The first AI-enabled open-source Human Capital Management system built for the agentic era — not a legacy HRMS with AI features bolted on, but a platform architected from the ground up with native MCP, A2A, and WebMCP protocols enabling any LLM client to query employee records, create calendar entries, and orchestrate multi-step HR workflows. Built on the battle-tested SuiteCRM/SugarCRM CE foundation and extended with 17 dedicated HR modules — recruitment pipeline with candidate scoring, onboarding checklists, competency matrices, employment history tracking, leave management with accrual policies, time and attendance, resource booking, travel and expense reporting, workplace management, performance evaluations, job description builder, employer branding campaigns, offboarding workflows, and a configurable analytics engine — all controlled through granular role-based permissions. The integrated LangGraph-powered AI agent operates with human-in-the-loop confirmation before mutating data, while the MCP server layer exposes structured HR operations to Claude Desktop, GitHub Copilot, and any MCP-compatible client. Native REST API enables integration with SAP, Workday, and custom applications. Mobile apps for iOS and Android provide field access to employee data and approvals. Runs on Apache2 with PHP 8.2, MySQL 8.0 or MariaDB, and ElasticSearch 7.10+ for full-text search and list indexing. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL v3 licensed.

Marketing campaigns and transactional mail from one open-source platform: Notifuse is a modern, self-hosted alternative to Mailchimp, Brevo, and Klaviyo without per-email or per-contact pricing. Built with Go and React on PostgreSQL, it separates concerns cleanly: a drag-and-drop visual builder composes responsive templates from MJML components with Liquid variables like {{ contact.first_name }} and per-template version history; campaigns add A/B testing across subject lines, content, and send times; and a REST transactional API serves application-triggered mail. Delivery routes through your choice of provider - Amazon SES, Mailgun, Postmark, SendGrid, SparkPost, Mailjet, or plain SMTP - with multi-provider failover. Contacts carry custom fields and a full activity timeline (messages, profile changes, webhook events), and real-time segmentation builds dynamic rules over properties, activity, and subscriptions. Event-driven automations create behavioral sequences, a notification center gives recipients self-service preference management, and an S3-compatible file manager handles images with CDN delivery. Multi-tenant workspaces with isolated databases and custom domains suit agencies. Open and click tracking report engagement in real time.

What Nitter was to Twitter and Invidious is to YouTube, Lingva Translate is to Google Translate: a privacy front-end delivering the service's full capability while cutting Google out of the loop between you and your text. Built on Next.js with TypeScript and Chakra UI, it uses the purpose-built Lingva Scraper to fetch translations from Google Translate without your browser ever touching a Google-related service - no cookies, no tracking, no account, while retaining what makes Google Translate hard to give up: 100+ languages with the translation quality of Google's production models, unlike offline engines that trade privacy for accuracy. The clean interface covers automatic source-language detection, text-to-speech audio playback for pronunciations, definitions and examples, and light/dark themes. For developers, every instance doubles as a translation API: a RESTful endpoint at /api/v1/:source/:target/:query returns JSON translations, an audio endpoint serves TTS buffers, and a full GraphQL API at /api/graphql exposes translations, audio, and language lists for richer integrations - all unmetered on your own instance. Deployment is a single stateless container with one environment variable for the site domain; defaults for theme and language pair are configurable. GPL-licensed, and popular as the translation backend for privacy-respecting apps.

Vigil monitors your entire distributed infrastructure and generates a public status page from a single Rust binary small enough to run on a Raspberry Pi, consuming minimal CPU and memory while providing crash-free reliability. Four distinct monitoring modes cover every topology: poll probes check HTTP, TCP, SSH, and ICMP endpoints for reachability with configurable intervals and thresholds; push probes receive health reports from Vigil Reporter libraries embedded in your application code across Node.js, Python, Golang, Rust, TypeScript, Dart, and C#; local probes delegate monitoring to Vigil Local slave daemons running behind firewalls on separate LANs; and script probes execute custom shell commands for specialized health checks. Each monitored service transitions through healthy, sick, and dead states based on consecutive probe failures, with configurable thresholds controlling state transition sensitivity. When services change state, Vigil dispatches notifications through twelve alert channels including Slack, Email, Twilio SMS, Telegram, Pushover, Gotify, XMPP, Matrix, Zulip, Cisco Webex, and generic webhooks. The generated status page displays service groups organized by category with real-time replica status, system load metrics from reporter probes, and a maintenance announcement system for communicating planned downtime through the Manager HTTP API. Configuration uses a single TOML file defining all probes, services, and notification channels with no database dependency. Docker deployment pulls the official image with volume-mounted configuration. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MPL-2.0 licensed.

Alexandrie provides a structured knowledge base with an extended Markdown editor, granular per-document permissions, and offline editing through its progressive web app. The CodeMirror 6 editor goes well beyond standard Markdown with colored containers, academic callout blocks, KaTeX math expressions, syntax-highlighted code blocks, footnotes, interactive checkboxes, cards, panels, and a custom snippet system with import and export. Full-text search via the Ctrl+K command center returns instant results with content snippets and relevance ranking across all workspaces. Five permission levels covering None, Read, Write, Admin, and Owner apply per document and per user, while OIDC single sign-on integrates with Google, GitHub, Microsoft, Discord, and any OpenID Connect provider. Documents organize into a hierarchical tree of workspaces, categories, and nested entries with tags, bookmarks, pinned notes, and custom icons. Integrated Kanban boards handle task management within each workspace without switching applications. The PWA installs on any device for full offline editing with seamless sync when connectivity returns. Voice-to-text dictation captures notes hands-free, and one-click ZIP backup exports all documents, files, and settings as a portable archive. Over 2,000 GitHub stars and 41 releases back the project. The Docker Compose stack orchestrates the Nuxt 4 frontend, Go Gin backend, MySQL 8 database, and S3-compatible RustFS object storage. Running on a VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

When Clarkson, the once-popular fuel logger, stopped receiving updates, Hammond stepped in as its logical successor - a self-hosted vehicle expense tracker. Written in Go with a Vue.js interface and SQLite storage - a single lightweight container, no external database - it tracks every cost your vehicles generate: fuel fill-ups with cost, volume, and odometer readings; maintenance and repairs; and arbitrary other expenses, each attachable with photos and documents stored against the vehicle. The multi-user, multi-vehicle design is what sets it apart from phone apps: a household or small business adds all its vehicles and all its drivers, shares vehicles across users, and every fill-up lands in one ledger no matter who was driving. The Quick Entries feature respects how expenses actually happen - snap a photo of the receipt or pump screen at the gas station, then complete the structured entry later when you have a minute. Reporting works at both the vehicle level (cost per distance, fuel economy trends) and across the whole fleet. Migration matters here: importers for Clarkson, Fuelly, and Drivvo bring years of fill-up history along, so switching does not mean starting your data over.

Grimoire captures, extracts, and indexes the content behind your bookmarks so you can search what pages actually say, not just their titles and URLs. The ingestion pipeline accepts links from the web UI, REST API, MCP server, browser bookmarklet, or bulk import, then fetches each page and extracts readable content using specialized parsers for GitHub repos, GitHub issues, StackOverflow threads, YouTube transcripts, PDFs, and standard web articles. Everything stores locally in SQLite with file-based content archives. Search operates in three modes: FTS5 keyword matching for exact terms, semantic embedding search for meaning-based retrieval using vector similarity, or a hybrid ranking mode combining both. Optional AI providers including OpenAI, Ollama, Anthropic, DeepSeek, and any OpenAI-compatible endpoint generate automatic tags, summaries, and embeddings without being required for core functionality. The interface built with React 18, Vite, TypeScript, Tailwind CSS, and Radix UI supports categories, nested tags, notes, archive and trash states, read-later flags, and multi-user isolated spaces. A single Bun-powered Hono process serves both the compiled frontend and the REST API on port 3210, requiring only one Docker container and a SQLite volume. Backup and restore export bookmarks, content, settings, and metadata as portable ZIP archives. Nearly 3,000 GitHub stars reflect growing adoption among developers and researchers. Running on a VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

With over 3,600 GitHub stars and a philosophy of deliberate simplicity, OliveTin eliminates the need for SSH sessions, admin panels, and complex automation platforms by letting you define shell commands in a YAML config file and access them as clickable buttons through a clean browser interface. The Go binary consumes only a few megabytes of RAM, running on everything from tiny ARM and RISC-V devices through Linux VMs, containers, macOS, and Windows. Each button executes a predefined shell command with optional typed arguments that render as dropdowns, text fields, and validated inputs, preventing free-form command entry while giving users controlled access to server operations. Access control lists define exactly who can view or run each action — guests, family members, or junior administrators see only the buttons they are permitted to use. Entity templates generate actions dynamically from lists of hosts, containers, or other resources, creating one template that produces many buttons without manual duplication. Flexible triggers extend beyond browser clicks: cron schedules, webhooks, calendar file events, and filesystem watchers run actions automatically when conditions are met. Authentication supports OAuth2, JWT, and header-based methods for integration with reverse proxies and identity providers. Dashboards organize actions into folders and fieldsets for clear navigation across dozens of commands. No plugin system, no extension marketplace, no premium tiers — every feature ships in the single open-source release. 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.

Getting non-technical friends and family onto a media server is its most tedious chore - Wizarr solves it. Instead of manually creating accounts, dictating server addresses, and explaining which app to install, you send one invite link. When the recipient clicks it, Wizarr creates their account on your server automatically - Plex, Jellyfin, Emby, Audiobookshelf, Komga, Kavita, and Romm are all supported - then walks them through a mobile-first, app-like onboarding wizard: download the right client, sign in, and learn how to request movies through your Overseerr or Ombi instance, with an optional Discord server invite along the way. Invitations are genuinely manageable: set expiration dates, usage limits, passphrases, library-scoped access tiers, and time-limited memberships that end access automatically. The wizard itself is fully customizable - Markdown-based steps managed from the admin UI, organized into pre-invite and post-invite phases (terms of service before joining, app setup after), reorderable bundles assignable to specific invitation types, and combined flows for invites spanning multiple servers. Multi-server and multi-admin support manages several backends from one dashboard, SSO support is plug-and-play, and a REST API with OpenAPI/Swagger documentation covers automation. A Flask/HTMX app in a single Docker container.

Revolt gives communities the full Discord experience without ads, behavioral tracking, or subscription fees: servers with text and voice channels, direct messages, group conversations, roles, bots, and custom emoji at zero cost per user. The Rust microservices backend splits responsibilities across Delta for REST API and authentication, Bonfire for persistent WebSocket real-time event delivery, Autumn for file upload routing to MinIO S3-compatible object storage, and January for link preview proxy and embed generation. Voice chat operates through LiveKit with WebRTC audio streaming supporting multiple concurrent participants per channel. Server administrators configure hierarchical role-based permissions at the server, channel, and per-role level, controlling who can send messages, manage channels, kick members, and access moderation tools. Text channels support Markdown formatting, custom emoji, file attachments up to 20 MB, GIF search via Tenor integration, and message reactions. The bot API enables automated moderation, entertainment, and custom workflow integration with community-maintained libraries available in JavaScript, Python, and Rust. The TypeScript and Solid.js web frontend provides a responsive interface with theme customization. Docker Compose deployment spins up the complete stack including MongoDB for message and user storage, Redis for caching, and MinIO for attachments, providing complete data sovereignty over all conversations and files. 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.

Where Miniflux strips reading down, FreshRSS gives you knobs - the feature-rich pole of self-hosted RSS, comfortable with thousands of feeds. It's a multi-user PHP aggregator (host family and friends on one instance, with an anonymous reading mode) with the reading workflow refined over a decade: favorites, custom tags, powerful filter and search queries, three reading views, and statistics that reveal each site's publishing frequency - useful for pruning subscriptions. Two properties make it the standard choice. First, the Google Reader-compatible API (plus a Fever API) syncs with virtually every serious RSS client - Reeder, NetNewsWire, ReadYou, FeedMe, Fluent Reader - so your phone reads from your server. Second, native WebSub support means compatible sources (WordPress, Blogger, Medium, Friendica) push new articles instantly instead of waiting for polling. A 50+ extension ecosystem adds what truncated feeds omit - full-text content fetching, reading-time estimates, trending views, auto-unsubscribe for dead feeds - alongside community themes and custom CSS. OPML import/export keeps subscriptions portable, a CLI handles administration, and article sharing posts to many services. AGPL-licensed, running on SQLite, MySQL, or PostgreSQL. Feedly Pro's feature set, minus Feedly's subscription and its algorithms.

PilotDeck introduces a WorkSpace-first architecture where each project receives its own isolated file system, memory store, and skill set, preventing context bleed between parallel tasks. White-box memory makes generation, extraction, storage, and retrieval fully visible, letting users audit, edit, pin, and rollback individual entries when the agent misremembers, while Dream Mode consolidates memory fragments during idle windows. Smart Routing auto-detects task difficulty and sends complex calls to flagship models like Claude Sonnet or GPT-4o while routing simple requests to lighter models, achieving claimed 70% cost savings through on-device and cloud co-orchestration with TokenSaver tiering and sticky session binding. Always-on background execution keeps agents running after the user closes the browser, with Discovery and Cron-based scheduling for recurring workflows. The platform natively supports the Model Context Protocol for first-class MCP server integration, community skills via ClawHub on npm, lifecycle hooks intercepting PreToolUse and UserPromptSubmit events, and custom memory store providers. Multi-provider fallback automatically switches to backup providers on timeout or rate-limit errors. The WebSocket and HTTP gateway serves web, CLI, desktop, and Feishu IM channels from a single configuration. 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.

With nearly 3,000 GitHub stars and 14 releases since its June 2025 launch, Kite delivers a lightweight Kubernetes dashboard that replaces the fragmented workflow of switching between kubectl, Lens, and separate monitoring tools with a unified multi-cluster management platform. The dashboard automatically discovers clusters from kubeconfig files and supports independent Prometheus configurations per cluster, providing real-time CPU, memory, and network charts alongside live pod log streaming with filtering and search. A built-in web terminal opens shells directly into pods and nodes without kubectl port-forward, while the Monaco-based YAML editor offers syntax highlighting and validation for in-place resource editing. The integrated AI agent, powered by OpenAI or Anthropic models via native Go SDK integrations, translates natural language into precise client-go API calls — querying cluster health, analyzing pod logs, scaling deployments, patching resources, and cleaning up failed jobs — all operating strictly within the logged-in user's RBAC permissions. Enterprise governance includes OAuth 2.0 single sign-on, multi-factor authentication, FIDO2 passkeys, granular role-based access control with per-namespace permissions, and comprehensive audit logging. Helm chart management enables browsing, installing, and upgrading releases directly from the UI, while the Docker registry integration provides quick image tag selection. Deploy via a single Docker container with SQLite or use the official OCI Helm chart with PostgreSQL or MySQL for production. 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.

The functions, config files, and one-liners you keep re-deriving finally get a searchable home: ByteStash is a self-hosted code snippet manager - a private Gist. Each snippet holds multiple code fragments, so a Docker Compose file, its .env template, and a plaintext usage note live together under one titled, categorized entry. Monaco-based syntax highlighting covers dozens of languages, from Python, TypeScript, Go, and Rust to YAML, Dockerfiles, Terraform, and Markdown. Retrieval is the point: filter by language or category, search titles and descriptions, and optionally include snippet contents in full-text search. Snippets can be pinned for quick access and shared via public links that recipients open without an account. Multi-user support runs on JWT authentication with optional OIDC single sign-on for teams on centralized identity, and a full CRUD REST API with Swagger documentation wires snippet retrieval into editors, scripts, and CI pipelines. Storage is a single SQLite database with optional encryption, and collections export as JSON or Markdown. A React frontend on a Node.js backend, deployed as one lightweight container.

Unkey is the open-source platform that unifies API key management, rate limiting, deployment, and observability into a single control plane. The Go API service validates keys with sub-millisecond latency using regional Redis caches and MySQL 8.0 persistent storage, while ClickHouse captures every verification event for per-key and per-keyspace analytics with filterable time-series charts, request counters, and active key tracking. Keyspaces organize API keys by product, environment, or tier, each configurable with custom prefixes, byte lengths, IP whitelists, encrypted key recovery, and delete protection. Per-key settings include expiration dates, rate limit quotas with configurable windows, RBAC roles and permissions, owner identities linking multiple keys to a single user or organization, and key rotation with grace periods from immediate revocation through 24-hour overlap. The deployment pipeline connects GitHub repositories for automatic Docker container builds, generates preview environments per commit, promotes tested versions to production, and validates releases with OpenAPI diff detection flagging breaking changes before production. The edge gateway authenticates and rate-limits requests at the closest region before routing to the nearest API instance. Immutable audit logs track every key creation, verification, deletion, and configuration change with actor, timestamp, and event metadata. The CLI provides terminal access to key management, analytics queries, and deployment operations. On RepoCloud, deploy Unkey on a dedicated VPS with Docker, root SSH access, and complete control over your API infrastructure, all under the AGPL license.

New hires fail from information overload and IT bottlenecks, not lack of goodwill - the observation behind ChiefOnboarding, a free, open-source employee onboarding platform (Django, Celery, PostgreSQL, Redis). Its answer is sequences - drag-and-drop timelines that drip-feed to-do items, resources, courses, forms, and badges to each new hire, triggered by dates or by completing a previous item, so nobody faces everything at once. Onboarding starts before day one: preboarding pages welcome hires early, and colleagues can leave personal messages that appear there. The account provisioning module creates the new hire's Slack, Google, Asana, and other accounts automatically on the scheduled day via a library of integrations plus custom webhooks - the IT ticket queue never gets involved. Everything works through two equivalent interfaces: a full web dashboard and a Slack bot, either usable standalone. Slack can even auto-create new hire accounts when someone joins the workspace and assign default sequences with zero manual action. Colleague tasks with comments and collaboration, a searchable people directory, scheduled introductions, and per-hire timezone awareness (no 3 a.m. notifications) round it out. No trackers, no phoning home - third-party credentials sit in encrypted fields on your server.

Memoh delivers an open-source multi-agent platform where every AI agent gets its own computer — not a chat window but a fully isolated container with dedicated filesystem, desktop environment, browser, network stack, and persistent long-term memory that survives across sessions, days, and platforms. The containerd-based runtime ensures each bot operates in complete isolation with snapshot and data import/export capabilities. The memory engine uses LLM-driven fact extraction with hybrid retrieval combining dense embeddings via Qdrant, sparse vectors, and BM25, plus 24-hour context loading and automatic compaction — with Mem0 and OpenViking as drop-in alternatives. Ten communication channels connect agents to users through Telegram, Discord, Lark, QQ, Matrix, WeCom, WeChat, Email, Web UI, and group chats with cross-platform identity binding. MCP tool calling enables agents to interact with external services, while browser automation drives GUI workflows for web research and data extraction. Agent hosting supports running external coding agents like Codex and Claude Code inside Memoh workspaces via ACP with per-bot configuration. Scheduled tasks run without human triggers, and agents proactively reach out when needed. The web dashboard built with Vue 3 and Tailwind CSS provides streaming chat, tool call visualization, file management, model and provider configuration, and bot lifecycle management. Deploy via Docker Compose with PostgreSQL, Qdrant, sparse service, and the Go backend server. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

Relaticle delivers the first CRM built from the ground up for both human operators and AI agents — a self-hosted platform where Claude, GPT, Gemini, or any custom model connects through a production-grade MCP server exposing 30 tools for full CRUD operations across companies, people, opportunities, tasks, and notes without a single line of integration code. The 22 custom field types include text, email, phone, currency, date, select, multiselect, entity relationships, conditional visibility rules, and per-field encryption — all configurable through the UI without database migrations or code changes. Multi-team isolation enforces data boundaries through a 5-layer authorization system with team-scoped workspaces, API tokens, and granular permissions. The JSON:API REST surface provides Spatie QueryBuilder filtering, sorting, and pagination with schema discovery endpoints that let agents introspect your data model at runtime. A built-in AI chat connects directly to CRM data for natural language queries, while the external MCP server gives any compatible agent the same 30-tool access. Docker Compose deployment runs five containers — app (nginx + PHP-FPM), Horizon queue worker, scheduler, PostgreSQL 17, and Redis 7 — with automatic migrations on startup and demo data seeding for new teams. 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.