2422 applications
Cortex Hub screenshot thumbnail

Cortex Hub

Cortex Hub gives every AI coding agent your team runs a shared brain, so what one agent learns in a repository is still there when the next agent, or the next person, opens it. Starting a session recalls the team knowledge and your own memory for that project, shows who else is editing, and picks up any task waiting for you. Agents search code by meaning and structure rather than text strings, tracing symbols, callers, and the blast radius of a change before touching it. Findings, file risks, and hard-won lessons are stored against the files they belong to, so they resurface exactly where they matter. Ending a session runs build, type, and lint checks, reports the result, and leaves a summary the next session starts from. A conductor can hand tasks to worker agents on other machines and track them centrally, while the dashboard shows sessions, keys, usage, and token savings across the team. Embeddings run locally by default, so your code memory never leaves the building just to be searchable. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
Nyro screenshot thumbnail

Nyro

Point Claude Code, Codex CLI, Gemini CLI, or any OpenAI, Anthropic, or Gemini SDK at one address and Nyro routes every request to whichever model provider you choose. The gateway translates protocols on the fly, including streaming, reasoning blocks, and tool calls, so a tool built for one API can run on a model from another. Define virtual model names, bind each to one or more providers, and pick weighted load balancing or priority failover; unhealthy targets are skipped and recover automatically. Issue API keys with limits on requests and tokens per minute and per day, and bind each key only to the models it may call. Exact and semantic caching return repeated answers instantly. A request log records provider, model, token counts, latency, and streaming speed, and usage charts break traffic down by model and provider. The Connect page generates ready-to-paste samples in Python, TypeScript, and cURL, plus one-click configuration for popular coding CLIs. Choose an embedded database for a single host or an external PostgreSQL or MySQL server for production, and run the gateway, the admin UI, or both as separate processes. 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.

Deploy
Limelit Open screenshot thumbnail

Limelit Open

When a buyer asks ChatGPT, Claude, or Perplexity which product to choose, Limelit Open shows whether your brand appears in the answer, where it ranks, and which sources the engines trusted. You define the prompts your market actually asks, register your competitors, and the tracker runs every prompt against seven engines on a schedule you control: ChatGPT, Claude, Perplexity, and Gemini through vendor APIs with web search on, plus Google AI Overviews, Google AI Mode, and Bing Copilot through scraper providers, each result labeled by how it was collected. Every stored answer is searched for your brand and each competitor with the rank of the list item they appear in, so visibility, share of voice, average position, and citation share rest on readable evidence rather than a black-box score. Click any number and you land on the full answer text with matches highlighted, the searches the engine ran, the brands it named, and every cited URL classified as yours, a competitor's, social, informational, or other. A prompt by engine grid makes weak spots obvious, and the built-in MCP server lets Claude or another assistant query the same data in plain language. Runs are capped by a daily ceiling you set, prompts and answers live in one SQLite file, and a single export command dumps the whole instance as JSON or CSVs for your own reporting. 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.

Deploy
Xianyu SaaS screenshot thumbnail

Xianyu SaaS

Xianyu SaaS runs all of your Xianyu (Goofish) shops from one self-hosted console, answering buyers with AI, delivering digital goods the moment orders verify, and keeping every store isolated in its own process. Add each shop by scanning a QR code in the Xianyu app, then switch between stores from one header while the overview tracks messages, replies, delivery results, orders, and pending tasks. The AI customer service center lets you pick a service persona, write shop-wide reply requirements in plain language, and maintain a separate knowledge entry for every product, covering audience, specifications, usage, delivery notes, and after-sales wording. Keyword rules answer the repetitive questions first, with product-specific rules outranking store-wide ones, and anything unmatched falls through to the AI with product knowledge and chat history in context. When a buyer pays, the system re-checks the platform order before delivering, drawing card keys one to fifty at a time from named pools, sending netdisk resources, or posting fixed text instructions, with a five-minute sweep catching orders missed while a shop was offline. A conversation workbench lets you search chats, take over from the AI with one click, send up to eight queued images, and jump from any order straight into the buyer's thread. A built-in operations agent manages a shop through chat, updating product knowledge, toggling reply rules, or binding delivery stock on request. 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.

Deploy
hy2scale screenshot thumbnail

hy2scale

A handful of cheap servers in different countries become one routed network with a browser dashboard on top. Nodes link directly through Hysteria 2 QUIC tunnels with no coordination server, and traffic can leave through any node, several hops deep. The overview dashboard, topology graph, node list, and world map show latency, uptime, and live rates for every peer. Each node can also serve SOCKS5, HTTP, Shadowsocks, Trojan, L2TP/IPsec, IKEv2, OpenVPN, and WireGuard clients, and the VPN servers run in userspace without extra privileges. Policy sets route traffic by user, source, destination, domain, country, or ASN, and each user can get a fixed exit, quality failover, or aggregated paths. Traffic limits with periodic resets, upload and download rate caps, and expiry dates control how much each account can use. Hole punching connects nodes behind NAT, and peers can carry several addresses. A built-in certificate authority manages TLS certificates. An audit log records every connection, and ping, traceroute, throughput tests, and a terminal sit on the Tools page. Backup and restore, signed in-app upgrades, and an interface in English, Chinese, and Korean round out the admin side. 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.

Deploy
KeiRouter screenshot thumbnail

KeiRouter

One endpoint, 130+ models from 90+ providers: KeiRouter is a self-hosted AI gateway, so apps, coding tools, and agents connect once and stop juggling provider keys. Your code speaks OpenAI Chat, OpenAI Responses, Anthropic Messages, or native Gemini, and KeiRouter translates to whichever upstream you want, including AWS Bedrock, Azure AI Foundry, Vertex, Snowflake Cortex, and self-hosted runtimes like Ollama and vLLM. Fallback chains keep requests moving when a provider goes down or hits a rate limit, using priority, round-robin, latency, or cost ordering, so coding sessions do not stop mid-task. Five token savers compress prompts on the way in and trim responses on the way out, with a live dashboard showing savings recovered. A response cache answers repeated prompts instantly for zero marginal cost, with optional semantic matching. Per-key budgets and rate plans set USD, token, RPM, and concurrency limits with auto-cutoff, stopping surprise bills. Guardrails scan for PII, prompt injection, toxicity, and banned topics at global, provider, model, chain, and key scopes, with a monitor showing what got blocked and what it cost. The dashboard tracks usage by provider and model, latency, a live console tracing each request through its fallbacks, and provider health. You can import from 9router or OmniRoute, white-label the portal for your team, and run replicas on Postgres and Redis for high availability. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
Edi Life OS screenshot thumbnail

Edi Life OS

Edi Life OS puts the habits, goals, projects, money, focus sessions, and notes that usually live in five separate apps into one calm dashboard on your own server. Start the day from an Overview that rolls focus, habit trends, goals, finances, and the week ahead into one readable score. Connect long-term goals to six life areas, drive progress from a checklist, a measure, or a habit you actually keep, and use weekly, monthly, or quarterly reviews to choose the next honest step. Log daily habits with streaks and monthly progress, run timed focus sessions with short and long breaks, and keep a history of the deep work you finished. Track expenses, income, budgets, debts, and credits in your chosen currency, including recurring entries that land straight in the ledger. Plan projects on draggable Kanban boards with labels, priorities, due dates, checklists, comments, and attachments, then see card deadlines and money dues together in one calendar. Capture Markdown notes with preview and export, pin sticky notes with colors and connections, and give each account its own private workspace, theme, and currency. Ask an AI assistant through the optional MCP server to read your dashboard, create goals, log habits, or record expenses through a token-protected API that never touches the database directly. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
DodoGuard screenshot thumbnail

DodoGuard

Before an AI agent meets real users, put it through a security checkup it cannot sweet-talk. DodoGuard is a web console and command line where teams register their agents, run evaluation and red-team tasks against them, and decide if each one is cleared for launch. The overview page shows a security index, open risks, remediation counts, and a pipeline that runs from asset intake through detection and remediation to launch monitoring and audit reports. An asset ledger lists every managed agent with its platform, environment, and risk level. A guided wizard creates assessment tasks that pick a test library for prompt injection, instruction leakage, tool misuse, and output risks, then runs black-box conversations against the agent. Evaluation configs cover prompts, providers, variable cases, and several assertion types, with OpenAI, Anthropic, Azure, Bedrock, Ollama, and any OpenAI-compatible endpoint supported. Findings land in a closed-loop board where owners confirm, fix, retest, and close each risk, and finished tasks export as reports for release evidence. Docker Compose with SQLite brings up the web UI on port 3000, and the same engine runs in continuous integration. Security teams use it for launch gates, platform owners use it for regression checks after prompt changes, and auditors use it for evidence. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
MATE screenshot thumbnail

MATE

Change an agent's prompt, model, or audience from a dashboard and watch it go live without a single redeploy. MATE opens in a Work Room where any root agent can be picked from a card grid and chatted with directly. The Studio holds the builder: a drag-and-drop canvas draws parent and child agents, attaches tools and MCP servers, and keeps every configuration versioned with one-click rollback. Trace Replay plays a past conversation back across that canvas so each hand-off is visible. A template library imports ready-made agent teams, from research pipelines to support desks. The Control Room covers governance: role-based access per agent, dollar costs per agent and project, budgets that warn or block, guardrails for personal data and prompt injection, and alerts to Slack, Discord, email, or a webhook. Eval suites score replies by exact match, similarity, or an LLM judge, and a Playground compares models or prompts side by side on score, speed, and cost. Agents can be embedded as a chat widget, called through an OpenAI-compatible endpoint, or exposed over MCP and A2A. Agencies running client agents and platform teams juggling dozens of them can manage the lot from one dashboard. 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.

Deploy
Narralume screenshot thumbnail

Narralume

NarraLume is a writing studio for long novels where the AI proposes and you dispose, so a book stays yours across tens of thousands of words. Everything lives around the story bible: your stated intent, outline, entities, confirmed facts, relationships, chronology, and foreshadowing, kept as the single source of truth that planning, drafting, and review all read from. You can write chapters by hand in the studio, save versions and comments, ask for a selection edit, or delegate a chapter, a run of chapters, or a whole quick-creation plan to a model; whatever comes back arrives as a candidate with diffs, never as silent edits to your manuscript or canon. Review findings come with evidence you can accept, reject, or mark as false positives, and when generated prose collides with a locked fact the task stops and waits for your ruling instead of improvising around it. The run center keeps every AI job's steps, model calls, and checkpoints recoverable, the long-form lab searches story memory and previews plot impact without touching the book, and delivery ends with quality checks, exports, snapshots, and full-library backups. 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.

Deploy
Coach Watts screenshot thumbnail

Coach Watts

Coach Watts is a self-hosted AI endurance coach that reads your training, recovery, sleep, and nutrition data together and tells you, each day, whether to push or rest. Connect Intervals.icu, Strava, Whoop, Oura, Garmin, Withings, Wahoo, Polar, Fitbit, Hevy, Yazio, Rouvy, or Ultrahuman and every workout, HRV reading, sleep score, and meal lands in one athlete profile instead of fourteen separate apps. Each session gets a detailed breakdown with an execution score, and the performance view tracks Fitness, Fatigue, and Form alongside power curves so you can see a training block working, or quietly burying you. Daily recommendations weigh HRV and sleep before suggesting intensity, and the interactive chat answers questions against your own data when you want the reasoning behind a call. Adaptive plans generate around your schedule and goals, then adjust as life interferes. Nutrition tracking applies metabolic fueling logic that shifts between Eco, Steady, and Performance modes based on session intensity, so long rides get fed differently from recovery spins. Coaching alerts and system messages arrive in the dashboard, Telegram coaching is available for nudges on the move, and the whole platform speaks more than ten languages with timezone handling that follows traveling athletes. A Google account provides sign-in and the Gemini models behind the analysis, while your synced history stays 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. Apache-2.0 licensed.

Deploy
TG Vault screenshot thumbnail

TG Vault

TG Vault turns Telegram into the front door of your private archive, pulling files out of channels and groups into storage you control and managing them from a proper web file manager. Batch-download channel and group media by date range or tag, subscribe to sources so new posts sync automatically, and upload, search, organize into folders, and preview media from the browser. Every transfer runs as a managed task with live progress, failure details, and pause, resume, and retry controls, whether it was started from the web console or the Telegram bot. Point the vault at local disk, OneDrive, Google Drive, Amazon S3, Aliyun OSS, WebDAV, or an OpenList instance, and let the optional qBittorrent extension forward finished downloads into the same storage, cleaning up sources or keeping them seeding. Access stays locked down with an administrator password, a bot user allowlist, and TOTP two-factor authentication, while one install script deploys and upgrades the whole Compose stack. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
Overclick screenshot thumbnail

Overclick

OverClick is the task board where your AI agents clock in: you write the assignments, they claim the work, and you stamp what actually got done. A card here is a contract, not a ticket: what should happen, why it matters, and a plain-language test script that says how to confirm it, all written before anyone starts. You tell your agent to grab the next task, and it claims the card over MCP, declares the CLI and model it really runs on, receives a self-contained briefing with the mission context and branch convention, and the card slides into progress. When it finishes, the handoff lands with a summary, evidence, branch and pull request links, and measured telemetry, the tokens per model and minutes the run actually took, read from the session transcript rather than guessed. Every card keeps three roles straight, who asked, who executed, and who reviews, and only a human can mark it validated; reopening with a comment puts your note in front of the agent's next claim. Big decisions can start as RFC cards whose approval spawns the execution cards, and insights roll up what each project, mission, and model consumed. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
PaperPull screenshot thumbnail

PaperPull

Years of bank statements, pay stubs and receipts sit scattered across dozens of websites, each demanding a login and offering one PDF at a time. PaperPull fetches that whole history for you: sign in yourself in a real browser window, answer the two-factor prompt, and it downloads statements, receipts, pay statements, W-2s and tax forms from 73 supported providers including Chase, Amex, ADP, Amazon, Walmart, Vanguard and Verizon. The tool only ever downloads; it never pays a bill, moves money or changes a setting, and that read-only promise is enforced by construction rather than by policy. Every archive is checked for freshness and for holes in the middle, so a series that looks current but quietly skipped three months is flagged by name, with per-account cadence learned from your own documents. Receipts become one long spreadsheet of every item you have ever bought across every store, with prices and dates, while transactions are read out of statement PDFs into workbook rows that are verified against each statement's printed beginning and ending balances. New documents can flow straight into a Paperless-ngx consume folder, everything runs under a password you choose on your own network, and no cloud account is involved anywhere. 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.

Deploy
M3U Studio screenshot thumbnail

M3U Studio

M3U Studio turns a tangled IPTV playlist into a tidy, published subscription you would actually hand to your player. Import channels from an M3U or TXT file, pasted text, or a remote link, then organize them properly: drag single channels or whole multi-selections into new groups, rename, reorder, and watch the list reshape itself as you work. Nothing goes live until you say so. Edits accumulate in a draft with undo and redo, and publishing keeps the last 30 configurations so a bad change rolls back in seconds. Channel logos stop being a scavenger hunt, because a unified logo library matches artwork automatically by name and alias, with search and batch upload when you bring your own. Select a pile of channels and fix them together: replace URL text, change groups, set EPG addresses, or move copies into another playlist, then run response checks to spot dead streams before your player does. Each playlist publishes as its own M3U or TXT subscription, or merged into a combined feed, under a custom short address that is easy to type into a TV box. Per-channel EPG, catch-up, and fast channel change settings travel with the export. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-2.0 licensed.

Deploy
Notesd screenshot thumbnail

Notesd

A notes app that is deliberately not a second brain: notesd keeps your grocery lists, journals, and work notes on a server you run, and syncs them to your phone for fully offline use. The web app and the native Android and iPhone apps each keep a complete local copy, so you can write on a subway and watch everything merge when a connection returns; conflicting edits are combined, or preserved as a linked conflicted copy instead of silently overwriting. Notes are stored as Markdown, so exporting your data or mirroring it to a folder of .md files is always one command away. Tags typed anywhere in a note, including nested ones like #home/garden, collect automatically in the sidebar, and Spaces keep work, personal, journal, and recipes in separate contexts. Full-text search runs across titles and bodies, indexed and ranked both on the server and on your phone. Individual notes can be locked with AES-256-GCM encryption performed on your device, unlocked by password, passkey, or biometrics, while the server only ever stores ciphertext. A few accounts per server, each with its own database, make it easy to host notes for family or friends. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
Excaliself screenshot thumbnail

Excaliself

Excaliself turns the Excalidraw canvas into your team's own whiteboard server, where every sketch, diagram, and flowchart lives in your database instead of a vendor's cloud. The home screen works like a file cabinet for drawings: nest them in folders, star the keepers, drag files between spaces, and find anything again by title or by the text inside the drawing. Share a link and teammates edit together in real time with live cursors and follow mode; links can stay members-only or open to guests who have no account at all. A shared Team space sits next to everyone's private space, and one team library holds the shapes and icons the whole group reuses. AI clients can join with a personal access token: Claude Code or Claude Desktop can search your drawings, read what a diagram says, and create new ones from shapes or a Mermaid flowchart. Accounts are invite-only, single sign-on covers Google, Microsoft, and any OIDC provider, and admins manage members, roles, and password resets from Settings. Deleted drawings rest in a trash folder for thirty days before they are purged, and everything auto-saves as you draw. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
Saki Panel screenshot thumbnail

Saki Panel

Saki Panel is a self-hosted operations console that manages your game servers, containers, and background processes across multiple Linux machines, with an AI assistant sitting inside the workspace when something breaks. Start, stop, restart, and monitor nine kinds of instances, from Minecraft and Steam game servers to Docker containers, Compose stacks, Node and Python apps, and plain shell commands. Remote nodes connect over SSH and report CPU, memory, and disk metrics to a cluster dashboard, so every machine is visible in one place. When an instance crashes, Saki Watch records the exit and its error fingerprint, then helps diagnose the cause from live logs, files, and metrics instead of making you copy text between a terminal and a chat window. Proposed fixes appear as diffs that need your approval, are graded by risk level, and can roll back automatically if verification fails after a patch. Day to day work happens in the same console: a web terminal, a file manager with an editor and archive support, database tools for SQLite, MySQL, PostgreSQL, and Redis, and cron-scheduled tasks with full run history. Role-based access with dozens of permission codes, audit logs, and incident notifications through webhooks or Telegram keep a small team in 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.

Deploy