big-AGI is an open-source generative AI workspace that provides a unified, local-first interface for orchestrating multi-model reasoning, automated code execution, and custom persona workflows across private infrastructure. Users query multiple large language models simultaneously through the Beam scatter-gather engine, which prompts independent AI systems in parallel, compares candidate completions side by side, and merges optimal passages into a single refined response. Knowledge workers assemble tailored AI personas equipped with specialized system instructions, custom temperature settings, and predefined document context to handle domain-specific tasks ranging from architectural design reviews to legal contract analysis. The application renders rich multimedia outputs including interactive Mermaid sequence diagrams, LaTeX mathematical formulas, syntax-highlighted code blocks with live execution previews, and AI-generated image generation canvases. Teams integrate local inference servers like Ollama and LocalAI alongside commercial API endpoints to route confidential datasets strictly through internal networks while monitoring per-prompt token usage and operational latency. Users attach complex PDF documents, spreadsheets, and source code repositories for automatic parsing and semantic retrieval, while local-first storage engines ensure private chat transcripts and custom presets remain encrypted on host drives. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

A server full of scattered services becomes one clean application hub under Flame - a self-hosted startpage where every bit of configuration happens in built-in GUI editors, never a config file. Applications and bookmarks are created, edited, and organized into categories directly in the browser, and favorites pin to the homescreen for one-click access. The integrated search bar filters your apps and bookmarks locally as you type, and prefix shortcuts (like /g for Google) route queries to any of 11 web search providers or custom ones you define, making Flame a genuine browser homepage rather than a static link wall. Docker integration is the standout for homelabs: mount the Docker socket, add flame.type, flame.name, and flame.url labels to containers, and new services appear on the dashboard automatically - Kubernetes Ingress annotations work the same way. A weather widget shows temperature, cloud coverage, and animated conditions for your coordinates, and password authentication protects settings and items. Appearance is deeply customizable with 15 built-in color themes, a custom theme builder, and full custom CSS support. The stack is Node.js with SQLite behind a React frontend - light, fast, and inspired by the minimalist SUI design.

Any blog, documentation site, or static website can host a complete comment section by running its own Waline server, with Markdown, emoji, reactions, and moderation tools included. A visitor writes as a guest, registers an account, or signs in with GitHub, Twitter, Facebook, Weibo, or QQ, and a live preview shows the formatting before anything is posted. Comments accept tables, strikethrough, highlighted code blocks, TeX formulas, custom emoji packs, and Giphy GIF search. On submission, a sanitizer strips scripts and styles while Akismet, per-IP rate limits, keyword and IP block lists, duplicate detection, and reCAPTCHA or Turnstile screen for spam, and an optional review queue holds the comment back until a moderator approves it. The site owner then hears about it by email, WeChat, QQ, Telegram, PushPlus, Discord, or Lark, and the commenter receives reply emails. Once published, readers react with up to nine emoji and sort threads by latest, oldest, or hottest, while pageview and comment counters can appear anywhere on a site and recent-comment and top-commenter widgets fill sidebars. Moderators edit, approve, flag, or delete from the web admin panel, manage users and custom labels, and import earlier discussions from Disqus, Twikoo, Valine, Typecho, Artalk, Commento, or WordPress. Comments stay in your own database, and the widget offers a dark theme and ten languages. 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.

With over 31,600 GitHub stars and thousands of production deployments, InfluxDB 3 Core is the open-source time series database rebuilt in Rust on the FDAP stack — Apache Flight for high-throughput data transfer, DataFusion for vectorized SQL query execution, Arrow for columnar in-memory representation, and Parquet for compressed columnar storage. The engine delivers sub-10ms query response times on recent data and handles millions of writes per second through line protocol ingestion over HTTP, with unlimited tag cardinality eliminating the high-cardinality limitations that plagued earlier InfluxDB versions. The diskless architecture persists data as compressed Parquet files to S3-compatible object storage, Azure Blob, Google Cloud Storage, or local disk with configurable partitioning strategies, while the write-ahead log and in-memory buffer serve real-time queries against recent data before compaction. Native SQL support through DataFusion includes window functions, CTEs, subqueries, and joins, while InfluxQL maintains backward compatibility with existing InfluxDB 1.x and 2.x applications through the same query API. The embedded Python VM enables processing engine plugins and triggers that execute custom logic on write events, perform cross-database queries, and transform data in real time without external tooling. Flight SQL clients provide high-performance query access from Python, Go, Java, and Rust, and the HTTP API supports writes in line protocol format compatible with Telegraf's 300+ input plugins. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT/Apache 2.0 dual-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.

Baby Buddy is a private self-hosted child care tracker that centralizes feeding sessions, sleep cycles, diaper changes, and developmental health milestones into a collaborative dashboard for parents and caregivers. Caregivers can start quick timers on mobile devices to measure nursing intervals, bottle feedings, naps, and tummy time sessions with single-tap precision. The dashboard automatically calculates daily averages, feeding amounts, and awake windows to help families establish consistent daily sleep and feeding routines. Parents can track diaper changes by recording wetness, stool consistency, and color anomalies to spot digestive health changes early. Physical measurements including weight, height, and head circumference plot directly against World Health Organization growth curves to visualize percentile progression between pediatric visits. Multi-child profiles allow families with twins or multiple young children to switch contexts instantly and monitor individual growth timelines. Granular user permissions let parents invite nannies, babysitters, and relatives with restricted logging permissions while keeping administrative settings private. The built-in REST API and webhook system enable physical smart button clicks and home automation routines to log events instantly without opening a browser. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. BSD-2-Clause licensed.

Keep users ahead of outages by consolidating infrastructure monitoring into Peekaping, a unified uptime monitoring and incident communication platform that alerts engineering teams to network and application failures before customers experience disruptions. Users can configure automated synthetic checks across HTTP endpoints, database engines, message queues, and container runtimes to verify response latency, payload integrity, and SSL certificate expiration. When performance thresholds degrade or connections drop, the platform broadcasts structured incident notices across twenty-two notification channels including Slack, Discord, Telegram, PagerDuty, and custom webhooks. Visual dashboards display live heartbeat timelines, historical latency percentiles, and rolling availability scores for each monitored endpoint. System administrators can assemble custom public status pages with custom domains, branded color schemes, and component grouping to inform external stakeholders during planned maintenance or unforeseen service degradations. Teams can schedule recurring maintenance windows to pause alert notifications during routine deployments and generate API tokens to automate monitor creation directly from CI/CD deployment pipelines. 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 over 10,000 GitHub stars and a reputation forged in the frustration of laggy corporate screen sharing, Screego delivers what Microsoft Teams and Zoom screen share consistently fail to provide: instant, high-resolution screen streaming that lets remote colleagues actually read your code. Built on WebRTC peer-to-peer connections, Screego transmits screen data directly between browsers without routing through centralized servers, achieving sub-second latency and native-resolution quality that makes pair programming and code reviews genuinely productive. The server component, written in Go with a TypeScript frontend, deploys as a single binary or Docker container with minimal configuration — set your external URL, generate a secret key, and you're live. An integrated TURN server handles NAT traversal automatically, eliminating the need for separate STUN/TURN infrastructure, with configurable UDP port ranges and support for external TURN servers when scaling beyond a single instance. Authentication supports three modes — requiring login for all actions, only for TURN connections, or none — with user management via simple credential files. Rooms are created instantly and support multiple simultaneous viewers, with system and tab audio sharing available for demonstrations that need sound. The architecture supports reverse proxy deployment behind Nginx, Caddy, or Apache with automatic TLS termination, and recent releases added riscv64 architecture support alongside existing amd64 and arm64 builds. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-3.0 licensed.

Hosting a Minecraft survival world, a Terraria server, and a Palworld host no longer means juggling SSH sessions and screen windows, because MCSManager puts every instance behind one web panel. A built-in marketplace installs game servers from ready-made templates, filtered by operating system and tagged with the Java version each one needs, while any Docker Hub image, uploaded ZIP archive, or plain process can run as an instance with its own start command, stop command, and live terminal. Docker instances get memory, CPU, port mapping, and volume settings, and each instance can auto start, auto restart, and run scheduled tasks. For Minecraft servers, the plugin and mod manager (Beta) searches Modrinth and CurseForge, and the file manager handles maps, configs, and uploads. Administrators create user accounts and assign instances to them, so friends or paying customers only see their own servers, which suits small hosting businesses that sell game servers. Extra machines join as nodes and connect to the same panel, and the drag-and-drop dashboard can be rearranged to taste. The interface supports many languages. 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.

Pinpoint distributed system bottlenecks across polyglot microservices using Uptrace, an open telemetry monitoring platform that correlates traces, metrics, and logs inside a unified diagnostic dashboard. Engineers can track end-to-end request flows across polyglot microservices, inspecting database queries, third-party API calls, and internal function calls with sub-millisecond precision. The platform automatically aggregates spans into high-level latency percentiles, highlighting p50, p90, and p99 bottlenecks while calculating baseline error rates across production deployments. Integrated log correlation links log entries directly to parent trace spans, eliminating the friction of manual search across separate monitoring tools during active outages. You can construct custom dashboard views using a visual query builder, monitor cluster nodes, and map out upstream and downstream service dependencies with interactive topological graphs. Automated alerting channels notify on-call teams via Slack, Telegram, webhooks, or email whenever error budgets or metric thresholds trigger an incident. 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.

A web interface for a folder of Markdown files - Flatnotes is exactly that, and the discipline of that design is why people love it. Every note is a plain .md file in a single flat directory: no database, no proprietary format, no hierarchy to maintain, no export step if you ever leave. Edit notes in the browser or open the same files in VS Code or Obsidian, sync them with Syncthing or rsync while the app is running - the Whoosh-powered search index synchronizes incrementally, so external edits just show up. The interface is a clean Vue.js app with both WYSIWYG and raw Markdown editing modes (TOAST UI Editor), instant full-text search behind the "/" shortcut with partial-match support, wikilinks for cross-note references, and automatic tag extraction from #hashtags in note bodies. Light and dark themes and a mobile-responsive layout make it pleasant everywhere. Authentication is flexible for a personal tool: none, read-only, username/password, or TOTP two-factor. A documented REST API covers create/read/update/delete for automation. The operational story is the quiet selling point - the only state is the notes folder and a rebuildable index, so backup is copying a directory. For a personal notepad that respects your data, Flatnotes nails minimal.

Portabase takes a zero-trust approach to database backups: lightweight Rust/Tokio agents deploy next to each database, encrypt dumps with AES-GCM before data ever leaves the host, and poll the Next.js control plane outbound every five seconds requiring zero inbound firewall rules. This architecture contains blast radius if the dashboard is compromised while supporting ten engines with stable backup and restore: PostgreSQL 12 through 18, MySQL 5.7 through 9, MariaDB 10 and 11, MongoDB 4 through 8, SQLite 3.x, Redis 2.8+, Valkey 7.2+, Firebird 3.0 through 5.0, Microsoft SQL Server 2017 through 2022 including Azure SQL, and Docker volumes on Engine 20.10+. Encrypted backups store on configurable backends including local filesystems, any S3-compatible provider (AWS, MinIO, RustFS), Google Cloud Storage, and Azure Blob Storage. Cron-based scheduling with Grandfather-Father-Son retention policies automates backup lifecycle management, while on-demand restore targets any compatible server for cross-environment recovery. The CLI installs agents with a single command and auto-updates when new versions ship. A RESTful API with MCP server integration enables automation from CI/CD pipelines and AI agent workflows. Developed by a non-profit under Apache-2.0. 1,270+ stars and 174 releases since October 2024. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console.

tirreno watches what accounts actually do inside your product, then surfaces the ones that look like account takeover, credential stuffing, fake signups, or insider abuse. Your backend reports events such as logins, registrations, page views, searches, email changes, and field edits through an SDK or one HTTP call, and a scheduled job turns them into per-user context: devices, IP addresses, sessions, and connected identities. Preset rules cover account takeover, credential stuffing, content spam, bot detection, multi-accounting, promo abuse, dormant accounts, API protection, and high-risk regions, and you can add rules of your own. Each rule adds to a risk score, and thresholds decide whether a user is flagged for manual review or suspended automatically. The review queue lists who needs a look, and the single user view shows behaviour patterns, risk scores, connected identities, and an activity timeline. A field audit trail records what changed and when, which supports compliance reviews, while the logbook lists every API request the instance received. Your application can ask a blacklist endpoint whether a user or IP should be blocked before it responds. An optional IP enrichment pack adds geolocation, ISP, and VPN or proxy detection. All event data stays on your own 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.

Most AI chat integrations bolt an LLM onto a text box and call it customer support; AgentDesk builds the entire helpdesk around AI agents that handle first responses, escalate to humans when they cannot answer, and track follow-up work through integrated ticket workflows. Each AI agent binds to a specific LLM configuration, one or more knowledge bases, a set of callable Skills, and MCP tool integrations, creating specialized support personas for different product lines or departments. When a customer message arrives, the agent retrieves relevant FAQ entries and document chunks through RAG-powered vector search (Qdrant), then passes retrieved context through an Answerability Gate that determines whether the knowledge base can support a reliable answer; if not, it triggers a fallback response and recommends human handoff instead of hallucinating. Human agents pick up escalated conversations in a dedicated workspace that preserves the full AI conversation history, customer profile, conversation tags, and linked tickets, so they never start from scratch. The ticket system converts conversations into tracked work items with category assignment, status flows, progress notes, and team routing. An admin dashboard provides user management, role-based access control, team scheduling, and automatic conversation assignment rules. Model configuration supports any OpenAI-compatible provider, letting you wire in LLMs, embedding models, and reranking models with per-model context limits, timeout settings, and rate controls. 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.

Bring your own API keys and work with OpenAI GPT models, Anthropic Claude, Google Gemini, Mistral, DeepSeek, Grok, Azure endpoints, and local models in one organized workspace: TypingMind is a unified chat frontend for large language models, replacing a browser tab per provider. Parallel chat sends the same prompt to multiple models and compares answers side by side, and models can be switched mid-conversation. A prompt library stores reusable, tagged prompts with variables, and the AI Agents system builds specialized assistants that bundle a base model, custom instructions, assigned plugins, and uploaded knowledge files for RAG. Plugins extend every connected model with web search, image generation (DALL-E, Stable Diffusion), Deep Research, URL reading via Firecrawl, and Zapier automation - plus MCP server integrations for Notion, Atlassian, and other external tools, and a JavaScript extension API for custom behavior. Chats store locally by default with optional sync. Self-hosting puts the interface on your own domain and, for teams, adds branding, member access limits, and shared prompt and agent libraries.

Build, deploy, and monitor chatbots and LLM-powered agents on one open-source conversational AI platform: Botpress. Its Studio is a visual development environment: a drag-and-drop canvas arranges conversation logic with nodes for messages, questions, choices, and actions, while a built-in emulator simulates conversations for debugging before anything goes live. Agents ground their answers in a knowledge base assembled from uploaded documents, ingested websites, and past conversations via retrieval-augmented generation, and the LLM layer connects to multiple model providers - GPT-4, Claude, Mistral - with a configurable model strategy. An autonomous engine handles reasoning, tool orchestration, persistent memory across sessions, and sandboxed code execution, and custom code actions in TypeScript extend agents past prebuilt workflows. Over 100 integrations deploy the same bot to WhatsApp, Telegram, Slack, Microsoft Teams, and web chat, and connect it to HubSpot, Zendesk, Zapier, and arbitrary APIs and webhooks. Human handoff, conversation analytics, and quality monitoring cover production operation. Originating in 2017 from a Montreal team, the community edition is developed openly on GitHub.

Mixpanel, OneSignal, and Crashlytics in one self-hosted stack - Countly is an all-in-one product analytics and engagement platform where every byte of first-party data stays on your server. A Node.js application over MongoDB, it collects through ten battle-tested SDKs spanning iOS, Android, web JavaScript, React Native, Flutter, Unity, and desktop (plus a data write API for anything else), and has powered tens of thousands of mobile, web, and desktop apps since 2012. The analytics core covers sessions, custom events, views, user profiles, and real-time dashboards, with exploration tools built for product managers as much as analysts. What separates Countly from pure analytics tools is acting on the data without third parties: built-in push notifications send automated, transactional, and personalized messages to iOS (APNs), Android (Firebase), and Huawei devices, with the SDK handling token retrieval and permission flows automatically; crash reporting captures symbolicated native crashes on iOS and Android plus JavaScript errors, correlated with the same user and session data. Email reports keep stakeholders updated, and the plugin-based architecture means features load as modules. For GDPR-sensitive products, engagement without piping user data to advertising companies is the entire point. AGPL-licensed server, installable in minutes.

CKAN lets governments, research institutions, and companies publish data as a searchable catalog, where every dataset carries its description, license, tags, and downloadable files. Organizations own their datasets, and members, editors, and admins get different rights, so a dataset can stay private until someone with publishing rights releases it. Visitors narrow results with faceted filters on tags, formats, and organizations, or write fielded queries with wildcards and fuzzy matching. Resource pages preview spreadsheets in a grid and, when the data fits, as maps and charts, and they also display images, PDFs, and HTML. The DataStore keeps tabular resources as queryable tables, serving filtered rows with range conditions and nested AND/OR logic. Everything the web interface does is also available through the Action API. Groups gather related datasets, and custom metadata fields extend each record. Per-dataset activity streams document how data changes, and follow buttons feed a personal news feed. Files can be stored on local disk or, with extensions, in S3, Google Cloud Storage, or Azure Blob Storage. Extensions add geospatial search, harvesting for federated portals, multilingual metadata, and more chart types, and themes restyle the portal to match your brand. 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.