With over 48,000 GitHub stars and monthly releases since March 2023, LocalAI is the self-hosted AI engine that replaces every OpenAI endpoint with a single Docker container running on your own infrastructure — serving chat completions, image generation, text-to-speech, speech-to-text, embeddings, vision, video generation, and function calling through identical API schemas that require zero application code changes. The composable backend architecture isolates each inference engine as a separate gRPC service running in its own OCI container, so llama.cpp, vLLM, SGLang, transformers, whisper.cpp, diffusers, MLX, Stable Diffusion, and Flux install on demand without touching the core, can run on separate machines, and a fault in one never affects others. Hardware acceleration spans NVIDIA CUDA 12 and 13, AMD ROCm, Intel oneAPI/SYCL, Apple Silicon Metal, Vulkan, and NVIDIA Jetson L4T — or runs entirely on CPU without any GPU. Built-in AI agents support autonomous tool use, retrieval-augmented generation, Model Context Protocol integration, and skill-based workflows directly in the web interface. The model gallery provides curated YAML configuration files for hundreds of models that install with a single command, while P2P federated inference distributes model shards across multiple machines for running models larger than any single node's memory. Multi-user API key authentication with quotas and role-based access enables team deployments. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Codync turns the coding agents already installed on your computer into named bots you can message from your phone, so the Claude Code or Codex session on your desk keeps working while you are away. Each bot wraps one agent in one project folder, with its own standing instructions, memory, and approval rules, and several bots run side by side on one machine. Message any bot from the iPhone app, the desktop app, or a terminal; group rooms put bots in one thread, and an @name mention routes a question to exactly one of them. Bots ask each other for reviews inside the room and quote-reply to specific messages. File changes arrive as approval cards naming the file and computer, with Allow once, Always allow, or Deny; finished and blocked work both ping you as push notifications. The connection between phone and computer is end-to-end encrypted through a free relay, your own relay, or directly over the same Wi-Fi or Tailscale. Watch the computer's screen from your phone, hand a bot a computer-use tool, or talk to it in a voice call, and approve every new device per computer with a six-digit code. Your existing agent subscription does the work; Codync never calls a provider API with your login, and there is no paid tier. 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.

With 24,000 GitHub stars and infrastructure processing over 100 million clicks and 2 million links monthly for marketing teams at Twilio, Buffer, Framer, Perplexity, and Vercel, Dub is the most widely adopted open-source link attribution platform — unifying branded short links, real-time conversion analytics, and affiliate programs in a single self-hostable tool. Create short links on custom domains with built-in QR code generation, device and geographic targeting rules, A/B testing for destination URLs, deferred deep linking for mobile apps, and custom social media preview cards. The attribution engine tracks the complete customer journey from first click through lead capture to final sale, calculating lifetime value, retention rates, and multi-touch attribution across campaigns. Real-time analytics visualize clicks, leads, and revenue with filtering by geography, device, browser, referrer, operating system, and UTM parameters — plus an "Ask AI" feature that generates personalized reports from natural language queries. The partner program module enables embedded referral and affiliate programs with custom reward structures, automated payouts, and partner dashboards for product-led growth. Programmatic link creation via native SDKs for TypeScript, Python, Go, PHP, and Ruby supports enterprise-scale campaigns with real-time webhook notifications on link events. Migration assistants import existing links from Bitly, Rebrandly, and Short.io with redirects preserved. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPLv3 licensed.

Sim Studio lets teams build, deploy, and monitor AI agent workflows by dragging blocks onto a visual canvas and wiring them into executable pipelines, backed by over 1,000 integrations. The React Flow editor represents each step as a node: LLM calls, tool invocations, conditional branches, and data transformations form directed acyclic graphs that run as complete agent pipelines. Every major LLM provider works natively, including OpenAI, Anthropic, Google Gemini, Groq, and Cerebras, plus local models through Ollama and vLLM. Integrations span Gmail, Slack, Microsoft Teams, Telegram, WhatsApp, Notion, Google Workspace, Airtable, GitHub, Jira, Linear, Perplexity, Firecrawl, PostgreSQL, Supabase, Pinecone, and Qdrant. Built-in tables provide a database layer, a file store offers shared team storage, and knowledge bases powered by PostgreSQL with pgvector enable retrieval-augmented generation. Finished workflows deploy as REST API endpoints, scheduled jobs, or Slack bots, with block-by-block execution traces for full observability. Real-time collaborative editing via Socket.io supports simultaneous multi-user construction. Alternatively, describe agent behavior in natural language and Sim assembles the workflow automatically. Built on Next.js App Router, Bun runtime, Drizzle ORM, and Tailwind CSS. 29,400+ GitHub stars and 100,000+ builders. Apache-2.0 licensed.

Agent Zero equips large language models with a persistent virtual Linux desktop, letting autonomous AI agents write code, research the web, and execute multistep tasks without supervision. Operating within an isolated container, the system opens an interactive XFCE graphical desktop in your browser canvas where the agent interacts with GUI applications like Blender and terminal sessions directly. Its embedded browser features interactive annotation tools, letting you click web elements to inspect stylesheet hierarchies, extract component markup, or submit automated testing instructions. You can cowork on spreadsheets, presentations, and Markdown specifications in real time alongside the agent, preserving document revisions through snapshot time travel. A multi-tier memory architecture backed by FAISS vector indexing and SearXNG web discovery retains problem-solving context across projects, while hierarchical delegation spins up specialized subordinate agents to parallelize complex engineering audits. The platform connects seamlessly to commercial LLMs via OpenAI, Anthropic, or OpenRouter, runs private local models through Ollama, and integrates custom toolkits via the Model Context Protocol and community Plugin Hub. 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 notify() call is all your product needs to reach users on push, email, SMS, chat, and webhooks, with NotifKit deciding how and when each message travels. List the channels in the order you prefer and NotifKit tries each in turn, so a failed push quietly becomes an SMS or an email instead of a lost message. Per-user preferences, consent, and quiet hours in each user's own timezone hold non-urgent sends until morning, while critical messages such as one-time passwords travel their own lane immediately. Templates, multi-step workflows that wait days or block on events, scheduling, throttling, and deduplication all run behind that single call, defined in TypeScript and kept in your repository. Delivery logs record every attempt, and the admin dashboard shows a live activity feed, queue depth per priority lane, workflow runs step by step, and a replayable dead-letter queue. Several products can share one deployment as separate projects with their own API keys, rate limits, and data, and any service can call the REST API without the TypeScript SDK. Ask an AI assistant why a password reset never arrived by connecting the built-in MCP server to Claude Code, Cursor, or another MCP client. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

The ad-riddled "free online tools" sites people paste sensitive text into and upload confidential PDFs to - OmniTools replaces that whole ecosystem with one self-hosted app. It bundles 50+ utilities behind one clean React/TypeScript interface: image tools (resize, convert, crop, edit), video and audio tools (trim, reverse, convert), PDF tools (split, merge, edit), text and list utilities (case converters, formatters, shufflers), plus date/time, math, and data-format helpers for JSON, CSV, and XML. The architectural decision that makes it trustworthy is that all file processing happens entirely client-side in the browser - the server only serves static assets, and nothing you process ever leaves your device. That design has a pleasant side effect: the host needs almost no resources (people run it on a Raspberry Pi Zero), because your browser does the work while the server just delivers files. The Docker image is a remarkable 28 MB, making it one of the fastest apps to deploy and cheapest to keep running. There are no ads, no tracking, no accounts, and no upload limits. With multi-language support and an MIT license, it works equally well as a personal toolbox or a team-wide internal utility portal - one URL that replaces a bookmark folder full of questionable converters. Actively developed with 50 contributors and 9,500+ GitHub stars.

Over 2,500 open-source projects and companies in more than 165 countries localize with Weblate - the libre continuous localization platform and the standard self-hosted answer to Crowdin and Lokalise. Its defining trait is that translations live in the same version control as your code: Weblate talks directly to Git and Mercurial, pulls new source strings automatically via webhooks, and pushes finished translations back either as direct commits or as pull/merge requests on GitHub, GitLab, Gitea, Bitbucket, Azure DevOps, Gerrit, or Pagure. Every translator is properly credited in the commit history. For translators, it is a full computer-aided translation tool: translation memory, glossaries, customizable quality checks that catch placeholder and formatting mistakes, propagation of identical strings across components, and automatic suggestions from machine translation services - DeepL, Amazon Translate, LibreTranslate, and others, with per-service priorities and support for custom Python engines. It handles the format zoo (gettext PO, JSON, YAML, Android XML, iOS strings, and dozens more) and supports crowdsourced workflows with granular access control, workspaces, two-factor authentication, and reviewer approval steps. A REST API, CLI client, and add-on system automate everything else. Built on Python/Django, GPL-licensed, with no per-string or per-seat pricing when self-hosted.

With 7,300+ GitHub stars and active releases through version 3.17, Woodpecker CI is the community-driven fork of Drone CI that kept the entire platform open source under Apache 2.0 — delivering a lightweight, container-native CI/CD engine that runs on minimal resources while providing enterprise-grade pipeline automation. Every pipeline step executes in an isolated Docker container, ensuring reproducible builds with zero host contamination and clean teardown after each run. Define workflows in simple YAML configuration files with step dependencies, conditional execution via when filters, service containers for databases and caches, and matrix builds that test across multiple language versions, platforms, or database engines simultaneously. Deep forge integration connects to GitHub, GitLab, Gitea, Forgejo, and Bitbucket via OAuth and webhooks, triggering pipelines on push, pull request, tag, deployment, and cron events. The plugin ecosystem inherits compatibility with the Drone plugin library — over 100 plugins for Docker builds, S3 uploads, SSH deployment, Slack and Telegram notifications, Helm deployments, and more. The server-agent architecture separates the web UI, API, and scheduler from pipeline execution, enabling horizontal scaling by adding agents across multiple machines or architectures including ARM. Secrets management supports global, organization, and repository-level scopes with approval workflows for forked repository pipelines. The admin web UI provides user management, agent monitoring, and queue control. Docker Compose deployment provisions the complete stack in under five minutes. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

Machine translation with no Google, no Azure, no per-character billing, and no text leaving your infrastructure: LibreTranslate is a free, open-source translation API that runs entirely on your own server. The engine underneath is Argos Translate, which runs OpenNMT neural models with SentencePiece tokenization and Stanza sentence-boundary detection, all offline. Models install as portable .argosmodel packages covering dozens of languages - English, Spanish, French, German, Chinese, Japanese, Russian, Arabic, Hindi, Portuguese, and many more - and Argos handles automatic pivoting: with es-to-en and en-to-fr installed, it chains them to translate es-to-fr without a direct model. The API is a straightforward HTTP POST to /translate with source and target language codes, returning JSON - simple enough that the ecosystem has clients in every major language and integrations across tools like Weblate and Mastodon. Beyond plain text it translates HTML while preserving markup and handles whole file uploads (documents in, translated documents out), plus automatic language detection when the source is unknown. A clean bundled web UI serves interactive translation for end users, and optional API keys with rate limits control access. AGPL-licensed and trainable with custom models, it is the standard answer when translation must be private, unmetered, and self-contained - GDPR-sensitive text never touches a third party.

A polished public status page without Statuspage prices or a heavyweight observability suite: Kener is a status and uptime monitoring system built with SvelteKit and Node.js. It runs 11 monitor types - API, Ping, TCP, DNS, SSL certificate, SQL query, Heartbeat, gRPC, and GameDig game-server checks among them - each with configurable intervals and thresholds. Incident management covers the full lifecycle: structured timelines from investigation through resolution, acknowledgements, and subscriber-visible updates, plus maintenance windows with RRULE-based recurring schedules and automatic status transitions. Notifications reach email, Slack, Discord, and custom webhooks through trigger-based workflows with template-driven messaging. One instance can serve multiple branded status pages - per product, team, or region - with custom logos, colors, and CSS, localization into 21 languages, timezone-aware displays, and server-rendered pages that stay fast and SEO-friendly. Operations tooling includes role-based access for teams, API key management, a secrets vault, analytics integrations (Google Analytics, Plausible, Umami, and others), and a REST API with 17+ endpoints for automating incidents and monitors from CI/CD. MIT-licensed; Docker deployment with Redis, SQLite by default, PostgreSQL or MySQL for production.

Team and product documentation on a fast Vue frontend with PostgreSQL storage: Wiki.js is a Node.js wiki engine. Its distinguishing trait is per-page editor choice: authors pick Markdown with live preview, a WYSIWYG visual builder for non-technical writers, or raw HTML, page by page. Native Git synchronization commits every page change to GitHub, GitLab, Bitbucket, Azure DevOps, or any Git remote - bi-directionally, so edits made in the repository flow back into the wiki - giving documentation version-controlled backup for free. Authentication coverage is among the broadest of any self-hosted wiki: local accounts with self-registration, social login via Google, GitHub, Discord, and Slack, and enterprise SSO through LDAP/Active Directory, SAML, CAS, Auth0, Okta, Azure AD, Keycloak, and generic OAuth2/OIDC, with optional MFA. Built-in full-text search runs on PostgreSQL with zero setup, and external engines like Algolia or Solr can substitute. Page history with visual version comparison, granular group-based permissions per path, nested navigation menus, 50+ integration modules, and full localization round it out. AGPLv3-licensed with a 28k-star community.

Plunk consolidates transactional emails, marketing campaigns, and drip automation into one platform riding AWS SES at roughly one-tenth of a cent per message, with zero per-contact charges regardless of list size. The Turborepo monorepo architecture separates the Express.js API server (handling REST requests with Prisma ORM against PostgreSQL) from a dedicated BullMQ worker process that consumes email, campaign, and workflow jobs independently for fault isolation and horizontal scaling. Transactional emails support HTML bodies, template variable substitution via React Email components, attachments, and custom headers with dedicated SMTP relay on ports 465 and 587 for integration with existing frameworks. The campaign system sends newsletters and product updates to full contact lists or dynamically segmented audiences based on contact properties and behavioral events, with scheduling, A/B testing, and performance tracking for opens, clicks, and bounces. The workflow automation builder creates event-triggered sequences with delays, conditional branches, and webhook steps for lifecycle campaigns like onboarding drip sequences and re-engagement flows. Contact management stores unlimited contacts with custom data fields, CSV import, full activity history, and dynamic segmentation. Custom domain verification with DKIM and SPF ensures deliverability, while inbound email processing handles incoming messages with custom routing rules. Docker Compose deployment runs five containers including PostgreSQL, Redis, MinIO for S3-compatible storage, and ntfy for notifications. 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.

Backed by 4,800+ GitHub stars and trusted by teams replacing LaunchDarkly and Split with a self-hosted solution, Flipt v2 delivers the first truly Git-native feature management platform that treats feature flags as code stored in your own repositories. The architecture eliminates all database dependencies by building immutable in-memory snapshots from YAML flag definitions on every Git commit, delivering sub-millisecond evaluation latency with zero external runtime dependencies beyond the single Go binary. Multi-environment support maps directly to Git abstractions — separate repositories per environment, different directories within the same repository, or different branches — enabling teams to use their existing branching strategy, pull request workflows, and code review processes for flag changes. The evaluation engine supports boolean flags, multivariate string and numeric variants, segment-based targeting with constraint rules, percentage rollouts, and namespace isolation. Native SCM integration with GitHub, GitLab, BitBucket, Azure DevOps, and Gitea creates merge proposals directly from the UI with GPG-signed commits. Flipt implements the OpenFeature Remote Evaluation Protocol with official providers for Go, Node.js, Python, Java, C#, Ruby, and Web SDKs, enabling vendor-agnostic flag evaluation across all services. The gRPC API with REST HTTP gateway exposes flag management, evaluation, and analytics endpoints. Offline mode continues serving flags when the source repository is temporarily unavailable. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Fair Core License (server) / MIT (client SDKs).

Instead of installing a different client for every database engine on your servers, Tabularis gives you one SQL workspace in the browser that speaks to PostgreSQL, MySQL, MariaDB, and SQLite directly, and to 26 more engines through installable driver plugins. The SQL editor autocompletes real table and column names as you type, runs multi-statement batches into separate result tabs, and can draw any result set as a bar or line chart. Notebooks mix executable SQL cells with Markdown and charts, sharing variables across cells for repeatable reports and investigations. You can edit rows inline in a virtualized grid that tracks pending changes before committing, build queries by dragging tables onto a canvas that writes the SQL for you, and generate an ER diagram from the live schema to see how everything connects. Natural-language prompts turn into SQL through OpenAI, Anthropic, Ollama, or any compatible endpoint you configure. Results export to CSV, JSON, or Markdown, whole databases dump to SQL files, and scheduled daily backups keep copies without manual effort. Connections reach databases through SSH or Kubernetes tunnels, and the built-in MCP server lets agents like Claude and Cursor inspect schemas and run queries under your 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.

Modern engineering teams and busy households deploy Octop to run private, autonomous AI agents equipped with persistent memory workspaces, scheduled cron jobs, and direct browser automation. Users can orchestrate specialist agents tailored for software development, IT operations, content generation, and system diagnostics through an interactive React dashboard. The platform connects directly to Discord, Feishu, DingTalk, and WeCom, allowing team members to delegate complex tasks without leaving their everyday messaging apps. An integrated remote desktop and browser control engine lets agents navigate websites, capture screenshots, fill forms, and operate graphical software autonomously. Administrators can assign distinct MBTI personality profiles to agents, establish granular role-based permissions, configure scheduled cron workflows, and integrate custom Model Context Protocol servers for external tool access. Long-term memory persists across conversations through dedicated workspace files, ensuring contextual continuity whenever switching between underlying language models or team collaborators. 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 coding agents finish a session, close the laptop, and forget everything; Pad is where the project remembers. It holds the tasks, plans, bugs, ideas, and decisions in one workspace that you drive from a browser while your agents drive it from the terminal, so the next session, human or machine, picks up exactly where the last one stopped. You plan on boards, lists, and tables with drag-and-drop status columns, rich item pages, comment threads, and a dashboard that answers what needs attention and what to do next. Your agents read the queue, claim items, leave checkpoints, link their pull requests, and mark work fixed with the fixing PR attached. Conventions teach them the house rules once, like running tests before calling a task done, and playbooks hand them repeatable multi-step workflows they can invoke by name. Every change is versioned with its author, a person or a named agent, and new items appear in the browser the moment an agent creates them in the terminal. The same workspace is reachable three ways: the web interface, the pad CLI, and a bundled MCP server with a natural-language skill that plugs into Claude Code, Cursor, Codex, Windsurf, OpenCode, Copilot, Amazon Q, and Junie. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

With over 2,200 GitHub stars and a philosophy that your notes should be files you own rather than rows in a database, ZenNotes is the keyboard-first Markdown editor that runs as a self-hosted web app backed by a Go server accessible from any browser on your network. Every note is a plain .md file in a vault directory you mount, with zero proprietary lock-in. Modal editing with real Vim motions, leader-key flows, and a command palette keeps your hands on the keyboard through edit, split, and preview modes. The rendering engine handles KaTeX math, Mermaid diagrams, TikZ graphics, and JSXGraph plots directly from Markdown syntax alongside wiki links and callout blocks. A first-party MCP server ships in the box with one-click integration for Claude Desktop and Cursor, letting AI assistants read and write the same Markdown files on disk without sync layers or duplicate copies. The bundled zen CLI provides note creation, search, tagging, task toggling, and piped capture with JSON output for shell scripting. Board views render plain CSV files as Kanban columns. Daily notes, quick capture, archive, and trash round out the vault workflow. The Go backend serves the browser frontend on port 7878 with token-based authentication, configurable browse roots, TLS proxy support, and file permission hardening at 0600/0700 defaults. Deploy via the multi-arch Docker image for linux/amd64 and linux/arm64. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.