2431 applications
Monbooru screenshot thumbnail

Monbooru

Monbooru is a private, tag-based gallery for your own image, video, and manga collection, searchable the way booru sites are, but hosted entirely on your server. Drop files into watched folders and they appear within seconds, with browser uploads, SHA-256 deduplication, and an inbox where new arrivals wait until you have reviewed and tagged them. Local auto-tagging runs ONNX models such as WD14, JoyTag, Camie, and PixAI on CPU or GPU, so a collection gets searchable labels without sending a single image to a cloud service. Tag management covers merges, aliases, implications, and custom categories, while rating tags with an SFW ceiling keep sensitive material hidden until you choose otherwise. Search combines wildcards, OR terms, and exclusions with filters for folder, date, size, dimensions, and AI generation settings, and saved searches keep favorite queries one click away. Batch actions retag, move, delete, or auto-tag whole selections at once, and the built-in manga reader opens CBZ and ZIP archives as single items. Image pages record sources, artist commentary, and your own notes, and near-duplicate detection lines up lookalikes side by side for cleanup. Multiple galleries can live in one instance, each with its own folders and database, and an optional password plus scoped REST API tokens control who and what can connect. 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
Jentic One screenshot thumbnail

Jentic One

Jentic One is a self-hosted execution layer that lets AI agents call real APIs through a broker that checks permissions and injects stored credentials, so agents do useful work without ever holding your API keys. You register the APIs an agent may use, store each credential once on your own infrastructure, and approve which agents can connect. Every call the agent makes passes the permission check first, and denied requests stop at the broker with a 403 instead of reaching the outside service. Allowed calls go out with the credential attached, and each one lands in an execution record you can review later. Cutting off a single agent takes one change in the control plane, with no key rotation across your other tools. Agents connect through the jentic CLI, a generated skill, an MCP server, or plain HTTP, so coding assistants and in-house agents share the same gate. The stack runs as two units over one database: the control plane on port 8000 for administration, and the broker data plane that agents call. Quickstart runs on SQLite for trials, and production setups move to Postgres with pinned images and TLS. 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
Kiwi Mem screenshot thumbnail

Kiwi Mem

Your AI stops forgetting you between sessions with Kiwi Mem, a self-hosted gateway that gives chat models a long-term memory modeled on the human brain. It sits between your chat client and your LLM provider, quietly extracting what matters from every conversation and injecting the right memories into the next one. Each memory carries a heat score: topics you raise often stay vivid, emotional moments decay slowly, and things nobody mentions cool down and blur instead of filling a database forever. At night, the Dream process cleans up stale fragments, merges related ones into coherent memory scenes, and surfaces conclusions nobody stated out loud. Calendar summaries compress history from day to week to month to year, so yesterday stays detailed and last season becomes an outline. When a new fact contradicts an old one, the outdated version retires automatically, and memories you lock by hand never fade at all. Any OpenAI-format client can connect, and Anthropic accounts link directly in native format with streaming and tool use intact. The browser admin panel manages providers, memories, projects with private layers, and more than 80 runtime settings. 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
Datakeel screenshot thumbnail

Datakeel

Datakeel is a workbench where teams proofread AI training data, trace every business number back to its definition, and approve risky changes before anything is deleted. Evidence review marks each claim as present, absent, or unknown, so missing annotations never pass as clean, and accepted decisions are stored apart from the extracted evidence. Ask data answers a question like last quarter's retail revenue from registered metrics, shows the bound SQL, source tables, and time range, and refuses or asks for clarification when a question is ambiguous. A data catalog maps sources, tables, fields, owners, lineage, and glossary terms, and an asset market handles access requests with purpose and expiry. A knowledge graph review queue turns document extractions into entities and relations that stay candidates until a person checks the source sentence. Dataset versions freeze file manifests with SHA-256 hashes, quality scores rank samples, and workflows run health checks, cleanups, and metric changes that pause at an approval sheet bound to a digest of the plan. Built-in agents and an MCP server can propose actions but never apply them alone, every receipt is kept in an append-only history, and the interface ships in English and Chinese with three themes. 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
NitroMTA screenshot thumbnail

NitroMTA

Your application already knows how to send mail through Amazon SES; NitroMTA lets it keep that code, change the endpoint and keys, and deliver from IP addresses you actually control. The engine answers a submission only after the message is committed to disk, so accepted mail survives a crash, a power cut, and even the loss of its host when the disk survives. Capture mode runs the whole engine locally and shows each message in a browser at port 9090 instead of sending it, which makes testing painless before any DNS exists. Out in production, new IPs warm up receiver by receiver from fifty messages a day, rising after clean days and backing off when complaints, bounces, or throttling climb. Each provider gets its own connection limits and cooldowns, hard bounces and spam complaints suppress the address automatically, and outgoing mail is DKIM-signed and sent over TLS with MTA-STS and DANE verified where published. Templates, identities, configuration sets, tenants, dedicated IPs, and SES-shaped events through an SNS subset cover the SES surface your tooling expects, and a CLI explains why any given message is still waiting. 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
AgentRun screenshot thumbnail

AgentRun

A control room for AI agents, where every run is recorded, capped, and ready to resume after a crash. Mission Control opens first with agent and run counts, tokens, success rate, and cost per day. A Templates page applies ready-made agents for code review, KYB due diligence, lead scoring, market monitoring, and release notes in a single screen. Every run gets a Report tab with the finished answer and a Timeline tab with each message, tool call, and charge. Tools are set to allow, ask, or deny. Spend caps pause a run instead of failing it. An agent can stop and ask a person a question. The Playground starts a run from a form and shows the same request as curl, so each agent doubles as an API. Triggers start capped runs on a schedule, from a signed webhook, or on a GitHub pull request. Learning mode keeps notes, skills, and workflows from each job so repeat work needs fewer tokens. Automated code review, customer research, and competitor digests are typical recurring jobs to hand 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.

Deploy
Campfire Rust screenshot thumbnail

Campfire Rust

Your team chat can be one executable on your own server: Campfire Rust runs rooms, direct messages, attachments, and search as a single binary that replaces the whole Ruby, Puma, Redis, Resque, and Thruster stack. Create rooms with access controls for projects, departments, or a private board discussion, and keep direct messages beside them for quick questions. File attachments arrive with previews, mentions pull the right person into a thread, and search finds the decision someone made months ago. Web Push notifications reach browsers and phones, so a quiet room still finds its people when it matters. Chatbots connect through a simple HTTP API for sending and receiving messages and attachments, which makes Campfire a home for build alerts, deploy notices, and support pings. Existing Campfire installs upgrade in place because the Rust binary reads the same SQLite database, storage layout, and signed cookies, with no data migration and no mass sign-out. Automatic TLS with Let's Encrypt certificates, HTTP/2, and Action Cable-compatible WebSockets are built in, and the whole system works on air-gapped networks that never touch the internet. Run it as your primary chat, as a backup for the day a hosted service goes down, or as a walled garden for executives and events. 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
Ticket Monitoring screenshot thumbnail

Ticket Monitoring

Name the route and the fare you will pay, and Ticket Monitoring keeps watch over five booking channels, alerting you the moment a real fare drops to your price. It collects actual flight details, not headline prices: flight numbers, times, transfers, cabins, aircraft, and baggage allowances from Qunar, Fliggy, Ctrip, Tongcheng, and Tuniu, with five optional app channels feeding the same tables. Every watched route carries its own rules: separate target lines for nonstop and connecting flights, airline whitelists, baggage and departure-time gates, a maximum trip duration, and pause switches that shelve a route without deleting it. Each scan writes every flight into a local price history, so the console draws candlestick trends, 14-day departure price bands, and low-fare calendars from your own collected data. When a fare crosses your line, a rich DingTalk post leads with the deal, its 7-day trend, and a buy-or-wait suggestion, and escalation layers add an @mention, an ntfy alert that rings through silent mode, or a voice call. ServerChan WeChat, Bark, and email reports with embedded charts run alongside, governed by quiet hours and a full send history. Routes, thresholds, scan intervals, channels, and notifications are all configured in the browser console, changes apply live without a restart, and all prices and credentials stay in local files on your 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.

Deploy
TavernAI screenshot thumbnail

TavernAI

Character-based chat and storywriting with large language models: TavernAI is the open-source frontend that leaves model choice to you. It generates no text itself; it connects to the backend of your choice - OpenAI (including GPT-4), Anthropic Claude, KoboldAI and KoboldCpp, Oobabooga's Text Generation Web UI, NovelAI, Ollama, and the crowdsourced Horde - so cost, model quality, and content policy are decided by your backend, not the interface. Characters are defined by portable card files in PNG or JSON format with personality, scenario, and example dialogue, and tens of thousands of community-made cards from sites like Chub.ai import directly. Conversations support group chats with multiple characters, a story mode for long-form writing, message swiping to branch between alternative responses, and full editing of any message. World Info injects lore into context when keywords trigger, keeping long roleplays consistent. Themes, custom backgrounds, and configurable generation settings round out the interface. It runs on Node.js, and the SillyTavern project began as a fork of it.

Deploy
MediKeep screenshot thumbnail

MediKeep

Your medical history, fragmented across a dozen patient portals, in one place on your server: MediKeep (formerly Personal Medical Records Keeper) is a self-hosted health record system. Built with a React frontend and FastAPI backend over PostgreSQL, it organizes 14 categories of medical data - medications with dosages and schedules, conditions, procedures, allergies, immunizations, symptoms, injuries, doctor visits and encounters, treatments, lab results, and even medical equipment with service dates and supplier info. Treatment management is genuinely sophisticated: an advanced mode links treatments to their medications with per-medication overrides for prescriber, pharmacy, and effective dates, and reverse lookup shows which treatments use a given medication. A dashboard summarizes records and recent activity, file uploads attach documents to records, and tagging works across categories. When a new specialist asks for your history, the report builder assembles custom reports by category and exports to PDF, JSON, or CSV - a curated, portable summary instead of a folder of photocopies. Authentication supports Google and GitHub SSO with OIDC providers like Keycloak and Authelia expected to work, and the built-in backup system protects the archive. Health data is exactly what should never live in someone else's cloud.

Deploy
Posta screenshot thumbnail

Posta

Built as a developer-first alternative to SendGrid, Mailgun, and Postmark, Posta delivers a complete self-hosted email infrastructure platform handling both outbound delivery and inbound reception through a single HTTP API with official SDKs for Go, PHP, and Java. The Go backend processes email through Redis and Asynq with automatic retries, priority queues, and async delivery while PostgreSQL stores templates, contacts, campaigns, and delivery analytics. Outbound features include versioned multi-language templates with variable substitution and stylesheet inlining, bulk campaigns with subscriber targeting and A/B testing per-variant metrics, scheduled timezone-aware delivery with draft/paused/cancelled lifecycle states, email address verification checking syntax, MX records, disposable domains, and role accounts, plus web view links with signed expiring URLs and one-click unsubscribe headers. The built-in SMTP receiver with TLS handles inbound email at your domains, parses messages and attachments, scores spam, and forwards structured payloads to your application via HMAC-verified webhooks with real-time SSE notification streams. The Vue-based dashboard manages templates, SMTP server pools, domains, contacts, API keys, campaigns, and email logs with dark and light mode support while admin-level platform metrics expose delivery rate trends, bounce rate graphs, and latency percentiles alongside Prometheus integration and daily health reports. Deploy via Docker with PostgreSQL and Redis. 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
Imp screenshot thumbnail

Imp

Imp runs large AI chat models privately on one NVIDIA RTX 50 or RTX PRO graphics card, exposing them through OpenAI and Anthropic compatible APIs plus a built-in browser chat. Start it with a single Docker command, point it at a model, and the chat opens in your browser with saved conversations and a live readout of generation speed. Coding agents such as Claude Code and Codex connect by changing one base URL, so your editor talks to the model on your own hardware instead of a rented cloud endpoint. Tool calls, structured JSON output, streaming responses, and reasoning models all work over the wire, and requests can be protected with an API key, per-IP rate limits, and concurrency caps. Load GGUF files you already have or NVFP4 and FP8 SafeTensors checkpoints straight from Hugging Face with no conversion step before the first answer. When a model is bigger than the card, mixture-of-experts weights stay in system RAM while the busiest experts are cached on the GPU, so a 123.6 GiB model still answers from a 32 GB card. Supported models can also read images alongside text, and tokenize, health, and model listing endpoints make the server easy to wire into scripts and monitors. 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
LiftTrace screenshot thumbnail

LiftTrace

LiftTrace is a self-hosted weightlifting tracker that keeps your entire training history, programs, personal records, and progress photos on your own server in a single Docker container. Log every set with weight, reps, RPE, warm-up markers, and supersets, or type a line like bench 3x5 at 225 and let the Smart Log parser turn plain text or a voice note into structured sets. Follow multi-week programs where each week prescribes its own sets, reps, tempo, rest, and load, and watch the diary prefill today's session from the active template. Browse an exercise library merged from wger, Free Exercise DB, and ExerciseDB, add custom movements, or bulk import your own catalog from a spreadsheet. Automatic PR detection, estimated one-rep maxes, volume and frequency charts, and dated progress photos with a drag-to-compare view show how training is trending. The built-in Trace AI coach reads your workouts, programs, records, and body stats to answer questions, log sessions, and adjust plans through Claude, OpenAI, Gemini, or a local Ollama model. Coaches can prescribe workouts, leave notes on individual sets, and review filmed set videos with comments stamped at the moment that matters, all with explicit consent from the athlete. Import years of history from Strong, Hevy, FitNotes, Jefit, or Garmin FIT files, keep logging offline in the gym, and sign in with OIDC through Authentik, Keycloak, or Authelia. 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
Supernote screenshot thumbnail

Supernote

Your Supernote tablet fills with handwritten journals, meeting notes, and sketches, and this server gives that handwriting a private home: Supernote is a self-hosted sync cloud for Ratta Supernote tablets that stores notebooks on your own hardware and can transcribe, summarize, and search them with AI. Point the tablet at your server under its Private Cloud sync setting and notebooks upload automatically, ready to browse in the web interface alongside your task lists and AI insights. Turn on the intelligence layer and each synced page is transcribed by a vision model, either Google Gemini or a local model served by Ollama or another OpenAI-compatible endpoint, so notes never leave your network. Analyzers then read your journals to surface tasks, themes, and Daily, Weekly, and Monthly summaries. Every word is indexed for semantic search, which understands concepts: searching for budget also finds pages about expenses or money, even when that exact word never appears. Tasks discovered in your handwriting export as calendar feeds that drop into Home Assistant, Apple Calendar, Google Calendar, and Outlook. An MCP server lets assistants such as Claude, Gemini, and ChatGPT answer questions against your notebooks, and notebooks convert to PDF, PNG, SVG, or plain text for use anywhere else. The hub idles at about 160 MB of memory, or roughly 135 MB in bare sync mode. 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
Attic screenshot thumbnail

Attic

Somewhere in your home sits a box nobody has opened since the move, and Attic is the self-hosted home inventory that turns its contents from a mystery into a searchable record. You catalog appliances, tools, electronics, books, games, and furniture as assets, each with photos, receipts, manuals, purchase date and price, condition, and warranty dates attached. Nested locations mirror the house itself, rooms containing cupboards containing boxes, with photo galleries so you recognize a storage space on sight. Categories carry their own custom fields, inherited by subcategories, so electronics can demand a serial number while books ask for an ISBN. Items stored inside other items, like tools in a toolbox, are tracked as asset contents and move with their container. Collections group a game library or a moving box across locations, while tags label anything that needs repair or is out on loan. Adding stock is fast: import plugins pull metadata and cover images from Google Books, TMDB, BoardGameGeek, IGDB, and Rebrickable for LEGO sets. Search combines full-text with nested match-all and match-any filters, and saved searches pin to the sidebar as shortcuts. A history timeline records repairs and maintenance per asset, and the dashboard totals purchase value across currencies while flagging expiring warranties. OIDC single sign-on, scoped API keys, a REST API, and an MCP server connect Attic to scripts and agents. 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
Codeman screenshot thumbnail

Codeman

Codeman is a self-hosted mission control for AI coding agents that runs Claude Code, Codex, OpenCode, Gemini, Copilot, and five more agent CLIs in persistent sessions you can watch and steer from any browser, phone included. Sessions live in tmux, so agents survive server restarts, network drops, and laptop sleep, with full scrollback replay when you return. Run up to twenty sessions as tabs or in a six-up tile grid, each streaming its real terminal with token and cost tracking, and tabs that blink when an agent goes idle or needs an answer. Idle detection re-prompts stalled agents, and when a subscription usage limit hits, Codeman parses the reset time, waits it out, and resumes the run unattended. Subagents appear as floating live windows tethered to their parent session, with real-time transcripts, token counts, and status badges. Agents can drive Codeman too, through a bundled skill, CLI verbs, and an MCP server that let one agent start, prompt, and collect answers from workers in other CLIs. Run a project in an isolated Docker container or on another machine over SSH, preview agent-created files in the browser, and reach everything from your phone with QR login and push notifications, or over Tailscale with a real certificate. 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
CPA Usage Keeper screenshot thumbnail

CPA Usage Keeper

Somewhere between the third coding agent and the fifth model subscription, nobody can say where the tokens went. CPA Usage Keeper keeps the receipts for a CLIProxyAPI gateway, saving every request locally with scheduled backups so history survives restarts. The Overview page shows requests, success rate, tokens, cache hit rate, and estimated cost with sparklines and a calendar heatmap, and Realtime plots time to first token against total latency and shows rolling cache levels and model speed. Analysis breaks usage down by API key, model, credential, or provider with donut charts and ranked lists. The Request Events log filters by model, source, and status, adjusts its columns, and exports records. Credentials cards show success rates, remaining five-hour and weekly quotas, priorities, and enable switches, and quota history charts how many tokens and dollars each percentage point costs over a cycle. Individual API keys can be given a read-only usage view. Deployment uses a Docker Compose file that bundles CPA with Keeper or runs Keeper beside an existing gateway, and the interface switches between English and Chinese and between light and dark themes. Check the dashboard before the invoice arrives and see exactly who spent what. 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
Synapse AI screenshot thumbnail

Synapse AI

Hand a repeating job to Synapse AI and it drafts readable steps, runs them the same way every time, and stops to ask before anything goes out. Each workflow is a graph of steps that can call agents, tools, scripts, and different language models from over a dozen providers, local or cloud. An AI builder drafts the graph from a description, and a visual editor handles hand adjustments. Human approval steps pause a run until someone says yes, in the web interface or from Slack, Discord, Telegram, Teams, or WhatsApp. Cron and interval schedules start jobs automatically, and a run viewer shows the path, timing, tokens, and cost of every step. Any REST endpoint, Python script, webhook, or MCP server becomes a tool agents can call, and a shared vault stores files between runs. A template gallery offers ready-made workflows for research, reporting, and content, and an embeddable chat widget puts a knowledge-grounded assistant on your own site. A versioned REST API enqueues, streams, and cancels runs from your products. 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