Claiming 60-80% token cost reduction compared to flat single-model deployments and backed by 6,500+ GitHub stars, OpenSquilla delivers an intelligent AI agent runtime where a local ML classifier evaluates every turn on message length, code blocks, keyword patterns, and semantic embeddings before routing it to the optimal model tier from C0 through C3. The pluggable provider layer connects natively to TokenRhythm, OpenRouter, OpenAI, Anthropic, Ollama, DeepSeek, Gemini, DashScope, Moonshot, Mistral, Groq, Zhipu, SiliconFlow, vLLM, LM Studio, and additional compatible backends with primary-plus-fallback selection. The four-tier cognitive memory architecture spans working, episodic, semantic, and raw layers with vector-semantic and BM25 retrieval powered by on-device ONNX embeddings that never leave your infrastructure. Security isolation operates at the syscall level via Bubblewrap on Linux and Seatbelt on macOS, complemented by policy-based execution controls and prompt injection protections. The unified TurnRunner executes identically across the Vue-based control console Web UI, terminal CLI, and chat channel integrations including Slack and Discord, ensuring consistent tool dispatch, retry logic, and decision logging regardless of entry point. Built-in skills cover deep research, multi-search-engine queries, document generation for DOCX, PPTX, XLSX, and PDF formats, GitHub integration, cron scheduling, and bounded subagent delegation. Per-agent workspaces with durable session storage provide transcript replay, context state management, and per-call cost tracking with automatic quota enforcement. 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.

Calendars, to-do lists, journal entries, and contacts, synced over the open CalDAV and CardDAV standards nearly every client already speaks: Radicale is a small pure-Python server that works with Thunderbird, DAVx5 on Android, Apple Calendar and Contacts, GNOME, and many more. Its defining design choice is radical simplicity: there is no database. Events live as plain .ics files and contacts as .vcf files in an ordinary folder structure, which makes backup a copy command, migration a move, and disaster recovery a matter of reading text files. The server works out of the box with no complicated setup, then grows as needed: flexible authentication (htpasswd files among other methods), per-collection authorization rules, TLS-secured connections, and a plugin system for extending storage, auth, and rights handling. Built-in limits on parallel connections, file sizes, and failed authentication attempts harden it for network exposure behind a reverse proxy. A bundled web interface handles creating and managing calendars and address books - useful since many clients cannot create collections themselves. Maintained since 2011 with 140+ contributors, GPLv3-licensed, and light enough to run on the smallest VPS or a Raspberry Pi.

With over 7,000 GitHub stars and active community maintenance through version 0.26.0 released in June 2026, Homebox fills the gap between inadequate spreadsheets and overcomplicated enterprise asset management by providing a purpose-built inventory system designed specifically for home users, families, and small groups. The Go backend with SQLite storage deploys as a single Docker container consuming under 50MB of RAM at idle, running on hardware as modest as a Raspberry Pi while the responsive web interface adapts seamlessly across desktops, tablets, and smartphones. The entity-based architecture introduced in v0.26 unifies items and locations into a shared structure supporting custom fields, attachments, entity types, and reusable templates for consistent data entry across inventory categories. QR code generation creates printable labels that scan with any smartphone camera to instantly display item details, photos, serial numbers, and associated documents. Warranty tracking records purchase dates, prices, and expiration dates while maintenance scheduling sends reminders for recurring service tasks. Location hierarchies organize items spatially with nested sub-locations, and flexible label tagging enables cross-cutting categorization beyond physical placement. Multi-user support shares collections with family members or roommates with OIDC single sign-on integration for Active Directory, Okta, and other identity providers. CSV import and export handles bulk operations, while the full REST API enables automation and third-party integrations. Collection-level ZIP export packages complete inventories with attachments for backup or migration. 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.

Salesforce's platform model, 100% open-source (Apache 2.0): Corteza is a Go/Vue.js low-code platform developed under a foundation, so there is no open-core bait to grow out of. The heart is Corteza Compose: namespaces contain applications, modules define record structures the way Salesforce objects do, and a drag-and-drop page builder assembles record pages, list pages, dashboards, and charts from configurable blocks. Automation comes from a visual, BPMN-style workflow engine plus JavaScript automation scripts, so cross-application business logic - approval chains, field updates, notifications - is configured rather than programmed. Granular role-based permissions reach down to individual modules, fields, and records, mirroring real organizational hierarchies. Corteza CRM ships as the flagship application built entirely on Compose: leads, accounts, opportunities, campaigns, and cases with a 360-degree customer view, covering most Salesforce standard objects - and because it is just a Compose app, adding or reshaping modules is configuration, not a fork. Everything is reachable over REST APIs, deliberately familiar tooling eases Salesforce admin migration, and a CLI can even generate synthetic records for load-testing what you build.

Mayan EDMS stores, classifies, and retrieves millions of documents with automatic OCR, workflow automation, and audit-ready access controls that organizations have relied on for over a decade. Tesseract integration extracts searchable text from scanned PDFs and images in over 100 languages, transforming paper archives into instantly queryable digital collections without manual data entry. The workflow engine routes documents through approval chains using configurable state machines that trigger notifications, enforce retention policies, and maintain complete audit trails for regulatory compliance. Version tracking preserves every revision with full diff capabilities, while GnuPG digital signatures provide cryptographic proof of authenticity and tamper detection for sensitive records. Role-based permissions combined with object-level ACLs and LDAP integration ensure documents remain visible only to authorized users, down to individual file granularity. Full-text search powered by Whoosh or ElasticSearch handles advanced queries across massive document stores with faceted filtering and relevance ranking. The Django REST Framework API enables programmatic upload, metadata extraction, and workflow triggering from external systems. Beyond simple folder hierarchies, metadata schemas, document types, tags, and cabinet structures provide multi-dimensional classification tailored to how your organization actually works. Background processing through Celery handles OCR, conversion, and preview generation asynchronously, keeping the web interface responsive under heavy ingest loads.

Livebook is an interactive notebook for Elixir where you write code alongside rich Markdown prose, execute it cell by cell with reactive dependency tracking, and deploy finished notebooks as standalone web applications with a single click. Nearly 6,000 GitHub stars reflect the Elixir core team's investment in a platform where code cells run on demand alongside Mermaid diagrams and KaTeX mathematical formulas. The Kino visualization library renders Vega-Lite charts, interactive data tables with sorting and pagination, Leaflet maps, and Mermaid diagrams directly within notebook output cells, while custom Kino components enable building interactive controls with sliders, text inputs, and buttons that feed values back into running code. Smart cells abstract high-level tasks into configurable UI widgets: query PostgreSQL, MySQL, SQLite, and BigQuery databases, train machine learning models with Axon, plot charts, and build map visualizations without writing boilerplate code. Real-time collaboration lets multiple users edit the same notebook simultaneously with cursor presence indicators and synchronized cell evaluation. Notebooks are stored as .livemd files, a Markdown-compatible format that renders cleanly on GitHub and integrates with standard version control workflows. Custom runtimes connect Livebook to existing Elixir applications for live introspection and documentation of running systems. The Docker image at ghcr.io/livebook-dev/livebook exposes ports 8080 and 8081 with password or token authentication. 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.

Exceptionless has earned over 2,400 GitHub stars and has been processing production errors since 2014 as the real-time event monitoring platform that captures far more than crashes. Built with ASP.NET Core on Elasticsearch for storage and Redis for caching, Exceptionless ingests exceptions, log messages, feature usage events, broken links, and custom event types through official SDKs for JavaScript, Node.js, .NET Core, ASP.NET, WPF, Web API, WebForms, Console apps, and React Native. Automatic event stacking groups related occurrences by exception type, message, and call stack into single actionable items, while manual stacking keys let developers create custom groupings for specific features or workflows. The real-time dashboard displays Most Frequent, Most Recent, and New event views with filtering by project, date range, environment, and custom tags. Stack management tracks resolution status with version-aware regression detection that automatically reopens resolved issues when the same error surfaces in a newer release. Webhook integrations connect to Slack, Discord, and external services through Zapier for automated issue tracking in GitHub Issues and Jira. Per-project notification settings control email and chat alerts for new errors, regressions, and critical events. OpenTelemetry support captures distributed traces alongside error data. The v8.6.0 release introduced a hosted Model Context Protocol server at the /mcp endpoint, enabling AI tools to query error data via OAuth-authenticated access. Deploy via Docker with the exceptionless/exceptionless image alongside Elasticsearch 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.

Describe what you want in plain language and get real SQL against your real schema: SQL Chat is an open-source, chat-based SQL client from the Bytebase team. Instead of writing queries in a traditional editor, you connect a database and describe what you want in plain language; the AI reads your schema automatically, generates SQL that references real table and column names, executes it, and returns tabular results in the conversation. Follow-up messages refine the query, so exploration becomes a dialogue - narrow a result set, add a join, change an aggregation - without retyping statements. It supports MySQL, PostgreSQL, SQL Server, TiDB Cloud, and OceanBase from one interface, and covers modification as well as reads: insert, update, and delete operations phrased conversationally. Built with Next.js and TypeScript, it deploys as a single stateless Docker container in single-user mode - connection profiles live in the browser, so there is nothing server-side to maintain. A custom AI endpoint setting routes inference through any OpenAI-compatible API, including self-hosted models, and an optional database-backed mode adds accounts and quotas for offering the tool to a team. MIT-licensed.

Open Agent Builder delivers a visual canvas for orchestrating AI agent workflows without writing Python scripts or managing complex codebases. The React Flow-powered drag-and-drop interface supports seven node types — Agent, Scraper, Transform, If/Else, Loop, User Approval, and MCP Tool — each configurable with provider-specific settings for Anthropic Claude (Haiku 4.5 and Sonnet 4.5), OpenAI GPT-5, Groq, or any OpenAI-compatible endpoint. The LangGraph orchestration engine handles state management, conditional routing, and human-in-the-loop approval gates while Firecrawl integration converts any website into structured, LLM-ready data through scrape, crawl, and map operations. E2B sandboxed code execution powers Transform nodes for secure data manipulation without risking host system integrity. Real-time streaming updates show execution progress node-by-node as workflows run, with Convex providing reactive database synchronization for workflow state and execution history. The TypeScript-first architecture (96.8% TypeScript) built on Next.js 16 App Router with Tailwind CSS delivers a responsive interface across devices. Clerk handles multi-user authentication with JWT integration for secure workspace isolation. Deploy via npm install and environment configuration with Firecrawl, Convex, and Clerk 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.

LearnHouse delivers a modern open-source learning platform that replaces proprietary course builders with a self-hosted alternative shipping a rich feature set out of the box. The Tiptap-powered block editor supports videos, documents, embeds, quizzes, and file uploads in a Notion-like interface with real-time co-editing powered by Hocuspocus and Yjs CRDT synchronization over WebSocket. AI tutoring integrates Google Gemini and LlamaIndex for RAG-powered context-aware assistance that adapts to course content, while interactive Playgrounds use AI to generate simulations, diagrams, and learning exercises. The platform handles the full course lifecycle: chapters and activities organize into collections and learning paths, assignments support automated and manual grading, and code blocks execute student submissions in 30+ languages with auto-grading. Analytics dashboards track learner engagement, progress, and completion rates in real time. The backend runs on FastAPI with SQLModel and Alembic migrations against PostgreSQL 16 with pgvector for AI embeddings, while Redis handles caching and session management. The frontend builds on Next.js 16 with React 19 and Tailwind CSS v4. Deployment uses an interactive CLI wizard that configures domain, database, admin account, SSL via Let's Encrypt, and optional features like email via Resend, S3 storage, and Google OAuth, then generates a Docker Compose stack ready to start. On RepoCloud, deploy LearnHouse on a dedicated VPS with root SSH access, persistent PostgreSQL storage for your course data, and complete control over AI provider keys and branding customization, all under the AGPL v3 license.

Solidtime is a time tracker for freelancers and agencies, offering a modern SaaS-quality interface that rivals commercial tools like Toggl and Clockify. The time tracking interface provides a running timer, calendar view, and weekly timesheet for flexible entry across desktop, mobile, and the dedicated macOS, Windows, and Linux desktop applications. Project management organizes work by client with hierarchical billable rates configurable at organization, member, project, and project-member levels, ensuring accurate billing across complex team structures. The invoicing module generates polished PDF invoices and structured EU e-invoices with configurable VAT rates, percentage and fixed discounts, EU reverse-charge handling, reusable company templates, and automatic line item generation from billable time entries. Reporting provides filterable summaries by user, project, client, and date range with exportable data for billing audits and team retrospectives. Multi-organization support manages separate workspaces from a single account with role-based permissions controlling access across organizations. Data import from Toggl, Clockify, and generic Timeentry CSV files enables migration from existing tools without losing historical records. The RESTful API with bearer token authentication enables automation and integration with external services. Docker deployment with PostgreSQL runs behind Nginx or Traefik reverse proxy. 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.

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 7,500 GitHub stars and 1 million Docker pulls — making it the most popular open-source database backup tool on GitHub ahead of pgBackRest and WAL-G — Databasus delivers production-grade backup management through a designer-polished web interface that replaces complex configuration files and CLI-only workflows. The platform supports PostgreSQL 14-18, MySQL 5.7-8, MariaDB 10-12, and MongoDB 4.2-8 with logical backups via pg_dump and mysqldump, while PostgreSQL 17+ enables physical backups using the native pg_basebackup engine with block-level incremental support via pg_basebackup --incremental and continuous WAL streaming via pg_receivewal for Point-in-Time Recovery to any second between backups. Storage destinations include local disk, AWS S3, CloudFlare R2, Google Drive, Azure Blob Storage, SFTP, NAS, and rclone-backed targets, while built-in AES-256-GCM encryption secures both backup files and stored credentials. Restore verification runs automated recovery into throwaway Docker containers, validating backups by comparing schema counts, table structure, and row counts against the source database — proving recoverability rather than merely checking checksums. The notification system integrates with Slack, Discord, Telegram, email, and webhooks for real-time backup status alerts. Deployment options span a single Docker container, Docker Compose with Caddy for automatic HTTPS, Helm charts for Kubernetes clusters, or a one-line install script. SSH tunnel support reaches databases in closed networks through bastion hosts without public exposure. 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.

Flexprice is a developer-first billing platform built specifically for AI-native and SaaS companies that need usage-based, credit-based, and hybrid pricing models without building custom billing infrastructure. The metering engine ingests millions of usage events in real time through HTTP APIs or SDK calls, supporting sum, count, unique count, latest value, and multiplier aggregation strategies across custom event schemas like API calls, token counts, compute minutes, and GPU time. Credit management handles prepaid wallets with promotional grants, rollover caps, auto top-ups, and priority-based credit application during invoice generation. The pricing engine supports per-unit, tiered, volume, package, and flat-rate models with per-customer overrides, committed minimums, and enterprise contract terms. Feature entitlements enforce boolean toggles, metered usage limits, and configuration values per plan, enabling applications to gate functionality through simple API checks. Automated invoicing calculates charges from real-time usage data with proration for mid-cycle upgrades and downgrades, generating detailed line items linked to tracked consumption. The architecture separates event ingestion through Kafka from billing computation via Temporal workflow orchestration, allowing each layer to scale independently with ClickHouse handling high-performance usage aggregation. Stripe Connect integration processes payments and manages customer payment methods. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPLv3 licensed.

Frappe Insights delivers a self-hosted business intelligence platform where non-technical users build complex analytical queries without writing SQL. The visual query builder uses Ibis under the hood to compose optimized SQL from drag-and-drop column selections, filters, aggregations, and group-by operations — translating point-and-click interactions into performant database queries across MySQL, PostgreSQL, DuckDB, and BigQuery. The join editor provides a graphical interface for defining multi-table relationships, letting analysts connect data across schemas without understanding foreign keys or join types. The chart builder renders interactive visualizations using Apache eCharts with support for bar, line, area, pie, scatter, funnel, and pivot table chart types — each configurable with axes, colors, legends, and formatting options. Dashboards combine multiple charts into shareable views with layout customization, auto-refresh intervals, and filter propagation across widgets. Data source management handles connection pooling across multiple databases simultaneously, enabling cross-database analysis in single queries. Server scripts extend query capabilities with custom Python transformations for complex business logic that visual tools cannot express. Built on the Frappe Framework's full-stack architecture, deployment uses Docker via the official easy-install script that provisions the complete stack including MariaDB, Redis, and Nginx. 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.

Mathesar puts a spreadsheet in front of your PostgreSQL database, letting anyone on the team browse, edit, filter, sort, and query tables without writing a line of SQL. Connect it to any existing PostgreSQL instance and immediately navigate schemas, tables, and records through an intuitive grid interface with inline editing, grouping, and summarization. The query builder joins tables across foreign key relationships, creates custom views with aggregations, and exports results to CSV. Rather than inventing its own permission layer, Mathesar maps each user or team to a native PostgreSQL role with granular schema-level and table-level privileges enforced at the database engine level, so there is never a gap between what the UI allows and what the database permits. Record summary templates display human-readable representations of linked records, making foreign key relationships immediately understandable instead of showing raw IDs. Import data from CSV files, create new tables and columns with proper PostgreSQL types including arrays, JSON, and custom domains, and modify schema structure through the web interface. Mathesar scales as well as the underlying PostgreSQL instance with no artificial limits on database size or complexity. Maintained by the Mathesar Foundation, a 501(c)(3) nonprofit, with a permanent commitment against vendor lock-in or licensing changes. Docker deployment connects to existing PostgreSQL instances or a bundled database in minutes. 5,000+ GitHub stars. GPL-3.0 licensed.

With over 3,800 GitHub stars and continuous development since 2002 spanning 24 years of active maintenance through version 16.4.0 released in May 2026, Piwigo has proven itself as one of the most battle-tested self-hosted photo gallery platforms available, trusted by professional photographers managing 150,000+ high-resolution images alongside small teams sharing event photos. The PHP backend with MySQL or MariaDB storage serves a responsive web interface that organizes photos into hierarchical albums with nested sub-albums, tag-based categorization, and smart albums generated dynamically from search criteria. Batch management tools handle bulk uploads, metadata editing, tag assignment, and album moves across thousands of images simultaneously. User permission controls define access at the album level with configurable public, private, and group-restricted visibility, while guest access allows public galleries without authentication. Image processing via ImageMagick or PHP GD generates multiple thumbnail sizes, watermarks, and responsive derivatives automatically. The plugin ecosystem with over 200 community-built extensions adds functionality from EXIF metadata display and GPS mapping to social sharing, download controls, and Lightroom synchronization for desktop workflow integration. The REST Web API with personal API key authentication enables programmatic album creation, photo uploads, and metadata queries from external applications. Mobile apps for iOS and Android provide on-the-go upload and browsing capability. Docker deployment via the official container or traditional LAMP installation on any hosting provider. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-2.0 licensed.

A Node.js server, a large shared canvas, and a URL - WBO (Whiteboard Ophir) is collaborative whiteboarding reduced to its essence. There are no accounts and no setup - to collaborate, you send someone the board's link, and every stroke appears for all connected users in real time over WebSockets, with cursor positions shared so you can see where collaborators are working. Board state persists automatically and continuously, so a diagram drawn in today's lesson is still there next week at the same URL. Boards come in three flavors: a public free-for-all, private boards with random unguessable names, and named boards with custom URLs shared by anyone who knows the name. The tools cover teaching and brainstorming needs - pencil, straight lines, rectangles, ellipses, text annotations, eraser, a full color palette with brush sizes - and boards export as SVG or PNG. Despite the simplicity, the server is production-minded: JWT authentication gates board access with granular capabilities (open, edit, and clear as separate permissions), rate limiting caps per-client message volume, reverse-proxy and subpath deployment are supported, and OpenTelemetry provides metrics, logs, and traces. It works on tablets and touch devices, speaks multiple languages, and consumes minimal resources. AGPL-licensed.