levels you can drag directly on the chart. Positions mark to market on every tick, and the panels track equity, balance, used margin, and free margin in real time. Session replay rewinds one-minute history and plays it forward at up to ten times speed, so you can rehearse entries against past price action. A trade journal records notes, tags, emotions, and ratings per trade, filtered by symbol when you review the week. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

MakersVault gives your scattered 3D print files and creative artwork one searchable home, so you stop loading models into a slicer just to remember what they are. You create folders and subfolders for projects, then drag and drop single files, batches, or whole folders straight into the library from your browser. Every model tile carries a rendered preview, and double-clicking opens an interactive 3D view you can rotate and inspect before downloading anything. Tags attach to any file, batch tagging covers many selected models at once, and tag tabs plus sorting by name, size, type, or folder keep large collections browsable. Notes on individual files record print settings, filament choices, or assembly reminders right beside the model they describe. Imports pull models directly from MakerWorld, Thingiverse, and Printables links, and zip archives prompt you to keep only the files you actually want. Supporting documents ride along with each model and travel inside its ZIP downloads, and prepared print data surfaces printer, material, nozzle, and time estimates on the card. The Open in Slicer button hands a model to your configured slicer through the desktop bridge, and themes from light and dark to neon accents restyle the whole workspace. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

OneGlanse tracks how ChatGPT, Perplexity, Gemini, Claude, and Google AI Overview mention, rank, and recommend your brand, using the same product interfaces your customers actually see. You add your brand, competitors, and the questions buyers ask, then start prompt runs against one AI product or all five in a single pass. Every run stores the complete answer text together with the citations and source domains the answer relied on, so you can open any response later and read exactly what was said. A model you connect with your own OpenAI or Anthropic key reads each saved answer and records mentions, ranking position, sentiment, and recommendation strength. The dashboard rolls those readings up into presence rate, average rank, top source, and top competitor views that update as new runs land. Competitor tables show which rival brands appear beside you, how often they show up, and how their sentiment compares across providers. Source reports rank the publishers and pages that AI answers cite most, down to citation share per domain. Perception panels collect the claims, pricing language, and strengths that answers repeat about your brand. Self-hosted deployments schedule recurring runs, transfer your signed-in provider sessions to the server, and keep prompts, answers, and scores in your own database. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Ziit tracks where your coding hours actually go and shows the answer in a dashboard you host yourself. Install the extension in VS Code, any of its forks, or a JetBrains IDE, and every editing session streams to your instance with its project, language, editor, file, branch, and operating system attached. The dashboard filters by time range and breaks your work down by project and language, so a week of effort becomes a readable chart instead of a vague memory. You sign in with GitHub or email and password, import existing history from WakaTime or a WakAPI instance, and keep building on years of data instead of starting over. README badges embed live coding time for a project into any repository page, turning your profile into a quiet proof of work. A public stats page summarizes the whole instance, and a public leaderboard ranks who logged the most coding hours, which makes self-hosted instances double as community scoreboards. Because the server, the database, and the extensions are all yours, no third-party service sees which files you opened or how long a private project took. Teams can run one instance for everyone and compare effort across projects with the same filters. 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.

OpenAdServer runs your own ad network on your own infrastructure, ranking every request with machine-learned click predictions instead of static rotation. A request arrives with a slot, user, device, and geo context; the pipeline retrieves matching campaigns, filters them by targeting, budget, and frequency caps, predicts click probability, and ranks survivors by eCPM before responding in milliseconds. You serve banner, native, video, and interstitial formats with geo, device, operating system, demographic, and interest targeting, plus daily and hourly frequency limits per user. Budget pacing smooths delivery across the day so campaigns do not exhaust spend in the first hour. Three prediction models ship ready to train and swap without downtime: logistic regression for speed, factorization machines for feature interactions, and DeepFM for deep learning on your click logs. Automatic feature engineering processes sparse and dense fields, and hot-swapping lets a retrained model replace the live one mid-flight. Impressions, clicks, and conversions stream into event tracking, Prometheus metrics expose full observability, and Grafana dashboards visualize performance in real time. Advertisers, campaigns, and creatives are managed through CRUD APIs, and bid types cover CPM, CPC, CPA, and optimized CPM. Training scripts prepare data from your logs, train a model in a few commands, and report AUC before you promote it. 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.

Docling Studio shows you exactly what a document parser sees, drawing a colored box around every title, paragraph, table, and picture it extracts from your PDFs. Import a PDF, run an analysis, and the result opens with three linked panels: the document tree on the left, the paged preview in the center, and the selected element on the right with its type, page, position, and text or table. Click any box on the page and the same element lights up in the tree and properties panel as other boxes fade away. The layers bar counts each element type and toggles boxes per type, or hides them all to reveal the bare page. You can analyze several documents at once from the list, watch progress percentages on long files, and queue work three analyses at a time. Ask a question and a local model answers from the document, with a reasoning timeline that links each step back to the passage it read. Finished results download as the original PDF, clean Markdown, or Docling JSON for downstream pipelines. AI agents connect over MCP to read and cite your documents, and an optional connection to your own Docling Serve server handles heavier parsing loads. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Building LangGraph agents in code means imagining the graph; LangGraph GUI turns that graph into something you draw, wire, and run from the browser instead. You place a start node, add step nodes, and drag edges between ports to define the flow, with cycles created by simply connecting nodes back toward each other. Condition nodes split execution into green true paths and red false paths, info nodes append context to stage output, and subgraph nodes run a whole named graph inside another one. Tool steps call real Python functions that you define in tool nodes with the familiar decorator style, so file saving, lookups, and custom logic sit inside the visual flow. Graphs save to JSON on your computer, load back for editing, and upload to the server as workflow files ready to execute. You configure which LLM to use and its API key in the panel, run against local models through Ollama or hosted APIs, then download every file the run produced in the workspace. Files upload to the server workspace as working environment, and a cache clean clears it between runs. Example graphs for role-playing loops, lottery branch switches, and tool-using flows show patterns you can copy and refine with your own prompts. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Searcharvester gives your AI agents a private search and research backend that runs entirely on your server, with a web UI where you watch every research job unfold. The search endpoint speaks the Tavily schema, so existing agent code points at your host and queries more than a hundred SearXNG engines without API keys or quotas. Send a URL to the extract endpoint and it returns clean markdown with navigation, footers, and ads stripped, sized in presets from five thousand characters to fully paginated long documents. Three extractors compete on each page and a quality gate keeps the best result, so hard pages still yield readable text. For bigger questions, the research endpoint runs a team of agents: a lead plans sub-questions, researchers gather in parallel, a critic tries to disprove the findings, and a fact-checker re-verifies numbers and dates before the final report arrives with clickable citations. You assign a different model and reasoning level to each role, follow agent branches, the reading graph, sources, and media live, then read the finished report in the same UI. Search settings let you toggle engines per category, test proxies, and apply changes with a targeted restart. A loop guard enforces budgets for calls, tokens, searches, and page reads across the whole job. 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.