KrakenD processes over 18,000 requests per second on a single instance while consuming under 50MB of RAM at 1,000 concurrent connections, operating as a stateless API gateway that requires no database whatsoever. The Community Edition has earned over 2,600 GitHub stars by outperforming database-dependent alternatives like Kong and Tyk in independent benchmarks. Written entirely in Go, it uses declarative JSON or YAML configuration files that integrate directly into GitOps workflows for version-controlled infrastructure management. The gateway aggregates responses from multiple backend services into a single API call, transforms request and response payloads with field filtering, grouping, and mapping, and applies zero-trust security policies including JWT validation, OAuth 2.0, CORS, HSTS, clickjacking protection, and XSS prevention. Traffic management features include multi-layer rate limiting at both the router and proxy levels, circuit breakers for backend fault isolation, spike arrest policies, and concurrent call support that requests the same data from multiple backends in parallel for improved response times. Telemetry integrates with OpenTelemetry, Prometheus, Grafana dashboards, Datadog, Zipkin, and Jaeger for distributed tracing and metrics collection. The gateway extends through Go plugins, Lua scripting, Martian modifiers, and Google CEL expressions for custom request processing logic. AI workload routing supports OpenAI, Anthropic, Gemini, and other model endpoints with built-in fallback, retries, and load balancing. Deploy via Docker with the devopsfaith/krakend image as a single binary. 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 110,000 GitHub stars and one of the fastest-growing open-source communities in the self-hosted space, Immich delivers a Google Photos-grade experience entirely on your own hardware. The platform handles automatic background backup from Android and iOS devices, deduplication, and support for RAW formats, LivePhotos, and MotionPhotos. Its machine learning pipeline runs facial recognition and clustering locally on your server, enabling you to group photos by person without sending a single image to the cloud. CLIP-based semantic search lets you find images by describing their content in natural language, while metadata-driven search covers EXIF data, dates, and locations. The web interface built with SvelteKit provides a responsive timeline view, albums, shared albums with configurable permissions, public sharing links with optional passwords and expiry dates, partner sharing for family libraries, and a global map plotting photos by GPS coordinates. Administrative features include multi-user support with per-user storage quotas, OAuth integration, API key management, and a user-defined storage structure for organizing files on disk. The architecture uses PostgreSQL for metadata, Redis with BullMQ for background job queues handling thumbnail generation, video transcoding, and smart search indexing, and exposes over 400 REST API endpoints documented via OpenAPI with auto-generated SDKs for web, mobile, and CLI clients. 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 over 7,700 GitHub stars and thousands of Cloudflare employees using it daily across every function, Cloudflare OS delivers an open-source AI workspace where every employee gets a personal agent grounded in company context, systems, and skills — not a generic chatbot but a programmable workspace that builds real applications, automates workflows, and connects to internal tools through governed access. The Code Mode agent writes and immediately executes code snippets to perform arbitrary tasks, build full-stack Gadgets with client code, server code, APIs, and durable SQLite state, debug errors, and test results within isolated sandboxes. Gadgets are private application instances running in separate sandboxes — each document, spreadsheet, or tool is its own secure runtime that cannot leak data even to attackers with access to other Gadgets. Blueprints enable sharing application code as templates that others instantiate with independent state, credentials, and resources. Gatekeepers provide security governance giving system owners precise control over what agents can see, change, and when human approval is required before actions execute. Built on Cloudflare Workers using Durable Objects for workspace persistence, Dynamic Workers for Gadget execution, and Facets for access management. Zero Trust security via Cloudflare Access verifies every user and request before granting access. Real-time collaboration lets colleagues use shared Gadgets. Deploy to your own Cloudflare account or self-host on workerd, the open-source Workers runtime, on your own servers. 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.

Duckle compiles visual data integration pipelines into vectorized analytical SQL executed on an embedded columnar engine, eliminating the overhead and cloud egress costs of traditional ETL infrastructure. Engineers can construct data pipelines on a drag-and-drop canvas, connecting hundreds of data sources spanning relational databases, cloud object storage, streaming event buses, vector databases, and SaaS application programming interfaces. An interactive mapping editor enables complex joins between primary data inputs and lookup streams with typed transform expressions and live sample inspections. Built-in transformation blocks execute change data capture, slowly changing dimensions, aggregation rollups, and integrated dbt models with zero row-based metering or cloud egress fees. Teams schedule headless production executions through a dedicated web console equipped with role-based access management, execution audit trails, and automated failure alerts dispatched to webhook endpoints. Embedded Model Context Protocol capabilities allow AI coding assistants to validate schema configurations, inspect execution logs, and trigger batch workflows directly through conversational commands. Workspaces store entire pipeline definitions as individual files in version control, ensuring reproducible deployments across staging and production environments. 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.

Backed by over 20,000 GitHub stars, 800 contributors, and organizations like Google, NASA, and the NHS, Wagtail is the Django-powered content management system that gives editors creative freedom through StreamField while keeping developers in full control of data structure and front-end rendering. StreamField lets editors compose pages from a custom library of content blocks — rich text, images, embedded videos, tables, code snippets, and developer-defined custom types — without compromising the underlying data model or breaking responsive layouts. The built-in JSON API supports headless deployments with versioned endpoints for pages, images, and documents, enabling decoupled front-ends in Next.js, Nuxt.js, or any framework that consumes REST. Editorial workflows provide configurable approval chains where content moves through draft, review, and publish states with commenting, task assignment, and email notifications built into the admin interface. Integrated search connects to Elasticsearch for full-text indexing with faceted filtering, or falls back to PostgreSQL and SQLite backends with fuzzy matching support added in v7.4. Multi-site management serves multiple domains from a single Wagtail installation with independent page trees, while the internationalization framework handles content translation with locale-aware URL routing. Image management includes focal point detection, responsive renditions, and automatic format conversion. The platform supports Django 5.2 and 6.0 with Python 3.10 through 3.14 and PostgreSQL, MySQL, MariaDB, or SQLite databases. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. BSD-3-Clause licensed.

What Trello fans wanted Trello to stay: Kan (kan.bn) is a minimalist, frills-free kanban board capturing the original vision before the enterprise pivots - and then adds the things 2025 actually demands. The core is exactly right: drag-and-drop cards across lists, labels and filters to find work fast, comments for discussion on cards, checklists, a detailed activity log tracking every change, and reusable board templates. Workspaces gather your team with member invites and role management, and board visibility controls decide who can view or edit each board. Migration is first-class: a built-in Trello importer brings existing boards over, so switching costs an afternoon, not a quarter. The standout differentiator is the bundled Model Context Protocol server exposing 46 tools across workspaces, boards, lists, cards, comments, checklists, labels, and members - meaning Claude Desktop, Cursor, Copilot, or any MCP client can read and manage your boards in natural language: "move everything assigned to me into Done" becomes a sentence, not a click marathon. The stack is modern TypeScript - Next.js, tRPC, Drizzle ORM over PostgreSQL, Better Auth (credentials or OAuth), Tailwind - with optional SMTP email and S3 file storage. Unlimited boards, lists, and cards; AGPL-licensed.

Wire nodes together in a browser, deploy in one click, and real-time data flows from sources through transformations to outputs: Node-RED is the OpenJS Foundation's flow-based programming tool for event-driven applications. Born at IBM as a proof-of-concept for manipulating MQTT topic mappings, it has become the lingua franca of IoT and automation glue - home automation, industrial control, edge data collection - with a community library of over 5,000 contributed nodes and flows covering protocols, devices, and services. Where visual wiring runs out, JavaScript function nodes written in a rich in-editor code editor take over, and every flow serializes to importable, exportable JSON that shares cleanly and version-controls sensibly. Version 5.0 (2026) delivered the largest editor overhaul in the project's history: a rethought layout with Explorer and Information panels in a split sidebar, a native dark theme with theme variants, improved accessibility, and refreshed node appearance. The runtime is lightweight Node.js, exploiting the event-driven non-blocking model so the same flows run on a Raspberry Pi at the network edge or a cloud VM. Apache-2.0 licensed with 240+ contributors, it pairs naturally with dashboard nodes for live charts and controls.

Backed by 39,500+ GitHub stars and over 339 releases, MindsDB delivers the open-source federated query engine that gives AI agents a single SQL interface to read, join, and aggregate across 200+ live data sources without any ETL pipelines or data movement. The Connect-Unify-Respond architecture wires up Postgres, MySQL, MongoDB, Snowflake, BigQuery, ClickHouse, Redshift, Databricks, Salesforce, Shopify, Slack, S3, GCS, Azure Blob, and dozens more through self-contained Python handler packages merged in the open from the community. Knowledge Bases fuse structured tables with vectorized unstructured data from PDFs, emails, support tickets, and documents using hybrid search combining vector similarity with keyword matching for retrieval-augmented generation. Jobs execute queries on configurable schedules refreshing Knowledge Bases nightly or syncing derived tables hourly, while Triggers fire on data changes to automatically vectorize new rows into the appropriate store. The SQL-compatible query language extends standard SQL with constructs for creating models, defining agents, managing workflows, and searching unstructured data. The built-in web editor at port 47334 provides interactive SQL authoring, while the MySQL-compatible API at port 47335 and PostgreSQL API at port 47336 connect any database client directly. An MCP Server integration exposes MindsDB to AI assistants, and the Python SDK enables programmatic access from application code. Docker deployment runs with a single command exposing all APIs immediately. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Backed by $50M+ from Benchmark, Y Combinator, and NVIDIA with 800+ contributors and 39,000+ GitHub stars, MindsHub Cowork is the unified AI workspace where open-source models handle entire projects — research, reporting, internal tools, scheduled operations — and return finished, shareable deliverables. The platform runs two interchangeable open-source agent harnesses, Anton and Hermes, swappable from a dropdown without losing context. A built-in Model Router pre-wires 25+ models spanning Anthropic Claude, OpenAI GPT, Google Gemini, DeepSeek, Qwen, Kimi, Grok, and MindsHub Air with automatic failover — no per-provider API keys required. A secure credentials vault connects BigQuery, PostgreSQL, Salesforce, HubSpot, Zendesk, Gong, Gmail, Google Drive, Notion, Linear, Stripe, and Slack, keeping secrets scoped per connection so agents never see raw keys. Agent output becomes publishable artifacts — documents, dashboards, apps, and code — each deployable to a live shareable URL. Cross-session persistent memory, a reusable skill library, and a background scheduler supporting hourly, daily, and weekly cadences enable autonomous recurring workflows. The architecture separates a React/Vite frontend (shipping as both Electron desktop app and web SPA) from a FastAPI backend with a versioned REST API at /api/v1 covering conversations, projects, artifacts, schedules, and connectors. Self-host via Docker Compose with nginx on port 3000 and the API on port 26866, or deploy on-prem, in a VPC, or air-gapped. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Why should your chat history live on someone else's servers? Chatpad AI - a React/TypeScript front end for the OpenAI API, built on the Mantine component library - is designed around that question. Enter your own OpenAI API key and start chatting with GPT models; every conversation, prompt, and setting is stored locally in your browser via DexieJS over IndexedDB, with no tracking, no cookies, and no backend database at all. That architecture is the point - the Docker image is just Nginx serving static files, making it one of the lightest AI deployments in the catalog, and pay-per-token API pricing typically undercuts a ChatGPT Plus subscription for moderate use. The interface earns its "premium quality" tagline with the details: a persona selector that switches communication styles per conversation, a saved-prompts library for messages you reuse constantly, organized chat history, and full data export/import so conversations move between browsers or into backups as files you control. A JSON config file customizes defaults - models, API endpoints, UI options - without rebuilding the image. AGPL-licensed, with desktop builds available upstream. For teams that want ChatGPT's utility with a self-hosted, zero-telemetry footprint, Chatpad is the minimal, sane answer.

Schema design with no account and a few clicks: drawDB is the browser-based entity-relationship diagram editor and SQL generator - an AGPL-3.0 React project with over 37,000 GitHub stars. Draw tables with columns, data types, defaults, and constraints; connect fields to create foreign-key relationships; group tables into labeled subject areas; and annotate with notes. When the design is ready, one export produces CREATE TABLE DDL - with constraints, indexes, and foreign keys - targeted at MySQL, PostgreSQL, SQLite, MariaDB, SQL Server, or Oracle. Diagrams can be database-specific, unlocking every native type plus dialect features like PostgreSQL enums and composite custom types, or generic for portability across all supported flavors. The reverse direction works too: paste existing DDL into the import dialog and drawDB renders your live schema as a navigable diagram - the fastest way to document an inherited database. Versioning and migration-script generation track schema evolution, full editor ergonomics (undo/redo, copy/paste, duplicate, themes) keep iteration fast, and diagrams export as PNG, SVG, or shareable JSON. Everything runs client-side against browser storage - no backend database connection needed - so the self-hosted Docker deployment is a featherweight static app that keeps proprietary schema designs entirely on your infrastructure.

With over 37,000 GitHub stars and used by teams at Y Combinator, Airbus, and Phantom, PostHog replaces an entire stack of paid analytics tools — Mixpanel, Amplitude, Heap, LaunchDarkly, Hotjar, and Google Analytics — with a single open-source platform where every tool shares a common event layer and user context. Product analytics captures events automatically or via manual instrumentation with HogQL (SQL) access for custom queries, while web analytics provides GA-like dashboards for traffic, conversions, and Core Web Vitals. Session replay records user interactions with DOM snapshots and network waterfall analysis, linking directly to errors and feature flag exposures. Feature flags safely roll out changes to specific cohorts with multivariate support and instant rollback, while experiments run A/B tests with automatic Bayesian significance calculations and revenue attribution. Error tracking captures stack traces linked to session replays and user properties for immediate reproduction context. AI observability monitors LLM generations, traces, token usage, latency, and costs across model versions. The managed data warehouse syncs 120+ external sources including Stripe, Postgres, Salesforce, and HubSpot alongside product events, queryable through a unified SQL editor. An MCP server enables AI agents in Cursor, Claude Code, or VS Code to query analytics and execute SQL 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.

With 5,400+ GitHub stars and sub-millisecond response times that eliminate the need for dedicated caches entirely, TrailBase consolidates your database, API server, auth service, realtime subscriptions, and admin interface into a single Rust binary weighing under 40MB. The platform generates type-safe CRUD APIs automatically from your SQLite schema with configurable access control rules using SQL expressions, while realtime subscriptions push data changes to connected clients via Server-Sent Events. The embedded Wasmtime runtime executes custom server-side logic as WebAssembly components compiled from Rust, JavaScript, Python, or any language targeting WASI, enabling complex business logic without external services. First-class geospatial support through the in-house LiteGIS GEOS extension provides GeoJSON integration, spatial indexing via R-Trees, and query operators including @within, @intersects, and @contains for location-based applications. Client SDKs span JavaScript/TypeScript, Dart/Flutter, Rust, C#/.NET, Swift, Kotlin, Go, and Python — covering mobile, web, desktop, and IoT platforms. The admin dashboard offers visual schema editing, a data browser, Record API configuration, OAuth provider setup, user management, SQL query editor, ERD visualization, and server logs. Experimental PostgreSQL support (v0.28+) allows connecting to existing Postgres instances via connection string. Deploy via a single binary, Docker container, or the one-line install script across Linux, macOS, and Windows. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. OSL-3.0 licensed.

OpenLLM serves any large language model as an OpenAI-compatible API endpoint from a single CLI command, handling model download, backend selection, quantization, and port binding automatically. It supports the full spectrum of popular models including Llama 3.3, Qwen2.5, DeepSeek, Mistral, and Phi3, choosing between vLLM and PyTorch inference backends based on hardware capabilities. When vLLM is available, continuous batching with PagedAttention achieves up to 23x throughput improvement over naive serving, while GPTQ and bitsandbytes quantization reduces memory requirements for GPU-constrained deployments. The server exposes a RESTful API on port 3000 with full OpenAI client library compatibility, enabling drop-in replacement for commercial providers in any application using the standard chat completions format. A built-in web chat UI at the /chat endpoint provides immediate interactive testing without external clients. Custom model repositories allow teams to maintain private catalogs of fine-tuned models alongside the default repository that tracks the latest releases. Deployment workflows generate production-ready Docker images automatically, with Kubernetes manifest support for orchestrated scaling. Native integration with LangChain and LlamaIndex supports RAG pipelines, Transformers Agents enables tool-calling workflows, and HuggingFace Hub handles model discovery. Server-Sent Events enable real-time token streaming across all API endpoints. Backed by BentoML's production ML infrastructure. 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.

Pelican Panel is an open-source game server management platform that enables gaming communities and hosting providers to deploy, configure, and operate multiplayer servers for titles like Minecraft, Palworld, and Counter-Strike within secure, containerized environments. Administrators can provision dedicated game servers in seconds using modular configuration eggs, allocating precise CPU cores, memory thresholds, and disk quotas to prevent resource contention across noisy neighbors. Players and server operators access an interactive web console featuring live terminal output, instant power state toggles, and direct command execution over secure WebSockets. An integrated file browser enables operators to upload server modifications, edit configuration scripts with syntax highlighting, and decompress archives without opening an external terminal. Built-in scheduling pipelines automate recurring tasks such as world backups, daily server restarts, and mod updates based on custom cron expressions. Multi-tenant permission controls allow guild leaders to invite co-administrators and grant granular privileges for restarting daemons, reviewing console logs, or managing database credentials without exposing the host system. Operators can also provision external SFTP endpoints, attach secondary IP allocations, and trigger webhook alerts whenever container health anomalies occur. 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.

"As simple as Trello but as feature-rich as Jira" is how the Leantime team frames its goals-focused project management system for non-project managers - built from the ground up with ADHD, autism, and dyslexia in mind, with behavioral science shaping customizable dashboards, time blocking, low-cognitive-load prioritization, and Kanban, list, table, Gantt, and calendar views so each person works the way their brain does. The PHP application (AGPL, Laravel Blade frontend) connects strategy to execution: tasks with unlimited subtasks and dependencies roll up into milestones on a timeline, sprints and retrospectives handle iteration, and strategy-level blueprint boards - Lean Canvas, SWOT, risk analysis, goal and metric tracking - keep the "why" attached to the work. Knowledge lives alongside: wikis and docs, idea boards, comments on everything, file storage on S3 or local disk, even screen and webcam recording. Time tracking with timesheets supports estimation and client billing. Admin features are serious for an OSS tool: per-project permissions, two-factor auth, LDAP and OIDC single sign-on, Slack, Mattermost, and Discord integrations, a plugin system, and an expanding API that now powers a mobile app. Recent releases added multi-collaborator task assignment and low-vision accessibility improvements. Available in 20+ languages.

With 15,500 GitHub stars and over 1,100 forks, Plandex delivers a terminal-based AI coding agent purpose-built for the complex, multi-file tasks that overwhelm single-file AI assistants. The Go-powered server maintains a cumulative diff review sandbox that quarantines all AI-generated changes from your project files until you explicitly approve them — enabling 20-file refactors where you cherry-pick good changes and reject bad ones without touching git. A 2M token effective context window loads only what each step requires, while tree-sitter project maps index repositories exceeding 20M tokens across 30+ programming languages, providing structural awareness of class hierarchies, function signatures, and import graphs without burning tokens on full file content. The configurable model pack system assigns different models to different roles — Claude for planning, GPT for coding, Gemini for summarization — supporting Anthropic, OpenAI, Google, OpenRouter, Azure OpenAI, AWS Bedrock, DeepSeek, Perplexity, and Ollama for local models. Full auto mode handles end-to-end autonomous workflows including high-level planning, context loading, implementation, terminal command execution, and automated debugging of both terminal and browser applications. The interactive REPL provides fuzzy auto-complete, version-controlled sandbox branching, rewind to any previous point, and Git integration for commit message generation. The Plandex Server exposes 60+ REST API endpoints for programmatic orchestration across organizations, projects, plans, and branches. Deploy via Docker Compose for self-hosted operation with your own API keys. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Backed by Alibaba's AIDC team and carrying over 27,700 GitHub stars, Pixelle-Video turns a single text prompt into a publish-ready short video in approximately three minutes — handling scriptwriting, image generation, voice narration, music selection, subtitle overlay, and final MP4 export in one automated pipeline. The engine supports multiple LLM backends for script generation including GPT-4, Qwen, DeepSeek, and local Ollama deployments, while image and video creation routes through either self-hosted ComfyUI workflows, cloud-based RunningHub pipelines, or direct API connections to DashScope Wan, OpenAI, Seedream, Seedance, and Kling AI. Text-to-speech synthesis uses Edge-TTS, Index-TTS, and other mainstream engines with multi-language voice profiles. Five distinct pipelines cover Quick Create, Standard, Digital Human Avatar broadcasting, Image-to-Video transformation, and Motion Transfer from reference video. The Streamlit web UI on port 8501 provides a visual workflow builder with template selection across portrait (1080x1920), landscape (1920x1080), and square formats, while the FastAPI server on port 8000 exposes a REST API with endpoints for async video generation, task polling, content scripting, TTS and image generation, template listing, and health checks. History persistence tracks all completed generations. HTML-based visual templates support static, image-overlay, and AI-video styles with customizable prompt prefixes. The modular architecture lets operators swap any atomic capability — image model, video model, TTS engine, or VLM — by editing a workflow JSON file without touching Python code. 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.